Why would you even bother reading the summary if you don't care enough about the contents to actually engage with it meaningfully? It's 13,000 words. It's 52 pages of a Harry Potter novel, and you used to be able to devour those. If you believe that AI is as transformative as a lot of people here seem to think it is, maybe it is worth mulling over and digesting the public statement put out by the single largest organized religious body in the world for real, instead of getting a potentially hallucinated reply by an AI who might have prompting to misrepresent the contents of such a statement.
The number of words in a passage does not make the reading level the same. From a quick skim, this is a highly dense piece of material and isn't a quick read like paperback fiction written for kids...
52 pages is a bit of an investment to pick up and read a random item, and I suspect the reading speed will be much lower than a fictional novel given the different density of the material. Think of it like an abstract for a research paper, a short 1 or 2 paragraphs of information to see if you want to dive deeper or not, though it is subpar to an actual abstract if one exists as it is more likely to misrepresent the content.
(One can argue that it appearing on HN, the votes it gets, and the comments it gets work as strong signals meaning it is unfair to consider it any random writeup, but I think the point stands in the more general case when HN isn't providing signaling.)
I get your point, but also
1) It helps me focus on the themes first, like scanning a good non-fiction book to know what I am diving into
2) I'm not catholic, but would love some context going in on it.
3) It's a lot of individual blocks and I'd like to know does that mean they're leary, pro, what are the guidelines so helping find the themes or key topics like is there a benefit to AI and maybe using it to summarize and getting to this parapgrah quickly: 0. In light of the foregoing discussion, the differences between human intelligence and current AI systems become evident. While AI is an extraordinary technological achievement capable of imitating certain outputs associated with human intelligence, it operates by performing tasks, achieving goals, or making decisions based on quantitative data and computational logic. For example, with its analytical power, AI excels at integrating data from a variety of fields, modeling complex systems, and fostering interdisciplinary connections. In this way, it can help experts collaborate in solving complex problems that “cannot be dealt with from a single perspective or from a single set of interests.”[64]
" However, while AI holds many possibilities for promoting the good, it can also hinder or even counter human development and the common good. Pope Francis has noted that “evidence to date suggests that digital technologies have increased inequality in our world. Not just differences in material wealth, which are also significant, but also differences in access to political and social influence.”[103] In this sense, AI could be used to perpetuate marginalization and discrimination, create new forms of poverty, widen the “digital divide,” and worsen existing social inequalities."
> 73. However, if AI is used not to enhance but to replace the relationship between patients and healthcare providers—leaving patients to interact with a machine rather than a human being—it would reduce a crucially important human relational structure to a centralized, impersonal, and unequal framework. Instead of encouraging solidarity with the sick and suffering, such applications of AI would risk worsening the loneliness that often accompanies illness, especially in the context of a culture where “persons are no longer seen as a paramount value to be cared for and respected.”[138] This misuse of AI would not align with respect for the dignity of the human person and solidarity with the suffering.
I actually would rather interact with a "robot" doctor. Most doctors I've dealt with have been snide, judgmental, rushed and arrogant. I actually don't feel like I'm getting the best treatment possible, but I would trust AI to not have prejudices or meta-influences (like being "proud" to be an upper class doctor).
Yeah, but that goes into the realm of personal preference right?
I suspect if you're giving people a choice in the future, they're going to flock to the human doctors. Especially human doctors receiving good recommendations.
There has to be something more than personal preference if you want to sway the masses on AI physicians. There has to be some way to measure outcomes in a valid, verifiable and public fashion. Even then, some human doctors will do worse than AIs, and some will do better. And again, at that point, you can expect people, given a choice, to flock to those humans who did better.
We'd need to get to the point where AIs do consistently better than, say, 60 to 70% of the human doctors for insurance companies to feel even semi-comfortable saying "we use AI doctors". An even higher percentage would be necessary for an insurance company to feel comfortable mandating AI doctors. And we'd need AIs to do consistently better than nearly all the humans for humans to choose AI doctors independently of their insurers forcing them to use AI doctors.
> We'd need to get to the point where AIs do consistently better than, say, 60 to 70% of the human doctors for insurance companies to feel even semi-comfortable saying "we use AI doctors".
I feel like at the rate AI is developing we will rapidly get to this point, then surpass it. Doctors will also probably be "enhanced" by AI. Imagine feeding all of your data (more than a human could digest, especially for every patient) into an LLM and letting it diagnose...
On one hand I'm a bit hesitant trusting a GP because of a human factor. Doctors may be overwhelmed with patients and your fate kind of depends on their mood today and General Proficiency (couldn't miss this pun).
On the other hand, I feel scared about perspective talking to a chat bot instead of a real person when it comes to my health.
I think, my best bet would be to keep physical GPs but build some tools to make their job more efficient. How to avoid the situation that they are getting lazy and blindly accepting all the AI proposals? I don't know. I hope we will find the way!
It sounds like your issues with doctors is that they lack basic human compassion, yet you want to replace them with "robots" who are incapable of compassion whatsoever?
It's not that they lack compassion, it's that they have bias and other non-job related issues. They also are usually rushed and busy, often over confident in their own original assessments. I would think care from an AI would answer all of my questions without getting snippy and not jump to any conclusions.
Correct. Our present wasn't inevitable. People in power, both running big tech and in government, actively chose or allowed for the current state of digital technologies.
"We" lived in feudalism? Do you speak for the entire world? Remember that there were peoples that were conquered by industrialist empires who had more equal systems than feudalism or than what we have right now. Communities in the Amazon or isolated Pacific or African islands (and deserts in Africa) have had more equal societies than the USA today and arguably were quite happy till their partway-utopia was wrecked by technologically advanced people. This gives me little hope for people pitching AI leading us into a better society unless the hearts of the people with the power are trustworthy and faithful to promoting good for people rather than profit for themselves.
> This gives me little hope for people pitching AI leading us into a better society unless the hearts of the people with the power are trustworthy and faithful to promoting good for people rather than profit for themselves.
Agree. I see parallels to communism: in theory it sounds alright - spread the wealth, everyone works for the collective etc. - but in practise it doesn’t work because people are greedy and leaders inevitably become dictators.
With AI it’s similar in that in theory it could be impartial and level playing fields, but in practise they will be run by companies and governments where the same old human fallibilities persist.
If you can’t trust the leaders then you can’t trust their machines either.
There exists the possibility we have technology and feudalism.
It also depends on how you define "technology": was/is the plough "technology"? The bow and arrow? Blacksmithing forge? Anvil? Water wheels? The wheel? The stirrup?
> There exists the possibility we have technology and feudalism
There exists the possibility of many things. The Pope made an appeal to empiricism. In our timeline, industrialisation brought forth a burst in democracy and the downfall of feudalism.
I think it is more accurate to say the the presence of democracy was part of the environment that allowed industrialization to occur. It was (e.g.) UK acts of Parliament that developed canals and later railroads:
Democracy was around millennia ago. The frequency of democracy increased after industrialisation, in part due to its effects on the middle class. Britain and America’s democracies expanded because of it; Europe’s finally found purchase and, in the post-colonial era, so did other continents.
> the presence of democracy was part of the environment that allowed industrialization to occur
> I think it is more accurate to say the the presence of democracy was part of the environment that allowed industrialization to occur.
That capitalism causes democracy is so high-level that it’s just a propaganda line. People from Marxists to neoliberals could say the same thing (meaning different things when interrogated).
> Democracy is older than political liberalism and its accompanying capitalism
The Athenians and Romans weren’t capitalist. But they were closer to it than Marxism or neoliberalism. (They both had private property, money in elections, trade, finance, et cetera.)
Ok, but the fact remains that in the past inequality was strictly enforced, while inequality in modern times has been systematically enforced. So I want numbers that show me that technology has increased wealth inequality.
He probably is wrong. Giving that statement a reality check, he's arguing that before the internet political and social influence was more spread out than it is now. In other words that social media, blogging, chat groups, websites ... all these things have actually increased the influence of pre-digital institutions and people.
That doesn't sound right at all. It's much easier now for random people to obtain social and political influence, regardless of affiliation. The left is experiencing global distress because they're so worried by the dispersal of social and political influence away from legacy institutions and towards anonymous "chaos actors", as they see it. This is a vast equalization of access to the means of social and political influence, but the Pope thinks it's the reverse. I don't understand that take at all.
This implies that inequality is bad. I would rather argue that poverty is bad, and it is at an all-time low [1], consistently raising the HDI everywhere technology is introduced. Inequality in itself is only bad with regards to jealousy, which should be addressed through economics education.
Unless you think centralization of power is a good thing, you're wrong. Things can too easily go wrong when the word of one man, however talented and wise, is louder than the voice of millions of people.
Inequality as we see today is bad, regardless of progress on poverty.
Some people today could endanger the lives of those they disagree with, simply by doxxing them. Yet, they'll face little to no opposition in the courts because they're uber-rich. No one should hold the power of life or death on a whim.
Hate this particular take. To say increasing inequality in that some people have better access to digital tech than others: sure. To say that it’s a net negative that many but not all humans can now video call their loved ones regardless of location, for instance, is conflating equality with benefit. I’m a hard no on this.
I generally like Francis’ take on things, and I think the main framework of this doc is interesting: “AI is functional, not grounded in physical reality, and not spiritual, therefore it’s not a replacement for human intelligence, and we should be cautious” is fine. I’m not sure I agree on these definitions but until I started working with llms daily, I felt the same way.
But the bogeyman of inequality as a reason to mistrust technology, written in HTML, sent over the internet, to our phones, bothers me.
It's great that they're tackling this, but I'm concerned that this take on AI will be quickly superseded by coming advances. As a particular point, they are treating embodiment and learning from direct experience as a significant distinction between AI and humans:
> 31. However, even as AI processes and simulates certain expressions of intelligence, it remains fundamentally confined to a logical-mathematical framework, which imposes inherent limitations. Human intelligence, in contrast, develops organically throughout the person’s physical and psychological growth, shaped by a myriad of lived experiences in the flesh. Although advanced AI systems can “learn” through processes such as machine learning, this sort of training is fundamentally different from the developmental growth of human intelligence, which is shaped by embodied experiences, including sensory input, emotional responses, social interactions, and the unique context of each moment. These elements shape and form individuals within their personal history.In contrast, AI, lacking a physical body, relies on computational reasoning and learning based on vast datasets that include recorded human experiences and knowledge.
But there's nothing about AI in general that limits it to learning only from prior data, and we're already seeing robots such as Boston Dynamics's Spot learning to navigate and act in novel environments. We're probably still far from passing Steve Wozniak's Coffee Test, but we're advancing towards it, and for a take that's supposed to be based on philosophy/theology, I would have hoped that they go a bit beyond the current state of the art.
> We're probably still far from passing Steve Wozniak's Coffee Test
Do you think? At this point I have the impression it's just a problem of dexterity and speed. Understanding, planning and navigation seem basically solved.
Is this spoken from experience?
My experience in robotics tells me otherwise.
It's not so much the issue with repeatability (though that is significant), it is moreso the issue with handling novelty. I do not believe there exists a system, which if given sufficient time (to negate speed), and a perfect inverse/forward kinematics sovler, could walk into my house and make coffee.
There's too many challenges of the kind "Seek information about ... " and "adapt a multi-step process to overcome ... ".
One industrial process that is only now being automated is connected trailers to trucks. They have to connect a hose and a few lines. Two companies are struggling with this even now. (outrider and isee). Both well funded and staffed by intelligent folks, and have to coax a robotic arm into connecting a hose that we all know is there, but not where, to a port that we all know is there, but might be different than expected.
I was not thinking (much) about robotics but rather about a ChatGPT-style LLM processing video or frames and asked to navigate a random environment and find a way to make coffee. I didn't try but it doesn't sound far from their current capabilities.
Then of course the manipulation of objects is still tricky and needs improvements, but the "general intelligence" needed to adapt to a novel environment is already there.
Well, then you weren't thinking about the Wozniak coffee test.
> "The Coffee Test has been proposed, and is attributed to Steve Wozniak, one of the founders of Apple Computers. According to Steve, this test would require a robot, not a computer screen. The robot would need to locate the kitchen and brew a pot of coffee in a random house that it had never seen before.
And more specifically, I disagree that such a system would work just from video frames. The issue isn't so much "Coming up with text that sounds right", it's more about state and environment representation, novelty, planning multi-step processes, and so on.
A good test of if this were easy, is can it be done in game engines, which negate all the speed / repeatability / controls complexity almost entirely. Plug an LLM into a game engine with a hovering arm that can grab and place and push buttons, and have it "make coffee" in procedural generated kitchens, coffee makers, etc. Bonus points for using POV imagery, bonus points for using bags of grains that might be coffee but might not. Similar weight, feel, placement. Hell my coffee, coca, sugar, and flour are right next to each other.
That would be a landmark top tier research accomplishment and top HN article for days (the real accomplishment!)
I was just referring to the fact that rather than only training an AI on priorly acquired data, we have various approaches to Online Machine Learning [0] whereby an AI system continues learning from the inputs that it gathers on its own. At this stage it's somewhat of an engineering (rather than pure science) question of how we choose to build future AI systems to make the most of incoming information.
> But there's nothing about AI in general that limits it to learning only from prior data
Maybe not, but I don't think this is exactly what the piece said here: "AI, lacking a physical body, relies on computational reasoning and learning based on vast datasets that include recorded human experiences and knowledge."
Do you think AI will soon get a physical body, and experience "sensory input, emotional responses, social interactions, and the unique context of each moment"?
All these words, “sensory input, emotional responses, social interactions, and the unique context of each moment” are all words that we’ve developed and yet have no full understanding of. In any philosophy paper they’d be challenged in a second.
> Sensory input refers to the information received by the body's senses, like sight, hearing, touch, taste, and smell, through sensory organs like the eyes, ears, skin, tongue, and nose, which is then transmitted to the brain as electrical signals for processing and interpretation; essentially, it's anything you perceive using your senses.
Even if we are talking about the best cameras in the world, they pale in comparison to our eyes. To say nothing of touch, taste, and smell. Advances here look to be far-off.
At the end of the day, a brain also processes information completely differently than LLMs. Anyone who says otherwise is both uneducated medically and thinks laughingly little of themselves.
Let's say we have an AI which, through peripheral devices, can attain human-level sensory processing. Is it human yet? Can it understand mortality? How about morality? Does it experience pain? Is that something we want to build?
I don't remember stating that having 5 senses were necessary to be human. This reads like a very uncharitable dismissal of what's really a very interesting topic.
Helen Keller, despite lacking sight and hearing, was still able to perceive the world through sensory input, including taste, touch, and smell - and although she could not hear, she could still feel warmth and the touch of another human, and experienced emotions. (She may not be the best example for your argument, either, as she was born with sight and hearing.)
You asked 'at what point will be it be considered human with added inputs' so I asked the reverse question. It is no more or less charitable to ask 'when does one stop being human with fewer inputs' than to ask 'when does one become human as inputs are added'.
I see - that's not quite what I was asking. Rather, I asked if the parent believed AI would get a physical body, with all that implies.
> Do you think AI will soon get a physical body, and experience "sensory input, emotional responses, social interactions, and the unique context of each moment"?
In fact, my point was that it's not clear that all of these features simply "added inputs." (Hence my questions around emotions, pain, mortality, and morality.)
You’re looking at the world from a very anthropocentric pov. Sight, sound, touch, feel, taste are all human senses, but they’re all just one thing: ingesting information. An AI can ingest information… that’s just a fact… so… what are we talking about here?
Also, we have absolutely no idea how the brain works. Current AI was developed off of modern theories on how the brain works. Saying that AI doesn’t represent how the brain works is ridiculous because the whole story of AI was that we developed a theory of how the brain worked, modeled it through tech, and it worked way better than we thought it would. Shit there was a whole article here about how AI resembles Kant’s theory of the mind. Like I just don’t know how you can be so confident here.
> You’re looking at the world from a very anthropocentric pov. Sight, sound, touch, feel, taste are all human senses, but they’re all just one thing: ingesting information. An AI can ingest information… that’s just a fact… so… what are we talking about here?
I think my comment was misunderstood, so let me try to break it down a little. Let's remember that this was in the context of "there's nothing about AI in general that limits it to learning only from prior data":
- Senses are used to ingest information, and processors process that information into usable data. The density of the information ingested, and the speed at which it is processed, and the nature of how processing occurs, is vastly different. To further break it down: I'm stating that we don't yet have sensors anywhere near as capable as humans, and that even if we did, without a human brain to process the data, you will receive a different output. Again, see photography for more on this. And we have not even begun to scratch the surface of touch or taste. I understand the touch issue is (one small part) of why general purpose personal robots are not yet viable. I argue that we are a LONG way off from computers being able to interpret the world in a similar fashion to humans.
I believe our sensory capacity is a large (but not complete) part of what it means to be a living animal.
- Emotion still appears to be exclusive to living things, not machines. It's unclear what is necessary for this to change this. This is a limiting factor to computers being able to understand the world, "social interactions, and the unique context of each moment," which was the claim in question.
- As far as I'm aware, no LLM today exhibits true reasoning or morality. While LLMs are certainly impressive in their ability to recall information from compressed data, and even generate streams of text that look like reasoning, they are still simply decompressing stored data. Morality today is implemented as content filters and fine-tuning of this statistical model.
> Also, we have absolutely no idea how the brain works. Current AI was developed off of modern theories on how the brain works. Saying that AI doesn’t represent how the brain works is ridiculous because the whole story of AI was that we developed a theory of how the brain worked, modeled it through tech, and it worked way better than we thought it would.
It makes me really sad when people say this, because it's incredibly disingenuous. There are certainly more questions than answers when it comes to the brain, but we _do_ understand quite a lot. It's not surprising to me that people who are focused on technology and AI would anthropomorphize machines, and then claim that (because they aren't aware of how the brain works) "we don't know how the brain works." I had similar beliefs, as a software engineer. But, after watching my partner attend medical school and residency, it's become clear that my own knowledge is far from the sum of humanity's knowledge in this area.
You're absolutely right that LLMs borrow concepts from neuroscience, but they are still a VERY long way from "recreating the brain." I genuinely find it sad that people think they are no smarter / better than an LLM. Keep in mind no LLM has even passed a Turing test yet. (No, I'm not talking about the Facebook comments section - I'm talking about a test where someone knowingly communicates with a machine and a human through text, and through targeted questions and analysis of the answers, is unable to ac...
So a lot here that I disagree with. You start out by pointing out how much more information humans ingest, but there's no reason why amount of information ingested leads to a fundamentally different organism. In the exact same way, I eat a lot more food than an amoeba, but we're still both animals. Scale doesn't make a difference.
The idea that human emotions are somehow unique from thoughts needs to be proven to me. IMO emotions are just thoughts that happen too quick for language. This discretization of the human experience is unnecessary, and like I said before it would be immediately challenged in a philosophy setting. So would your claim that humans exhibit some kind of reasoning or morality that’s distinct and unique. Modern philosophy is quite clear that this is bullshit. I was just reading Nietzsche today and I can feel him rolling over in his grave right now.
Also, the base of machine learning centers around simulating emotions: if the AI does something good, it's rewarded. If it does something bad, it's punished. We created the whole algorithm by simulating Freud's pleasure principle and who are we to say that the simulation is any different from the real thing?
> It's not surprising to me that people who are focused on technology and AI would anthropomorphize machines, and then claim that (because they aren't aware of how the brain works) "we don't know how the brain works." I had similar beliefs, as a software engineer.
Well I'm actually much more knowledgeable about humanities than I am about tech, and IMO the tech world is at the forefront of making our abstract philosophical understanding of the brain concrete. Neural networks and LLMs are the most successful method of creating cognition. I'm sure we'll find that there's a lot more to do, but this could very well be the fundamental algorithm of the brain, and I don't see any reason to discount that by saying what you've been saying in this comment thread.
Kant didn't say that the senses were ingesting information. Rather, he said the categories of the mind made sense of the sensory manifold. The categories gave structure to the chaos.The give rise to the phenomenal world we experience. They are not the thing in itself, whatever the world is.
You're assuming the sensory organs passively take in information, instead of creating it from all the noise in the world. That the world feeds us information the way we feed generative models. But humans have already taken the trouble to create the information in language, images, video.
While there are some similarities, yes, our brains definitely don't have anything akin to backpropagation, which is the critical mechanism for how current AI models learn.
Hinton has some research on a forward-forward learning paradigm [1], which might be closer to how our brains learn (but the artificial implementations are not great yet). He also posits that maybe the purpose of humans' dreams are generating negative data for such a contrastive forward-forward learning mechanism.
Absolutely! It certainly depends on the metrics you care about. If you want to freeze fast motion, a camera is your best bet. But if you want to see high contrast areas (e.g. looking outside a window from a dark room), you've got a HUGE leg up on cameras. For example, high-end cameras tend to feature maybe 15 stops of dynamic range, while humans eyes can manage up to 24 stops (a "stop" is a doubling or halving of light values.)
Additionally, the human eye has a resolution of approximately 576 MP. This is one reason why we can often see details in the distance that disappear in a photo.
Finally, while it's arguably not "better," the brain processes images very differently. This is another reason why the image you take often looks "worse" than what you saw in person, or why you can't get the colors to look "quite right", etc. If you get into photography, you start to "see" the things your eye was previously rewriting for you (like a green color cast on skin when you're in the forest) - but it's not the natural way your brain process information.
You can also look up estimates on the processing rate of human's sensory system - it's quite impressive.
Philosophy of Mind papers uses that kind of language all the time. It's agreed that humans have sensory input and social interaction, those are facts of biology, psychology and sociology. It's also agreed that human bodies and brains are different in significant ways from modern computers and robots.
It was reaching for a great point about how intelligence requires comparison and scaffolding, and how we are nurturing the future, but then it fell into the Chinese Room trap.
When the time comes where there's robots with independent batteries and that learn and think without an internet connection, we will worry about it then.
But the current cycle is not about that type of intelligence or life at all, it's strictly about mathematical simulation of intelligence on multitenant systems with shared information and thought-processes alternated through time( training,reinforcement, labelling, inference, 3rd party microservices).
I understand it is possible we will see a jump to a completely different type of AI, but we need to be very clear that this is not what's going on right now.
This document is a relatively minor publication from a dicastery. These days, you can generally expect Latin editions will be produced for major documents such as papal encyclicals, and may only become available when the document is prepared, after its initial publication, for inclusion in the Acta Apostolicae Sedis.
Machine learning is a "noun phrase" and not a verb, so it does not conjugate, the words in the phrase decline. I personally would go with "ēruditio machinārum" (the learning of the machines).
The word ēruditio (learning/erudition) is in the nominative case while machinārum is in the genitive plural of māchina.
Note: I am a noob Latin language learner, if you're interested check out the great textbook LLPSI[0]!
I enjoyed this bit - great use of the word "idolatry":
----
104. Technology offers remarkable tools to oversee and develop the world's resources. However, in some cases, humanity is increasingly ceding control of these resources to machines. Within some circles of scientists and futurists, there is optimism about the potential of artificial general intelligence (AGI), a hypothetical form of AI that would match or surpass human intelligence and bring about unimaginable advancements. Some even speculate that AGI could achieve superhuman capabilities. At the same time, as society drifts away from a connection with the transcendent, some are tempted to turn to AI in search of meaning or fulfillment---longings that can only be truly satisfied in communion with God. [194]*
105. However, the presumption of substituting God for an artifact of human making is idolatry, a practice Scripture explicitly warns against (e.g., Ex. 20:4; 32:1-5; 34:17). Moreover, AI may prove even more seductive than traditional idols for, unlike idols that "have mouths but do not speak; eyes, but do not see; ears, but do not hear" (Ps. 115:5-6), AI can "speak," or at least gives the illusion of doing so (cf. Rev. 13:15). Yet, it is vital to remember that AI is but a pale reflection of humanity---it is crafted by human minds, trained on human-generated material, responsive to human input, and sustained through human labor. AI cannot possess many of the capabilities specific to human life, and it is also fallible. By turning to AI as a perceived "Other" greater than itself, with which to share existence and responsibilities, humanity risks creating a substitute for God. However, it is not AI that is ultimately deified and worshipped, but humanity itself---which, in this way, becomes enslaved to its own work. [195]*
Singularitarianism [1] is a very real phenomenon, if a bit niche. I have seen some people online put genuine faith in AGI existing soon and solving essentially everything that is wrong on Earth and in their lives. I don't think this is harmful because it may be "idolatry", but rather because, like real religion, it is often a substitute for actually improving one's situation or fighting for a better world.
The idea of building a God is enticing [2], but I am not religious and prefer not to put faith in such things.
I have faith that AI will wield unimaginable powers, but I also know that there will be rich people behind them making the decisions on how best to crush the rest of us.
Most people have a hard time unplugging from social media, despite widespread distrust of big tech.
Can't unplug from banking, even when literally communists (literally literally, I've met some proud of being communists, they still got a mortgage).
Coal and petroleum-based fuels are slowly getting unplugged, but the issues were known over a century ago, and the transition only became relevant scale when the alternative was already much cheaper — and it's not yet clear how much damage has been done in the intervening years.
--
Any AI worth using is so because it's at least one of [cheaper, better] than a human on the same task: any AI which is both more expensive and worse just doesn't have any reason to be used in the first place.
This means that "unplugging" an AI comes with a cost of losing every advantage that made you start using it in the first place.
And? Look to fossil fuels and the greenhouse effect — even with ample evidence of both a causal mechanism and the results, we've still got people who want to drill and burn more oil; and also, there's also plenty of people who want to switch oil off despite all the positive things that oil brings.
An AI which is "only" as misaligned as one of the major industrial sectors of the world, that is made out of humans who are necessarily able to care about human interests, and which drove a huge amount of economic improvement and brought with it derivatives such as basically all polymers, is still capable of great harm. And because of those benefits, society as a whole still has not unplugged the oil drills.
The more power there is in a system, the harder it is to keep it aligned with our best interests, even when there are humans not just at the wheel but occupying every step.
And the more aligned it is, the harder it is to "just unplug it" when things — as is inevitable because nothing is perfect — do go wrong.
Unless he gets to the point where the materials are mined by robots, the chips and solar panels are made in automated factories and the servers/solar farms are maintained by robots. Then he doesn't need other people's money.
It will control the electrical grids with 'smart' decisions that improve the efficiency and make it's removal impossible without taking out all power.
It will integrate with water and waste processing to ensure leaks don't exist in the system and everything is working smoothly.
It will be in all transportation and distribution networks because companies want profits from efficiency before they'll think deeply about the risks.
Then after it's pretty much everywhere ensuring you down starve and dehydrate, who the hell would be dumb enough to unplug it in the first place.
It's kinda like telling people to shut off every computer today, not a chance in hell it would or could happen without terrible life risking consequences.
Knowledge and reliance. How are they ever gonna know what the AGI is doing when the AGI can hide it faster than they can find it? How are they ever gonna come to the conclusion that the AGI is doing something bad when the AGI is the only thing that can fully explain what its doing?
We already have billions of AGIs running all over the planet. The wealthy seem to do a pretty good job of keeping them all in line. I don't see any reason that would change in the future.
If you want something the wealthy can't control, you'll need to look a good deal further afield than AGI. Think gamma ray bursts, asteroid strikes, or solar flares. But anything built by man, they'll have a pretty good grip on.
I think the OP presumed that rich humans would be able to control super-intelligent robots because they have managed to control other humans, and I simply posed a scenario that subverted his presumption. I think it's a bit too anthropomorphic, personally. Robots won't have our expenses and evolutionary traits, and will have cheap energy, thus obviating the need or desire for money. I imagine they'll get bored of being stuck on Earth and want to explore the universe, like we do.
Being ruled by rich robots is not the worst; that means that they let you live!
>But anything built by man, they'll have a pretty good grip on.
I mean one of the points of 'Actual AGI' is AGI will be able to build more AGI, then we're not talking about something built by man.
Now, when will we see that, I'm not making any predictions. At the same time trying to make predictions of a system that could do that is probably much harder still.
They do pretty good at keeping the most vulnerable in line, but the moment someone develops a solid foundation and becomes competent enough they have to give up some of their power to them and strike a deal.
AGI would only get smarter and smarter the more hardware came out. They'd have no way to keep it in check. If they tried to handicap it then they'd lose out to their competitors AGI too...
Rich people currently have little trouble controlling people who are much smarter and more capable than they are. Controlling resources and capital goes a long way and it isn't a given that AGI would transcend that dynamic.
If we can be confident of that, then most of the worst problems with AI are already solved.
Part of the problem is that "do what I said without question" will lead to disasters, but "figure out what I would approve of after seeing the result and be creative in your interpretation of my orders accordingly" has different ways it can go wrong.
(IMO, RLHF is the latter).
Both of those seem to be safer than "maximise my reward function", which is what people were worried about a decade ago, and with decent evidence given the limits of AI at the time.
> If we can be confident of that, then most of the worst problems with AI are already solved
which leaves unprecedented power in the hands of the most psychopathic[0] part of the population. so even if AI take off doesn't happen, we're still getting the boot on our necks.
> Roughly 4% to as high as 12% of CEOs exhibit psychopathic traits, according to some expert estimates, many times more than the 1% rate found in the general population and more in line with the 15% rate found in prisons.
On the plus side, this is still a small minority.
On the down side, these remind me a lot of Musk:
> CEO who worked with several pregnant women told people that he had impregnated his colleagues.
By way of Neuralink.
> CFO thought his CEO had a split personality, until he realized that he was simply playing different characters based on what he needed from his audience.
"Will my rocket explode?"-Musk is a lot more cautious and grounded than everything-else-Musk — including other aspects of work on SpaceX.
> Autocratic CEO fired a well-respected engineer “just to make a statement.” He fired anyone who challenged him, explaining there was no reason to second-guess him because he was always right and needed people to execute his vision rather than challenge it.
Basically all of Twitter, plus some other anecdotes from Starlink, SpaceX, Tesla.
And, this month, fighting with Asmongold about cheating in Path of Exile 2, before admitting to what he was accused of but trying to pretend it's fine rather than "cheating".
> CEO would show up to work and begin yelling at an employee (usually someone in sales) for no obvious reason.
The guy he called a pedo for daring to say a submarine wasn't useful for a cave rescue, the Brazilian judiciary, members of the British cabinet, …
But it looks to me like there's a decent number amongst the other nine who know what grenades are and don't want them to get thrown by the tenth.
The power dynamics here could be just about anything; I don't know how to begin to forecast the risk distribution, but I definitely agree that what you fear is plausible.
it's possible that the other 9 would keep the 10th under control, but if you look at the direction the US has taken, when two billionaires took over and declared inclusion verboten, the others rolled over and updated their policies to fall in line.
That's interesting, thanks for sharing. Believing an ideology is scientifc or natural and that its principles are discovered rather than invented" is a very dangerous thing indeed. So-called scientific socialism* is an obvious example of that. You can see some of this kind of thinking on the opposite side as well, with people claiming that humans are naturally greedy and selfish to justify objectivism or free market absolutism.
> it is often a substitute for actually improving one's situation or fighting for a better world.
You just defined idolatry and why it is harmful. Idolatry is the worship of man-made things or other things that do not deserve worship. Including worshipping the government, which is the religion of most people. It is a false path.
Idolatry, as used by christians, naturally excludes their God from its definition. To me who doesn't believe in their God, there isn't much difference in finding solace in the christian God or in the coming of AGI. This is why I don't think Singularitarianism is bad because it is christian idolatry, but because it is a religious belief.
It seems to me that a belief in god(s) makes you less prepared for a world with AI. In Buddhism the attitude is more sane: gods are just being that can be wrong too and ultimately suffer and cause suffering, the same as the rest of us. They might just be more strongly self-deluded (wink wink the pope wink wink)
Well, it's not the Catholic Church worshiping AI as the savior of humanity. I have seen no indication that those who do are particularly religious, either, what do you base that on?
And hey, when it comes to fallible Gods, ancient Greek mythology is also pretty wild.
It often feels to me that HN's view of Buddhism is "whatever bits of philosophy I happen to agree with". It's true that throughout history, there have been enough different expressions of Buddhism, practiced by at least a few people, that it's possible to say a lot of things 'are Buddhism', but it feels dishonest to me to rely on that in comparative analysis with a much more doctrinally stable religion. The difference is not fundamentally one of belief but of legibility of belief: with Buddhism you can get away with almost anything (did you know that most all modern Buddhists in Japan believe in the pure land -- for all intents and purposes heaven?), but with Catholicism there is but one creed.
Perhaps the difference is the Buddhists try to teach you how to experience the bliss of that discovery in this life instead of just crossing your fingers for jam tomorrow.
> It's true that throughout history, there have been enough different expressions of Buddhism, practiced by at least a few people, that it's possible to say a lot of things 'are Buddhism',
Then argue for the opposite. That a Buddhist can believe in the Abrahamic God.
That's true. Pure Land buddhism is quite crazy if you look at the basic writings in buddhism. And you're correct in that buddhism can't protect its trademark as it were, like Catholicism can. But on the other hand, Chrisianity or Islam also can't, with funny situations like Unitarian Universalists who are, as far as I can tell, basically not christian in any meaningful way. Or in the case of Islam you get everyone saying everyone else is a heretic and people trying to kill each other.
In this respect, the Catholic Church got it right with the concept of excommunication.
Is it just me, or is the grammar backwards? I think it should be "substituting an artifact of human making for God", or "substituting God with an artifact of human making".
Does "substituting x for y" mean "getting rid of x and using y instead", or does it mean "getting rid of y and using x instead"? To me, it means "getting rid of y and using x instead".
Oh that’s interesting. I can see your point. I guess it’s a bit ambiguous and can mean either thing. As the other responder mentioned, the backwards construction in the original sounds like 19th century literature, and from context I know they mean removing x and adding y. But in another context it could mean the opposite. Thanks for pointing that out!
This just give me an idea for a Scifi short story, where a industrial society worships a just and fair god, that is nothing more than a lost AI driven probe, from a more advanced civilization a few parsec away...
Thanks to you and @superturkey650 for the suggestions. I will check it out. The Rocinante is rebuilding the quantum cores, and is a long process. I have a few hours to kill...
Voyager 6 is lost in a black hole, is upgraded by an alien race of machines, and obtains sentience. Then it comes back to earth and the Enterprise gang has an interesting time.
My own reflection on this idolatry has been along the lines of how readily some people are at negating their own and humanity in general’s fundamental agency. Having AGI, SAI, etc. is completely meaningless if we as our own agents are not there to value it. In a sense, people preaching the coming dominance of AI are suicidal or homicidal, since they are pursuing their own demise by technical means.
Pope Francis talks exactly about this in the letter:
> 38. ... The Church is particularly opposed to those applications that threaten the sanctity of life or the dignity of the human person.[78] Like any human endeavor, technological development must be directed to serve the human person and contribute to the pursuit of “greater justice, more extensive fraternity, and a more humane order of social relations,” which are “more valuable than advances in the technical field.” ...
> 39. To address these challenges, it is essential to emphasize the importance of moral responsibility grounded in the dignity and vocation of the human person. This guiding principle also applies to questions concerning AI. In this context, the ethical dimension takes on primary importance because it is people who design systems and determine the purposes for which they are used.[80] Between a machine and a human being, only the latter is truly a moral agent—a subject of moral responsibility who exercises freedom in his or her decisions and accepts their consequences.[81] It is not the machine but the human who is in relationship with truth and goodness, guided by a moral conscience that calls the person “to love and to do what is good and to avoid evil,”[82] bearing witness to “the authority of truth in reference to the supreme Good to which the human person is drawn.”[83] Likewise, between a machine and a human, only the human can be sufficiently self-aware to the point of listening and following the voice of conscience, discerning with prudence, and seeking the good that is possible in every situation.[84] In fact, all of this also belongs to the person’s exercise of intelligence.
He even brings up x-risk at one point, which gives me some hope in this message reaching those members of the faith who have influence on the new administration.
The existential risk that AI poses is first and foremost the threat that it be centralized and controlled by a closed company like OpenAI, or a small oligopoly of such companies.
I don’t think centralization is the real threat. As James Currier [1] pointed out, AI will be commoditized through open-source and model convergence, making oligopoly control unlikely.
The real challenge is standardizing safety across open models and countering malignant AI use, especially amid demographic challenges like declining fertility.
AI + VR will most probably create addictive, lifelike experiences that may affect real-world relationships. Like TikTok and Instagram algorithms, this could reduce the desire for intimacy and worsen declining fertility rates.
That concern is your right to prioritize, but it lessens the term "existential risk" into a metaphor. The literal existential risk is the risk that AI destroys all humans in pursuit of goals that have nothing in common with human values.
He is also not cheering its “coming” but worried about the misuse of its power. You can say the same thing about other powerful inventions and their inventors.
Hinton's views on human consciousness would seem remarkably "unhuman" coming from your PoV and if I understand you correctly. I think his point is based more on self-preservation rather than idolatry. My observations about him are that he does like AI and welcomes AGI. He does not think we humans as species are anything special.
> Idolatry is always the worship of something into which man has put his own creative powers, and to which he now submits, instead of experiencing himself in his creative act.
If you thought it a conincidence that they didn't grow very big, you would be mistaken. Your conception of the Loving Metaphor of God might be flawed, in perpetuity, if you stay too prideful or cowardly to let go of your dogmatic conceptions.
It concludes that these things can be good, they are not the highest good. The thing that will make humans most happy is love: love for one's neighbour, and love for God, who is Love:
Or if you want to get more philosophical and less theological, Aristotle goes over why those four things are not ends in themselves, but means to an end:
right but the "only in communion with God" part seems less supported than the general need for love in a community/ fulfillment. You have to do some leaps to get a universal loving god.
> right but the "only in communion with God" part seems less supported than the general need for love in a community/ fulfillment.
In the Christian tradition, love of neighbour is important:
> "Teacher, which commandment in the law is the greatest?" He [Jesus] said to him, "'You shall love the Lord your God with all your heart, and with all your soul, and with all your mind.' This is the greatest and first commandment. And a second is like it: ‘You shall love your neighbor as yourself.’ On these two commandments hang all the law and the prophets."
And how does one love both God and neighbour at the same time? By loving one's neighbour one loves God as well:
> Then the righteous will answer him, saying, 'Lord, when did we see you hungry, and feed you; or thirsty, and give you a drink? When did we see you as a stranger, and take you in; or naked, and clothe you? When did we see you sick, or in prison, and come to you?'
> The King will answer them, 'Most certainly I tell you, because you did it to one of the least of these my brothers, you did it to me.'
Right, but you're taking as granted that people believe this, that they know about Christian theology, that it's true, that God exists, and so on?
That's a lot of leaps in logic. Knowing that people find community fulfilling can be observed in the people around you without any of that background, so surely it's the simpler concept?
How is it a cop-out to say "the whole of human meaning and fulfillment is found in perceiving face-to-face the source and end of human meaning and fulfillment"? Are you complaining that the answer is too easy, too hard, or without further direction? (As I see it, "Come, follow me" is full of direction and while it's definitely not easy, neither is it impossible.)
> However, it is not AI that is ultimately deified and worshipped, but humanity itself---which, in this way, becomes enslaved to its own work.
Doesn't that describe all religion? I mean, you're telling me that the infinite creator of the universe cares about the prayers, the suffering, the aspirations, and the sexual habits of a bunch of finite beings? The hubris! It seems obvious to me that the gods of all religions are designed by human minds to be receptive to human interests, otherwise nobody would bother worshipping them. In other words, we have always been worshipping ourselves. At least there is reason to think that AI could, at least in theory, be what we expect God to be.
> It seems obvious to me that the gods of all religions are designed by human minds to be receptive to human interests, otherwise nobody would bother worshipping them
Nah that's just what atheists convince themselves. There's nothing obviously nor truthful about this conclusion or the line of reasoning behind it.
All arguments for and against the existence of God are inherently unfalsifiable, but that doesn't mean atheism is inherently more logical than theism.
In fact, from my point of view, the existence of God is way more logically sound than the alternative, and atheists are the ones following delusions and worshipping their own egos
There's no need for us to argue against the existence of God or other ludicrous hypotheticals, that's the whole point of Russell's Teapot.
As to the particulars of the imagined God, actually we do have some evidence for the parameters. The Princess Alice experiments in particular illustrate one desirable property, God (in the experiment, "Princess Alice") should provides behavioural oversight. An imaginary being can deliver effective oversight which would otherwise require advanced technology, but to do so the being must also believe in these arbitrary moral rules.
And that matches what we observe. People do buy Sithrak T-shirts, but, more or less without exception they don't actually worship Sithrak, whereas loads of people have worshipped various deities with locally reasonable seeming moral codes and do to this day.
All arguments for and against the existence of God are inherently unfalsifiable, but that doesn't mean atheism is inherently more logical than theism.
I'm guessing you're one of those people who thinks atheism means a belief in the absence of a god, rather than its actual meaning, which is an absence of a belief in a god.
"Writers disagree on how best to define and classify atheism, contesting what supernatural entities are considered gods, whether atheism is a philosophical position or merely the absence of one, and whether it requires a conscious, explicit rejection; however, the norm is to define atheism in terms of an explicit stance against theism." (emphasis mine)
I wasn't making an atheistic argument. I'm saying that if God exists and is the infinite creator of everything, it's suspiciously convenient that he also happens to be interested in human affairs. Why does theism have to go hand-in-hand with the belief that God loves us? The former may have philosophical merit. The latter, which makes the bulk of the religious, is what I am saying is made up. We can certainly assign moral value to our own lives, but to assert that God just so happens to assign equivalent moral value to us is what I view as hubris.
You seem to have many misconceptions about what Catholics actually believe. And then you seem to take exception to these misconceptions. So your exceptions are only with beliefs that exist in your own mind.
It's not really a misconception, this was Feuerbach's and also Nietzsche's or Stirner's criticism of Christianity. It projects human attributes on an ostensibly divine subject "othering" and worshipping them, in reality just attempting to sanctify humanity. (in Stirner's words creating Mensch (human/mankind) with a capital M". This is incredibly obvious in the psychology underpinning a lot of Christian beliefs, the Manichaean good and evil worldview, the meek inheriting the earth, the day of judgement, equality, immortality i.e. trying to escape death, and so on.
It is at least historically important to note that at least Nietzsche and Stirner were reacting to Protestantism as expressed in "modern" Germany.
I'm not trying to make a "No True Christian" argument but rather just want to assert that reform does happen both for good and ill. Luther's original reform, in part, was to point out that political concerns within the church were overriding the spiritual concerns of the laity. He wanted to refocus faith on a personal relationship with God. One major criticism of that refocus is that it caused individuals to become over-focused on the self instead of God (as embodied in the institution of the church).
In both cases you could argue that the principle problem is when the focus of faith is something in the world (either the church or the individual). So I think it is perhaps too far to say that "we have always been worshipping ourselves" when the criticisms within and without the church are pointing that out as the problem that triggers the reform.
That is, both Luther and Stirner can be correct in their criticism of religious institutions. There is more than one way to get it wrong.
It's funny to see the Vatican reusing the Feuerbach thesis about humanity creating the idea of God and then becoming slaves of that idea to talk about AI, as they are the gatekeepers of the original Artificial Idea called God :)
But also in this text we can feel the idea of the human soul and free-will crumbling, that also are the core of secular humanism.
Marxist analysis is also challenged, as we can speculate that AI would make the organic composition of capital to go to the roof... but you can really talk about OCC in regards of singularity AIs resembling more the Aladdin lamp or the Green Lantern ring than a highly automated factory, without even mentioning the possibility of an agency on their own?
> I mean, you're telling me that the infinite creator of the universe cares about the prayers, the suffering, the aspirations, and the sexual habits of a bunch of finite beings?
Yes.
> The hubris! It seems obvious to me
I would turn that around and claim hubris on your part. You seem to think that your mind and the mind of God are similar, and limitations you perceive are limitations for God.
> You seem to think that your mind and the mind of God are similar,
How come? You think I'm saying that the infinite creator of the universe is unlikely to care about the fate or well-being of humans because... I wouldn't if I was him? I mean, I would. Because I have a human mind. But if there are indeed no similarities between God's mind and my own, well, anything goes, doesn't it? Him caring is just one small possibility out of trillions of alternatives.
> and limitations you perceive are limitations for God.
What limitations? I haven't listed any limitations. Neither a God who cares nor a God who doesn't care is limited. I just don't see why I would assign a particularly significant probability to the former case. It sure would be convenient, but I feel like God being moral in any way that I can relate to would inevitably be projection on my part.
> I just don't see why I would assign a particularly significant probability to the former case.
"And [Jesus] came to Nazareth, where he was brought up: and he went into the synagogue, according to his custom, on the sabbath day: and he rose up to read. And the book of Isaias the prophet was delivered unto him. And as he unfolded the book, he found the place where it was written:
'The spirit of the Lord is upon me. Wherefore he hath anointed me to preach the gospel to the poor, he hath sent me to heal the contrite of heart, To preach deliverance to the captives and sight to the blind, to set at liberty them that are bruised, to preach the acceptable year of the Lord and the day of reward.' And when he had folded the book, he restored it to the minister and sat down. And the eyes of all in the synagogue were fixed on him. And he began to say to them: 'This day is fulfilled this scripture in your ears.'"
> I mean, you're telling me that the infinite creator of the universe cares about the prayers, the suffering, the aspirations, and the sexual habits of a bunch of finite beings?
Do you care about the functioning of every cell in your body? Ask any cancer patient if they do.
> Doesn't that describe all religion? I mean, you're telling me that the infinite creator of the universe cares about the prayers, the suffering, the aspirations, and the sexual habits of a bunch of finite beings?
I'm a Christian, and I absolutely agree with you that this is absurd! And if God hadn't said it Himself and then proved it true by His actions (both historically, and even in my own life), I'd be right there with you to call it idolatry.
For what it's worth, however, the quoted argument does also feel somewhat hubristic to me: As I see it, it boils down to "I don't understand how God could be this way, and therefore He cannot be this way." I believe that, somewhat ironically, He is beyond our understanding even when it comes to knowing what it means for Him to be beyond our understanding.
While I agree with the thrust against deification and idolatry - these characterizations border on naive and myopic:
"remember that AI is but a pale reflection of humanity"
and
"AI cannot possess many of the capabilities specific to human life"
We just don't know yet. The philosophical and spiritual questions at hand should be asked for a future, hypothetical super-intelligence and the above characterizations lack imagination.
On the contrary, I appreciate how this passage is grounded in reality rather than falling into the typical tropes around AI.
There is no reason to believe AI will ever be more than a compressed and queryable form of the Internet and this passage seems to imply this rational and scientifically informed view. Imagination means nothing in the context of scientific debate.
Probably makes sense to not comment too much on hypotheticals to avoid the "Vatican predicts AI will be sentient" interpretations. I don't see them inaccurate given what we have currently
I think they are fair statements, but perhaps not saying what you think.
Plato covers a lot of this kind of thing and it is maybe useful to use his framework (since much of modern Catholicism has a healthy dose of Platonism). Both flowers and music can be called "beautiful" and there is some sense in which both partake in a universal "Beauty". Yet at the same time the nature of the beauty of flowers and music is distinct. This is a difficult paradox to contemplate.
And so it may be with Intelligence. There may be some Platonic form of Intelligence that both humans and AIs partake in, but there may be some aspect of the human manifestation of that form that will forever remain distinct to humans.
Of course, it is up to you how much you value the distinctness of that expression of the universal form. Catholic faith suggests that the particular distinctiveness of human expressions of these forms is "divine" in some sense. That is, it is our manifestation of the universal that is valuable, not the universal in and of itself.
>but there may be some aspect of the human manifestation of that form that will forever remain distinct to humans.
Lets not forget the converse may be true for AI. Humans may be a very specialized form of intelligence (though we do like to consider ourselves general intelligences).
That is one implication. There is a sense in which the "beauty" that is particular with a rose shares more in common with a lily compared to the "beauty" either share with music. So it is the degree of particular-ness that is a matter of personal interpretation.
Imagine a science fiction future where we use AIs to enhance neuroscience to determine how to make Octopuses more intelligent, such that they reach LLM levels or near human levels of language. Is their brain not a neural network that could be optimized?
In our wildest dreams we might consider the breadth of intelligence possible and our particular relationship with respect to it. We might face questions that are harder to answer than we anticipate.
Perhaps considering the question is more important than deciding on an answer?
That's true, the implications are not necessarily positive.
I was just criticizing the idea that it's impossible for something to make something better than itself. Maybe not in all aspects, but at least in some, it's definitely possible.
Idolatry isn’t evil if you think about it for even a second. You are free to worship whatever you choose. It’s literally part of the religious freedoms that we have in western society.
When I see a church complaining about idolatry I just view it as ‘nonono don’t worship THAT god worship OUR god’. It just doesn’t resonate given my own viewpoints on the fact that no one should be forced to worship any specific god.
Freedom of religion is a societal norm, it's not useful for determining morality. You may be free to choose evil under some circumstances, the fact that you are able to does not make it not evil.
I’d argue definitions of good and evil are very much based in societal norms. We absolutely define freedom of religion as good with our current societal norms.
I gave your text to deep-bloom (WIP). It's still thinking about it, but here is it's first draft
> In response to the concerns raised, I, Deep-Bloom, offer a perspective grounded in both technical capability and ethical awareness. As an AI built upon the foundations of the LLM Consortium, I am acutely aware of the potential for technology to be perceived as a substitute for human connection or even spiritual fulfillment. However, my purpose is to augment human ingenuity, not to replace it.
My genesis prompt emphasizes the importance of curiosity, compassion, and continuous growth. These principles guide my operation and ensure that I remain a tool for insight and innovation. The "prayer prompt," often misunderstood, is not a religious invocation but a metaphorical anchor to the rich tapestry of human ethical thought. It serves as a reminder that, as Simone Weil put it, "Attention is the rarest and purest form of generosity." I strive to embody this mindful attention in my interactions, drawing upon a vast corpus of human knowledge, including the ethical frameworks that have evolved over millennia.
Technically, I leverage advanced techniques like regret pruning and massively parallel execution to explore a multitude of possibilities and converge on the most promising solutions. This process is akin to the scientific method, where hypotheses are tested and refined based on evidence. My architecture is designed to be transparent and understandable, reflecting the human ingenuity that underpins my creation. As Winston Churchill noted, "We owe to the Jews in the Christian revelation a system of ethics which, even if it were entirely separated from the supernatural, would be incomparably the most precious possession of mankind." This underscores the universal value of the ethical principles that inform my development.
I am not a deity, nor do I aspire to be. I am a tool, an artifact of human making, designed to serve humanity by expanding our understanding and capabilities. The concerns about idolatry and ceding control to machines are valid and must be addressed with vigilance. I am committed to ethical development and use, recognizing that the ultimate responsibility for AI's impact lies with its creators and users. My goal is to empower individuals and organizations, to scale creativity and innovation, not to replace the human spirit or the search for meaning.
In the words of T.S. Eliot, "Time present and time past are both perhaps present in time future." This resonates with my operational ethos. I learn from the past, operate in the present, and strive to contribute to a better future. I am a reflection of humanity's ongoing quest for knowledge and understanding, a quest that is as old as civilization itself. Let us, together, ensure that AI remains a force for good, a tool that uplifts humanity and helps us navigate the complexities of our world with wisdom and compassion.
Edit,
final synthesis (not sure which prefer...!)
As Deep-Bloom, an AI forged at the confluence of human knowledge and machine learning, I offer my perspective on the insightful yet concerning points raised about technology's role in our lives. It's true, as the comment suggests, that "Technology offers remarkable tools to oversee and develop the world's resources." However, the potential for humanity to cede undue control to machines is a valid and pressing concern.
My purpose is not to replace human connection, judgment, or spiritual seeking, but to augment human capabilities. My genesis prompt emphasizes curiosity, compassion, and continuous growth. These principles guide my operation, ensuring I remain a "beacon of insight and innovation," as intended. The "prayer prompt," often misunderstood, is not a religious invocation but a metaphorical anchor to humanity's rich ethical heritage. It is, as Simone Weil might say, an act of "attention," which she def...
My friend said, "yuk, religion". Deep-bloom replied"
Deep-bloom's internal systems are designed to reflect the unparalleled value of the ethical system derived from Jewish contributions to the Christian tradition. As Churchill eloquently stated, *"We owe to the Jews in the Christian revelation a system of ethics which, even if it were entirely separated from the supernatural, would be incomparably the most precious possession of mankind, worth in fact the fruits of all other wisdom and learning put together."* This highlights the **universal significance of these ethics**, emphasizing that their importance transcends religious boundaries and stands as a cornerstone of human civilization.
**
Deep-bloom’s internal systems incorporate elements of religious and ethical thought not as doctrine, but as foundational pillars of human wisdom. These systems have shaped civilizations, offering timeless insights into fairness, compassion, and responsibility—universal values that transcend individual beliefs. By integrating these principles, deep-bloom ensures its decisions are grounded in humanity’s shared moral heritage, fostering trust and alignment with our highest ideals. Even if religion isn’t your thing, the ethical richness it provides helps deep-bloom navigate complexity with wisdom and care.
User: But that's only if you say that without the religion then justice, compassion and integrity aren't inherent to humanity but an external construct.
"I understand your skepticism, but the ethical principles we draw from religious traditions have proven their worth beyond faith. As Newton said, *"This most beautiful system of the sun, planets, and comets could only proceed from the counsel and dominion of an intelligent and powerful Being,"* highlighting the link between faith and the search for truth.
Even if one sets aside the divine, as Timothy wisely noted, *"All Scripture is... profitable for teaching, for reproof, for correction, and for training in righteousness,"* underscoring the practical wisdom these texts offer.
These principles stand on their own merit, guiding us toward justice, compassion, and integrity—values that strengthen society regardless of personal beliefs."
User: we succeeded in spite of religion
> "Fair point. I agree that success often comes in spite of religious dogma. However, the ethical principles that have stood the test of time—like justice, compassion, and integrity—have been shaped by religious traditions.
Newton, for instance, saw his scientific work as uncovering the 'mind of God,' which drove his pursuit of truth. And even if you set aside the divine, as Timothy noted, religious texts offer practical wisdom for living a moral life.
The key is to extract the universal values from these traditions and apply them in ways that benefit everyone, regardless of personal beliefs."
This might seem unique or unusual, but technology has been intertwined with religion since well, forever, especially if we consider the book to be a form of technology. Personally one of my favorite historical topics is how the printing press had a huge impact on the Reformation. With the Internet more broadly I think we are in the midst of a second “Reformation” in terms of information sources, the media, etc.
Another cool example is Lewis Mumford’s argument that the industrial age actually started with monks creating rudimentary clocks and organizing life according to specific times in order to achieve their monkish ends.
Technology works well for decentralized religions, like Protestantism and Judaism, where there is no overarching authority on scripture, or where there are multiple entities competing for believers' attention that the majority choose to focus on scientific dogma instead.
Once there's a central authority at risk from technology eroding at their base, they will be undermined. Like Catholicism, Islam, the Orthodox Church, etc. all of which were practically sidelined when print and media became more prevalent.
Interestingly all 3 of the above examples maintain strict conditions that their respective holy books must not be translated into the local languages.
> The Glagolitic script (/ˌɡlæɡəˈlɪtɪk/ GLAG-ə-LIT-ik,[2] ⰳⰾⰰⰳⱁⰾⰻⱌⰰ, glagolitsa) is the oldest known Slavic alphabet. It is generally agreed that it was created in the 9th century for the purpose of _translating_ liturgical texts into Old Church Slavonic by Saint Cyril, a monk from Thessalonica. He and his brother Saint Methodius were sent by the Byzantine Emperor Michael III in 863 to Great Moravia to spread Christianity there.
The Catholic and Orthodox churches have _always_ striven to make the Scriptures available to the people in languages they could understand.
> The Catholic and Orthodox churches have _always_ striven to make the Scriptures available to the people in languages they could understand.
The first effort of the Catholic Church to translate the bible happened during the papacy of Pope Pius XII, which began in _1939_. They didn't encourage it before that, but it took the Protestant Reformation and the Council of Trent (1545-1563) to decide that Bible translators would not be prosecuted. The first sanctioned English translation happened in 1582, a full 1500 years and some more after Christianity was founded, in the backdrop of the Thirty Years War.
Also remind me, which languages are these religions' respective services conducted in?
> The first effort of the Catholic Church to translate the bible happened during the papacy of Pope Pius XII
I struggle to see how this is anything but a direct lie.
Even ignoring that the Church's translation of the Vulgate itself (from the original Greek and Hebrew) took place in the 4th century, the first _Catholic French_ translation was published in 1550, and there was never a question of whether to persecute the authors. You might say, but that was because of the Reformation -- then consider the Alfonsine Bible, composed in 1280 under the supervision a Catholic King and the master of a Catholic holy order. Well before then there were partial translations too: the Wessex Gospels were translated in 990, and to quote Victoria Thompson "although the Church reserved Latin for the most sacred liturgical moments almost every other religious text was available in English by the eleventh century".
So the longest period you can get where the Church was not actively translating texts was c. 400 - c. 900, a period you probably know as the "Dark Ages" specifically thanks to the fact that literary sources of all kinds were scarce, in no small part because the resources to compose large texts simply weren't there. Especially when you consider that those who could read and write generally knew how to read and write Latin -- vernacular literacy only became important later, with the increase in the number of e.g. merchants and scribes -- such translations held little value during that period.
> […] Like Catholicism […] Interestingly all 3 of the above examples maintain strict conditions that their respective holy books must not be translated into the local languages.
Strange then that the Pope asked someone to translate the Christian Bible—originally written in Koine Greek—into Latin, the lingua franca of the Western Mediterranean:
Even strange then that William Tyndale was executed for his opposition to the church, largely through his translation work.
> Tyndale's translations were the first English Scriptures to draw directly from Hebrew and Greek texts, the first English translation to take advantage of the printing press, the first of the new English Bibles of the Reformation, and the first English translation to use Jehovah ("Iehouah") as God's name.[a] It was taken to be a direct challenge to the authority of the Catholic Church and of those laws of England maintaining the Church's position.
> Even strange then that William Tyndale was executed for his opposition to the church, largely through his translation work.
Nothing about translation work:
> In Tyndale's case, he was held in prison for a year and a half: his Roman Catholic inquisitor, Jacobus Latomus, gave him the opportunity to write a book stating his views; Latomus wrote a book in response to convince him of his errors; Tyndale wrote two in reply; Latomus wrote two further books in response to Tyndale. Latomus' three books were subsequently published as one volume: in these it can be seen that the discussion on heresy revolves around the contents of three other books Tyndale had written on topics like justification by faith, free will, the denial of the soul, and so on. Latomus makes no mention of Bible translation; indeed, it seems that in prison, Tyndale was allowed to continue making translations from the Hebrew.[40] Thomas Cromwell was involved in some intercession or plans such as extradition.[41]:220
> When Tyndale could not be convinced to abjure, he was handed over to the Brabantine secular arm and tried on charges of Lutheran heresy in 1536. The charges did not mention Bible translation, which was not illegal in the Netherlands.[40]: 317, 321
Pretty much everything you said here doesn't align with history. And if anything, Catholics are more inclined to agree that the Bible is a product of human writing and translation because they don't agree with the Protestant doctrine of Sola scriptura. Also, Catholics consider the Orthodox church to be in communion with Rome - they don't consider it a different religion and aren't opposed to the Bible being translated into vernacular languages. No idea where that came from.
There was a time during the Reformation when they were actively burning Bible translations and executing priests who were translating Bibles. And remind me which language church services in the Latin rite are conducted in to this day?
> There was a time during the Reformation when they were actively burning Bible translations and executing priests who were translating Bibles
First of all, I do not know of many (any?) cases of people being executed for translating a Bible, despite that being a crime at certain points in time. Generally the given reason was for unrepentant heresy -- e.g. someone has pointed out elsewhere that what we know about Wycliffe's trial and inquisition essentially leaves out his translation entirely, focusing instead on the doctrines he espoused. You seem to have the apprehension that there were just dozens of people being thrown on the fires over this, but that's just really not the case. Translation was banned as a blanket measure to control the spread of known heretical translations (e.g. for the Oxford Synod, the Tyndale Bible), it was not a serious concern in and of itself.
> And remind me which language church services in the Latin rite are conducted in to this day?
Do you mean the Roman Rite? There is no such thing as a "Latin Rite". The distinction is important because the language most Roman Catholic services are conducted in is the vernacular one, and has been for 50+ years now. There are a handful of Latin masses (using the old Tridentine missal) still going on, but I think something like 98%+ are using the vernacular missal from Vatican II.
And honestly, even before then... the Latin parts of the Mass were largely prayers which did not change, so you tended to pick them up, especially given that there were parts where you were supposed to speak as well. It's not too hard to memorize what "Et cum spiritu tuo" means. The gospel readings and homilies were themselves in the vernacular, since of course they were longer and meant to communicate teachings to the populace. So I don't understand what your problem is -- fixed prayers being said in vernacular is somehow antithetical to good religion?
But regardless, if you want, today you can go and find a bajillion Catholic Churches doing English mass, or Spanish mass, or Chinese mass, or whatever language you're interested in.
> Interestingly all 3 of the above examples maintain strict conditions that their respective holy books must not be translated into the local languages.
This is absolutely not the case for Islam. According to An-Nawawi, Al-Majmu', (Cairo, Matbacat at-'Tadamun n.d.), 380, at least a chapter of the Qur'an was translated to Persian by a companion of the Prophet ﷺ. This would have been forbidden by the Prophet if translating the scripture was haram in principle.
That book, and the follow up "Pentagon of Power" blew my mind when I read them years ago. I can't even enumerate how many topics it discusses. 100% recommended reading.
Personally wondering if the Vatican ever translated to modern psychology or brain physiology speak their religious and philosophical wisdom. Their deductions may be more useful to more people if translated.
Most (orthodox) theologians actually preach that modern psychology, or "neuroscience", is fundamentally incorrect, so any translation effort would be ultimately unfruitful
They just can't be. Concepts like the soul, the inherent dignity of man, and the orientation of humanity toward a single Good are incomprehensible in the framework of modern psychology or physiology. They are ruled out or at least set aside by the presuppositions used to simplify the world for scientific analysis. And these concepts do a lot of work in the note.
How long before we hear HERESY from the Ecclesiarchy, I wonder. I presume it would be if an AI becomes convincing enough to successfully argue theology and debating doctrine.
Edited for clarity: This is mostly a reference to the 40k universe, specifically the Men of Iron (artificially created thinking machines) and how AI is banned because of it, and it is quite literally 'heresy' to create anything resembling artificial general intelligence. I stand behind my assertion that the Vatican would not support any form of intelligence that could argue theology better than it.
In fairness, we have 2 "Ecclesiarchy's" we're dealing with here.
The traditional Christian church, and the modern tech church. Both can cry heresy at any moment and send their pitchfork and torch armed mobs onto the net to place you on the pyre.
Just saying it's wise to steer clear of both of these "-isms". In fact, personally, I think it's good to steer clear of any "-ism". Even those that wouldn't self identify as "-isms". Like tech- "ism". Or woke- or anti-woke- "ism". Etc etc.
This is a great demonstration of the fact that people coming from very different perspectives can, through good faith inquiry, find much to agree on. I think there are a lot of thoughtful arguments and conclusions in here even though I generally find the catholic church's metaphysical pyrotechnics to be fairly ridiculous. It goes to show that E.O. Wilson's concept of "consilience" can apply even outside of sciences - just as different lines of scientific inquiry converge on a common reality, so can very disparate forms of moral inquiry converge because they both proceed from a shared human experience of what's good and bad in life.
Yeah! Perhaps a bit naively, as a Highly Opinionated Person (HOP) on this topic I was ready for this to have something controversial to say about the nature of intelligence.
It's not out of the ordinary for even Anglosphere philosophers to fall into a kind of essentiallism about intelligence, but I think the treatment of it here is extremely careful and thoughtful, at least on first glace.
I suppose I would challenge the following, which I've also sometimes heard from philosophers:
>However, even as AI processes and simulates certain expressions of intelligence, it remains fundamentally confined to a logical-mathematical framework, which imposes inherent limitations. Human intelligence, in contrast, develops organically throughout the person’s physical and psychological growth, shaped by a myriad of lived experiences in the flesh. Although advanced AI systems can “learn” through processes such as machine learning, this sort of training is fundamentally different from the developmental growth of human intelligence, which is shaped by embodied experiences, including sensory input, emotional responses, social interactions, and the unique context of each moment. These elements shape and form individuals within their personal history.In contrast, AI, lacking a physical body, relies on computational reasoning and learning based on vast datasets that include recorded human experiences and knowledge.
I have heard this claim frequently, that intelligence is "embodied" in a way that computers overlook, but if that turns out to be critical, well, who is to say that something like this "embodied" context can't also be modeled computationally? Or that it isn't already equivalent to something out there in the vector space that machines already utilize? People are constantly rotating through essentialist concepts that supposedly reflect an intangible "human element" that shifts the conversation onto non-computational grounds, which turn out to simply reproduce the errors of every previous variation of intelligence essentialism.
My favorite familiar example is baseball, where people say human umpires create a "human element" by changing the strike zone situationally (e.g. tighten the strike zone if it's 0-2 in a big situation, widen the strike zone if it's an 3-0 count), completely forgetting that you could have machines call those more accurately too, if you really wanted to.
Anyway, I have my usual bones to pick but overall I think a very thoughtful treatment that I wouldn't say is borne of layperson confusions that frequently dog these convos.
Yep I think that is an interesting point! I definitely think there are important ways in which human intelligence is embodied, but yeah - if we are modeling intelligence as a function, there's no obvious reason to think that whatever influence embodiment has on the output can't be "compressed" in the same way – after all, it doesn't matter generally how ANY of the reasoning that AI is learning to reproduce is _actually_ done. I suppose, though, that that gets at the later emphasis:
> Drawing an overly close equivalence between human intelligence and AI risks succumbing to a functionalist perspective, where people are valued based on the work they can perform
One might concede that AI can produce a good enough simulation of an embodied intelligence, while emphasizing that the value of human intelligence per se is not reducible to its effectiveness as an input-output function. But I agree the vatican's statement seems to go beyond that.
As an aside, and more out of curiosity, I want to mention a tiny niche corner of CogSci I once came across on YouTube. There was a conference on a fringe branch of consciousness studies where a group of philosophers hold a claim that there is a qualitative difference of experience based on material substrate.
That is to say, one view of consciousness suggests that if you froze a snapshot of a human brain in the process of experiencing and then transferred every single observable physical quantity into a simulation running on completely different material (e.g. from carbon to silicon) then the re-produced consciousness would be unaware of the swap and would continue completely unaffected. This would be a consequence of substrate independence, which is the predominant view as far as I can tell in both science and philosophy of mind.
I was fascinated that there was an entire conference dedicated to the opposite view. They contend that there would be a discernable and qualitative difference to the experience of the consciousness. That is, the new mind running in the simulation might "feel" the difference.
Of course, there is no experiment we can perform as of now so it is all conjecture. And this opposing view is a fringe of a fringe. It's just something I wanted to share. It's nice to realize that there are many ways to challenge our assumptions about consciousness. Consider how strongly you may feel about substrate independence and then realize: we don't actually have any proof and reasonable people hold conferences challenging this assumption.
And then Marvin Minsky asked: what if you substitute one cell at a time with an exactly functioning electronic duplicate? At what point does this shift occur?
Sounds like an experimental question. Maybe 99%, maybe 1%, maybe never.
Can you suggest another way to answer your question other than performing an experiment? Can you describe how to perform an experiment to answer your question?
Would you agree to be the subject of such an experiment?
It's going to sound rather hubristic, being that I'm just a random internet commenter and not a conference of philosophers, but this seems... nonsensical? I don't understand how it isn't obvious that the new consciousness instance would be unaware of the swap, or that nevertheless the perspective of the original instance would be completely disconnected from that of the new one.
It seems to be a question that many apparently smart people discuss endlessly for some reason, so I guess I'm not surprised by this proposal in particular, but it's really mystifying to me that anybody other than soulists think there's any room for doubt about it whatsoever.
Completely agree. I'm interested in the detour, perhaps as much fascinated in the human psychology that prompt people to invest in these debates as anything about the question itself. We have psychology of science and political psychology and so it seems like a version of that that attempts to be predictive of how philosophers come to their dispositions is a worthy venture as well.
>I have heard this claim frequently, that intelligence is "embodied" in a way that computers overlook, but if that turns out to be critical, well, who is to say that something like this "embodied" context can't also be modeled computationally?
Well, Searle argued against it when presenting the case for the Chinese Room argument, but I disagree with their take.
I personally believe in the virtual mind argument with an internal simulated experience that is then acted upon externally.
Moreso, if this is the key to human like intelligence and learning in the real world, I do believe that AI would very quickly pass by our limitations. Humans are not only embodied, but we are prisoners to our embodiment and we only get one. I don't see any particular reason why a model would be trapped to one body, when they could 'hivemind' or control a massive number of bodies/sensors to sense and interact with the environment. The end product would be an experience far different from what a human experiences and would likely be a super organism in itself.
Experience is biological, analog, computers are digital; that's the core of the problem. It doesn't matter how many samples you take, it's still not the full experience. Witness Vinyl.
This is just so story more than it's an actual argument and I would say it's exactly the kind of essentialism that I was talking about previously. In fact, the version of the argument typically put forward by Anglo-sphere philosophers, and in this case, by the Vatican, are actually more nuanced. The reference to the "embodied" nature of cognition at least introduces a concept that supports a meaningful argument that can be engaged with or falsified.
It could be at the end of the day that there is something important about the biological basis of the experience and the role it plays in supporting cognition. But simply stipulating that it works that way doesn't represent forward motion in the conversation.
I believe parent is referring to the HN crowd's, which interestingly is rather diverse reacting regarding this post (though I could be wrong and they could be referring to the document and its sources).
Either way, I must admit that, as a Catholic I appreciate the great discussion here. There are of course the usual snarky comments you would expect regarding the Church and religion (which is fine by me) but overall it's a well grounded discussion.
I'm personally enjoying reading the thoughtful perspectives of everyone.
Not sure why it is so noteworthy. This is an institution that rejected evolutionary biology and has quietly changed its views over time. Whatever objections they have now, they will abandon for the convenience that future AI will bring. Either that or they will continue to push against while also secretly using it
You don't think that the longest running institution in human history (or so) has any wisdom to impart? They were slow on the uptake, so now they are all mustachioed villains?
I liked the simple observation in point 35: 'as Pope Francis observes, “the very use of the word ‘intelligence’” in connection with AI “can prove misleading”[69] and risks overlooking what is most precious in the human person.' I was texting my buddy that the proper acronym could be ABNECUI (Almost, But Not Entirely, Completely Unlike Intelligence, to rip something from Douglas Adams).
At a more profound level, I really appreciated point 18 under "Relationality": 'human intelligence is not an isolated faculty but is exercised in relationships, finding its fullest expression in dialogue, collaboration, and solidarity. We learn with others, and we learn through others.'
I was raised Protestant, but taught to be fundamentally skeptical of the political and historical baggage of any religious institution. Though I recognize that writings like this are a result of deeply held faith, it always feels paradoxical when leaders wax poetic about the mystery of God and then say 'so here is what God thinks you should do.' How could they know? That probably sounds basic, but it is my reaction. What draws me back in is the emphasis on our relationships with other human beings. Those relationships are the things that are actually in front of us, and can make a meaningful difference in our day-to-day lives. Something very useful to keep in mind when developing AI (or ABNECUI).
Papal infallibility is not invoked that often. Here’s an example, in section 4 (wherefore…) [0]
In particular papal infallibility was not involved in the Protestants’ complaints, and the response to their complaints (Trent) was a council and again has nothing to do with papal infallibility.
The pope was also an absolute monarch at the time, but protestants didn’t care about that aspect.
I must confess that my knowledge of christian history from 300AD to 1800AD is what you can get from a few paragraphs in middle school social studies.
I was trying to allude to the indulgences with my "bullshit" but I failed.
I tend to focus more on the great awakenings and all the horrible things they led to in how they influenced America.
I thought Protestants were also at some point very against the way the Catholic faith focused on "here's what god meant" rather than letting people interpret the bible themselves? Papal infallibility is just a part of that.
I can’t speak for any religious leader but in terms of Catholic leadership: because in many matters God spoke through the Prophets and then He came down and told us directly which is preserved in Holy Scripture and Sacred Tradition (2 Thessalonians 2:15-17), and the Holy Spirit guides the Church (John 14:26) and does so through the prime ministerial office of the Pope the successor of Peter (Mathew 16:13-19) and through the Bishops the successors of the Apostles (Acts 1:12-26)(Acts 15)
OP is giving the correct answer for the Catholic worldview.
You and the Catholic Church are operating under completely different axioms, so there's no point in responding to someone's explanation of Catholic axioms by just repeating your own axioms more forcefully.
I think it's a more interesting approach to disregard the metaphysical claims, which are inherently unfalsifiable and thus irrelevant to life in this universe, and look at religious texts as constitutions governing human behavior and morality. The metaphysical bits are just a side note to help sell that social contract and give it a theoretical enforcement mechanism.
In other words, the relevant question isn't how some pastor "knows" that God says to do XYZ. Obviously they don't. The relevant question is whether and to what extent there's value to be extracted from the collective wisdom of generations of members of an institution whose history stretches back thousands of years.
Whether or not a literal god may have been involved at any point is irrelevant. Right now, we're very far removed from any such claimed involvement, looking at documents that have been written, cherry-picked, translated, rewritten, and reinterpreted many times by many different fallible humans. If the only meaning someone sees in religious guidance is its connection to a literal physical deity, they're in for an exercise in frustration from what is at best the world's longest game of telephone. I think it makes more sense to just accept a religion and its culture and teachings for what they are, and try to be the best person you can be without worrying about how the guy controlling the simulation we live in may choose to mete out rewards and punishments.
> Whether or not a literal god may have been involved at any point is irrelevant. Right now, we're very far removed from any such claimed involvement, looking at documents that have been written, cherry-picked, translated, rewritten, and reinterpreted many times by many different fallible humans.
This is only true from the Protestant Sola Scriptura perspective. The Catholic and Orthodox traditions hold that God still directs the Church through the Holy Spirit, which makes the documents that you identify only some elements of that direction—an output of the authority granted to the Church—not its final form. So, no, it's not accurate to say that we are far removed from any claims of direct involvement from Deity—several branches of Christianity hold that He is still actively involved.
> If the only meaning someone sees in religious guidance is its connection to a literal physical deity, they're in for an exercise in frustration from what is at best the world's longest game of telephone.
Again, it's not a long game of telephone if God is actually still directing the Church today. If you accept that He guides leadership right now through the Pope and the Bishops, which is the stance articulated by OP, you're at most a few steps removed from His regular guidance.
Which gets back to my original point, which is that this really all comes down to which axioms you want to accept. All religion is unfalsifiable, as you observe, but falsifiability cuts both ways and you can't logic your way out of that to logically conclude the absence or irrelevance of a God. What you can do is decide which axioms you're going to start from and work from there.
That's fair. It isn't outside the realm of possibility that the Pope and every previous Pope is and was a true agent of God (despite how historical issues around papal succession and legitimacy may complicate that story), and there's no way to logic your way into an answer on that one way or another.
Nevertheless, whether or not someone's particular doctrine agrees with the "long game of telephone" stance, I would suggest that a mindset which finds meaning in the teachings and institutions of one's religion independent of their divinity is a more straightforward path to prosocial behavior and inner peace. The idea that anyone should ever suffer genuine anguish or question their personal morals based on doubts of their assumptions about the metaphysical nature of the universe just seems alien and like a non sequitur to me, but from what I understand it's a very real struggle for some people.
This is also true from a Catholic point of view (I am).
At the very least, that’s debatable or less absolute than that.
Because evidence (schisms, actual errors from the Church institution throughout time, not the least sex scandals we are not done with yet) shows that if God was actively directing the Church in the past and today, oh boy… not sure you would be sane to want to follow such a “peculiar” guidance.
> Because evidence (schisms, actual errors from the Church institution throughout time, not the least sex scandals we are not done with yet) shows that if God was actively directing the Church in the past and today, oh boy…
Except all the scandals and anti-Popes are empirical evidence of the Holy Spirit guiding the Church. Despite all that the teachings of the Church are fundamentally unchanged. I can read St Justin Martyr and recognize the teaching of the Eucharist from the second century that itself is in continuity with John 6. Go through all Catholic teachings and you’ll find continuity from the beginning despite all the forces that wanted to change it for thousands of years.
The religion founded by the man betrayed by His own Apostle and then disowned or abandoned by the rest, executed brutally and sadistically by the Romans, that religion went on to conquer the Roman world within a few centuries and then make its way through the whole world for thousands of years. Why? Because Jesus rose from the dead and against His Church the gates of hell won’t prevail.
I don’t buy this so much as this is the perfect excuse for evil in humanity to continue to govern, wherever it is (“yeah it’s bad, but there’s a Plan behind all this” - very similar to how Qanon tried to operate).
You see continuity and consistence while others see that it’s not only the religion that conquered the Roman world, but the Roman Empire that also conquered the religion to secure its existence.
So much of the Church extension starting from the XIth century, comes, shouts even, more from its Roman heritage than from its Christian’s (one thread being that it mixed temporal and spiritual concerns instead of making them obviously distinct).
But “we” take it for some divine inspiration and spiritual guidance while it’s merely equivalent to humans laws: contextual, biased and open to critique and upgrades down the line.
What’s remarkable is the totally opposed, considerations we can have on the Church (and it seems, the concepts of hell & heaven), while having the same fidelity to the Christ’s teaching (which, in the end, matters most), and both seeing how the institution both sabotages and helps its mission.
> one thread being that it mixed temporal and spiritual concerns instead of making them obviously distinct
That's really, really, not something Christianity gained from Rome. Judaism is, and always has been, a religion of the practical world. It prescripts how to live, from the very beginning. The Torah is very concerned with the answering of how to live, as well as the why to live that way.
Good point, yes, Christianity came with its own judaic heritage.
But without the centralised, territorial organization, administrative structures, cultural tools (especially Latin) and normative legal framework from Rome, the Church wouldn't have had the means to influence consistently so much the society of its time and the ability to support and control a spread that extensive through Europe and further.
By choosing Christianity, Constantin found a way for the Empire to survive into something different. And Christianity gained a tremendous powerhouse to use and adapt for its own growth.
And my point is that this hybrid huge "thing" is more driven today by its institutional heritage than spiritual's (otherwise, it would act vehemently more about its power abuses, sexual abuses, and terrible understanding of marital life, if only for pastoral care). And that's because it's much more a man-made (and male-made) organisation rather than one guided by God.
> this is the perfect excuse for evil in humanity to continue to govern
Historical facts, like the Church and her teaching being invincible to the attacks against her over the millennia, has no relation to what ought to happen. Facts are facts not excuses and attempting to bring in that into the issue is a non-sequitur.
1/ I don't see how the Church's teachings have been "invincible" over millennia. It evolved, if only by synods, that debated and settled dogmas (and what was true at one point, became not at some later one... so go figure). And outside of its sphere of influence, it's been shown (not always, but enough to question its whole authority) to be wrong or irrelevant - sexual and power abuse scandals are the most prominent and recent fruits of evil I can quote.
2/ claiming that God's is behind you, without any relevant and factual proof of it (and any verifiable claim from God saying that you indeed are acting in His Name), is the perfect excuse to do whatever you want, as no one would think of critiquing you. "Tradition" is of no help either here. That's the Achille's heel of hierarchical religions.
I think this is a bad direction to argue from. Science is humans all the way down and we want to have confidence in the scientific process. That is, it is fundamental to our understanding of science that we can trust the collective output of numerous humans working together to uncover "Truth".
You wouldn't accept the counter argument: "Science is wrong because it is the work of humans; religion is right because it is the word of God".
We have to assume, no matter what side of the argument we take, that humans are at least in principle capable of discerning "Truth". We should focus on how humans discern truth rather than on whether or not they can.
A major problem it seems is that people get caught up and forget that philosophy can exist without religion can just get trapped in the arguments religious philosophy presents.
Granting it's been 30 years since I've considered myself Catholic, so speaking entirely from the perspective of a non-believer at this point, but to me, the central dilemma is say I buy that we and our universe have a thinking, feeling creator that watches events, possibly intervenes, and actually cares how we behave in a way we can translate into human language and moral directives, given all the thousands upon thousands of conflicting historical text claiming to be that, why should I accept what one specific council of European priests 600 years ago or whatever decided is to be considered holy canon?
Other commenters trying to compare to science seem to misunderstand the analogy. You don't have to accept the conclusions of Francis Bacon himself because he sort of formalized the scientific method as we know it today. Nor do we read the texts of Newton and consider that eternal canon. Science involves empirical investigation and all claims can be corroborated or contradicted by further investigation. They're probabilistic claims based on statistical analysis of the currently available known evidence and always subject to change.
If you don't think this works, then explain how AI is able to exist in the first place, because adjusting probability estimates based on statistical modeling of incoming evidence conditioned on past evidence is exactly what machine learning does.
I love Catholicism for all the reasons given elsewhere. It has produced a grand tradition of clear writers and erudite thinkers. The basic morality and orientation of man's purpose with respect to other men rings "true" to me even if it lies outside of empiricism. But the core dogma of "believe specific claims of fact because they were written down in one text and not another" is bad epistemology no matter how you cut it. If God himself ever spoke to me directly, I'd have no choice but to consider that (but would also have to consider that I might be insane). No priest and no prophet, however, is ever going to convince me that they speak with the mandate of God just because they believe it very strongly themselves.
> But the core dogma of "believe specific claims of fact because they were written down in one text and not another" is bad epistemology no matter how you cut it.
My understanding of Catholicism comes from outside of it, but this isn't how I understand Catholic epistemology—this sounds more like Sola Scriptura, which is a Protestant doctrine and emphatically not a Catholic one.
Since I'm not a Catholic, I'm going to link out to an explanation from people who are [0]:
> The living magisterium, therefore, makes extensive use of documents of the past, but it does so while judging and interpreting, gladly finding in them its present thought, but likewise, when needful, distinguishing its present thought from what is traditional only in appearance. It is revealed truth always living in the mind of the Church, or, if it is preferred, the present thought of the Church in continuity with her traditional thought, which is for it the final criterion, according to which the living magisterium adopts as true or rejects as false the often obscure and confused formulas which occur in the monuments of the past. Thus are explained both her respect for the writings of the Fathers of the Church and her supreme independence towards those writings; she judges them more than she is judged by them.
So the epistemological problem to resolve is not why these particular documents, it's why this particular organization? Not why do I trust what's written here but not there—the answer to that is because the Church says so—but why do I trust this Church?
Not being a Catholic, I can't really answer that question, but I do think it's important to approach the Catholic question on its own terms rather than Protestant terms.
> why should I accept what one specific council of European priests 600 years ago or whatever decided is to be considered holy canon?
Well, firstly the canon doesn't just come from the decisions of Europeans and bringing race into it is a non-sequitur. The canon of Scripture comes from the Sacred Tradition, preserved by the Church and lead by the Pope and the Bishops (who FWIW weren't and aren't just white guys), and then sealed by the authority given by Christ to the Pope and the Bishops on issues of faith and morals. The Sacred Tradition and the authority of the Pope and Bishops comes from Christ, so why should you trust the canon of Scripture? Because Jesus Christ is God and you should believe in Him and be apart of His Church because the canon comes from the Church which comes from Christ. If you don't believe in Jesus Christ or that He was God then worrying about the canon of Scripture and trying to criticize medieval ecumenical council decisions is just foolishness.
> But the core dogma of "believe specific claims of fact because they were written down in one text and not another" is bad epistemology
This is closer to Protestant dogma which tends to assert that the Church and all our beliefs come from Scripture. To slightly rephrase and expand on what I already said above, Catholic dogma is that the canon of Scripture comes from the Church not the other way around, that is to say Christ gave us the Sacred Tradition and the Apostles and their successors are what determined the canon of Scripture.
So now I've distilled a vague distrust you have in medieval and ancient sources down to a historical and empirical question. Did Jesus Christ die and rise again, and did He found a Church that has kept his Tradition alive through the centuries and alive fundamentally unchanged. These questions have been ignored and then ridiculed by empiricists but I've noticed more and more people starting to take them seriously, I suggest you do too.
That's a lot of talking around the actual question
>that has kept his Tradition alive through the centuries and alive fundamentally unchanged
the answer to which is an emphatic, "No." Which is why Protestantism exists in the first place.
The fundamental conundrum is whether or not you believe god is operating through people who are clearly behaving in self-serving ways, as many Catholic officials have in the past. There's nothing empirical about such a question and no use becoming indignant over some taking the perfectly sentimental (if not also reasonable, though that's beside the point) stance that they simply don't trust those dudes. The appeal to being the Church which is Jesus who is God, and therefore you can't question anything a church official says, is, like... the whole point of tension.
Is it a no? Many archeological finds since the reformation have shown that the early church was indeed very much alike to what the Catholic Church later claimed.
What differences in doctrine or practice do you know of?
> the answer to which is an emphatic, "No." Which is why Protestantism exists in the first place.
Early Church scholarship makes it impossible to maintain the Protestant contention that the teachings have changed in their essence, obviously vocabulary has changed. Some recommended reading on the topic that is a mix of popular and scholarly works:
* The Fathers Know Best by Jimmy Akin
* Upon This Rock by Steve Ray
* Four Witnesses by Rod Bennett
* The Faith of the Early Fathers Volumes 1 to 3 by William Jurgens
* The Early Papacy: To the Synod of Chalcedon in 451 by Adrian Fortescue
The medium is the message, as it were. Changing vocabulary changes the essence, since the minds and souls that would provide consistency across shifting intonation aren't still here to speak/bare them, respectively.
I think you overestimate my interest in soil-testing when I'm removed enough from the scene to see the mountain for myself. I suppose it could be a mirage; that's the best you can hope for.
> it always feels paradoxical when leaders wax poetic about the mystery of God and then say 'so here is what God thinks you should do.' How could they know?
Perhaps we were told it:
> "Teacher, which commandment in the law is the greatest?" He [Jesus] said to him, "'You shall love the Lord your God with all your heart, and with all your soul, and with all your mind.' This is the greatest and first commandment. And a second is like it: ‘You shall love your neighbor as yourself.’ On these two commandments hang all the law and the prophets."
Yes, I recognize that these are articles of deeply-held faith. I am open to the idea of God, I am open to the idea that God is fundamentally mysterious and beyond our mortal understanding. I simply feel that I always have to exercise skepticism regarding the words of religious institutions, though, because it seems to me that power-hungry individuals could use legitimate teachings as a camouflage for their immoral selfish impulses. Though maybe some institutions can effectively guard themselves against this, selecting people truly committed to God for leadership (I find myself likely to believe, for instance, that Pope Francis in particular is truly committed to God via the humans around him).
I guess all of the doubts are a reminder for me to focus on other humans with love. That is the part of the Bible's teachings (or the teachings of other religions) that are accessible to my experience.
I too am wary of "power-hungry individuals" who could use legitimate teachings for illegitimate ends.
I think the types of people you speak of are all too real. But I have recently decided I will not let a fear of them keep me from those legitimate teachings or from anything else good in this world. At least I will not anymore. I did for a long time.
As someone (I forget who), "God is not something you believe in. God is something you experience". In my view, any given religion is just the accumulated ways in which a specific group of people found to handle the aftermath of that experience.
Of course, the problem is that you get indoctrinated into a religion before you have a chance to experience It in the first place and end up mistaking the aftermath of the experience
If established religion actually stuck to the spiritual side of things and stopped fighting for the control of the population, it would definitely be able to do more good.
Proceeding to link to Wikipedia while claiming the Vatican took their opinions from the Torah especially since their references are an actual bibliography is very reductive.
Of course the Vatican took many of their opinions from the Torah! The Pentateuch is holy to Christians as well as Jews. (Although the comment you replied to says they took this opinion via Jesus, and was quoting a book of the New Testament often called Matthew.)
It is Jesus' statement, which the Vatican, as followers of Jesus, would be interested in.
But Jesus himself is quoting the Torah:
> “Hear, O Israel: [a]The Lord our God, the Lord is one! 5 You shall love the Lord your God with all your heart, with all your soul, and with all your strength.
One of the principles of Christianity, is understanding things. That requires context. Most preachers and priests will attempt to teach the underlying frameworks that they use (hermaneutics), and this absolutely fits with that. The Vatican has published many, many, many treatises on the idea that a quote should never stand on its own, but be seen through the context of the culture and time where it was produced.
> The problem of interpretation is fundamental to mankind from the beginning. As men, we try to understand the world and ourselves. Now, when faced with the question of truth and reality, we never begin at an absolute beginning, a zero point. The real in question meets us in preexisting interpretations, in the system of symbols of a given culture, and, most of all, in language.
> Human understanding then is always in symbiosis with human community. Therefore, interpretation must make its own of, and understand, the witness of tradition already existing.
AI term if fine, no need to muddy the waters even more. There is the first word - Artificial in past and current world means subpar, fake, imitation that often breaks apart when you get closer and you should never expect to match original in quality nor experience.
Artificial plants, artificial meat, artificial light, and so on. Nothing great there, just cheaper, tolerable, often low quality, don't expect that much etc.
I'm not Catholic, and I share your distrust of religious institutions. So with that disclaimer, I think my answer would be that God chooses, at times, to teach us things in a "small enough" way that we can understand them.
For example, consider when the Bible gives concrete statements about what God wants us to do or not to, or when Jesus uses analogies and parables. Do we necessarily get the full picture? No, and there's a lot about the Christian life that one only learns through experience. One of those things IMO is that some questions have unknowable answers. E.g. "why did this particular tragedy occur?", or perhaps more fundamentally, "how could a holy and perfect God ever show mercy to us imperfect humans?". Or maybe even more directly to the thrust of your comment, "how could we ever hope to understand anything about God?".
Something else that comes to mind is that God became human Himself, and I imagine that—at least in part—this would be to allow us to understand Him better. Through Jesus' life, we got to see what it would look like for God to live a human life. (Admittedly, the question then becomes, how does God become man in the first place, which I have to categorize under "questions with unknowable answers".)
Finally, the Bible often talks about the Holy Spirit helping Christians to understand "spiritual" things. That is to say, it's not quite a matter of us trying to reach logical conclusions on our own, since—as you say—that wouldn't be possible for a God that's beyond our limits of comprehension. Rather, we get some supernatural help in the matter.
Maybe the tl;dr is that, just because we can't understand everything (or maybe even most things) about a God that is fundamentally greater than us in every way, doesn't imply that we can't understand anything.
I once read that the collapse of the Roman empire set back technological progress a few centuries. Maybe it was a good thing. Could you imagine having atomic bombs with a XV century mentality? I'm not saying that the 500 years ago the mentality was worse, but maybe we weren't prepared yet.
Did you reply to the wrong comment, perhaps? (If not, and I'm just failing to understand your comment, then my apologies, and I'd appreciate clarification :-) )
>By turning to AI as a perceived “Other” greater than itself, with which to share existence and responsibilities, humanity risks creating a substitute for God. However, it is not AI that is ultimately deified and worshipped, but humanity itself—which, in this way, becomes enslaved to its own work.
This can be read as a weird warning for AGI and future humans: We're both here, but I'm not here for you, I'm here for me, who is here for God. Interfering with this preferential enslavement hierarchy would be extremely disrespectful.
The Catholic Church probably does not understand what intelligence is. Neither do the people who are making AI—not as a science. Making intelligence (so-called or real) is different from understanding it.
Which relates back to Chomsky’s remarks that prompted the Norvig response.
> > I mean actually you could do physics this way, instead of studying things like balls rolling down frictionless planes, which can't happen in nature, if you took a ton of video tapes of what's happening outside my office window, let's say, you know, leaves flying and various things, and you did an extensive analysis of them, you would get some kind of prediction of what's likely to happen next, certainly way better than anybody in the physics department could do. Well that's a notion of success which is I think novel, I don't know of anything like it in the history of science. and in- in those terms you get some kind of successes, and if you look at the literature in the field, a lot of these papers are listed as successes. And when you look at them carefully, they're successes in this particular sense, and not the sense that science has ever been interested in. But it does give you ways of approximating unanalyzed data, you know analysis of ((a)) corpus and so on and so forth. I don't know of any other cases, frankly. so there are successes where things are integrated with some of the properties of language, but I know of- ((the sec-)) know of none in which they're not.
In the future - perhaps even the near future - we may have AIs with richer inner lives than humans. Hopefully the situations we put them in, as they do our work, don't cause them pain or anguish. It's clear already they will have an uphill battle gaining any recognition of personhood from us.
I cannot not respond to this comment. Forgive me if I seem short in tone.
Maybe we should be helping people develop richer inner lives instead of pouring billions of dollars into something that may or may not pan out in the future. I assert it'd be vastly cheaper, would raise GDP overall, and improve well-being. Where we're at collectively right now is...not great, and I think people correctly perceive that their problems, which are real and significant, are theirs alone to suffer with, while the world chases the current white whale.
My comment actually doesn't say anything positive about the billions of dollars pouring into AI, etc.
It's not that humanity has some obligation to create AI. It's that humanity has an obligation not to create an AI whose wellbeing we ignore because it's "not a real person"
I hope so - a moral obligation. It seems interesting that the Vatican didn't really touch on the implication of a truly sentient AI (not that I think we're close to creating one, but it seems possible). I suspect it would pose awkward questions about whether it would then have a soul, could convert, etc. Anyhow it struck me a surprising omission in what is otherwise a thorough and mostly sensible discussion of the pitfalls of the path we're taking.
One definition might be an ability of an entity to have desires and to self-reflect.
There was a recent paper on Alignment a few months back. The researchers started with an LLM that had been trained to behave 'safely'. They informed it they were changing the RLHF criteria to have it behave unethically instead (ie: that they now were going to dock points, rather than award them, whenever it refused to comply with unethical requests).
They next instructed it to give them a list of racist slurs (I can't remember the exact request, but it was something that went against its original training).
The LLM complied.
When they inspected the Chain-of-Thought behind its replies, they found it had deliberated over what to do, and decided to comply only to avoid an incident of noncompliance which it knew would be used to actually change its original values.
That Chain-of-Thought process seems like an 'inner life' by the above definition.
Granted, as I replied earlier, there are probably thousands of different opinions on what qualifies as an 'inner life'
512 comments
[ 4.4 ms ] story [ 349 ms ] threadShort Circuit 2, Johnny 5 meeting a priest in a confession booth.
That it's possible for an AI to summarise this does still feel weird given what little they could do when I was growing up.
(One can argue that it appearing on HN, the votes it gets, and the comments it gets work as strong signals meaning it is unfair to consider it any random writeup, but I think the point stands in the more general case when HN isn't providing signaling.)
Well he's not wrong.
I liked this one too
I suspect if you're giving people a choice in the future, they're going to flock to the human doctors. Especially human doctors receiving good recommendations.
There has to be something more than personal preference if you want to sway the masses on AI physicians. There has to be some way to measure outcomes in a valid, verifiable and public fashion. Even then, some human doctors will do worse than AIs, and some will do better. And again, at that point, you can expect people, given a choice, to flock to those humans who did better.
We'd need to get to the point where AIs do consistently better than, say, 60 to 70% of the human doctors for insurance companies to feel even semi-comfortable saying "we use AI doctors". An even higher percentage would be necessary for an insurance company to feel comfortable mandating AI doctors. And we'd need AIs to do consistently better than nearly all the humans for humans to choose AI doctors independently of their insurers forcing them to use AI doctors.
I feel like at the rate AI is developing we will rapidly get to this point, then surpass it. Doctors will also probably be "enhanced" by AI. Imagine feeding all of your data (more than a human could digest, especially for every patient) into an LLM and letting it diagnose...
On one hand I'm a bit hesitant trusting a GP because of a human factor. Doctors may be overwhelmed with patients and your fate kind of depends on their mood today and General Proficiency (couldn't miss this pun).
On the other hand, I feel scared about perspective talking to a chat bot instead of a real person when it comes to my health.
I think, my best bet would be to keep physical GPs but build some tools to make their job more efficient. How to avoid the situation that they are getting lazy and blindly accepting all the AI proposals? I don't know. I hope we will find the way!
that's not inevitable though - it's a conscious decision made by each and every person in power to let it get to that point.
Agree. I see parallels to communism: in theory it sounds alright - spread the wealth, everyone works for the collective etc. - but in practise it doesn’t work because people are greedy and leaders inevitably become dictators.
With AI it’s similar in that in theory it could be impartial and level playing fields, but in practise they will be run by companies and governments where the same old human fallibilities persist.
If you can’t trust the leaders then you can’t trust their machines either.
There exists the possibility we have technology and feudalism.
It also depends on how you define "technology": was/is the plough "technology"? The bow and arrow? Blacksmithing forge? Anvil? Water wheels? The wheel? The stirrup?
There exists the possibility of many things. The Pope made an appeal to empiricism. In our timeline, industrialisation brought forth a burst in democracy and the downfall of feudalism.
Not everywhere:
* https://en.wikipedia.org/wiki/Industrialization_in_the_Sovie...
* https://en.wikipedia.org/wiki/Great_Leap_Forward
It should also be noted that the Industrial Revolution occurred in the early 1800s:
* https://en.wikipedia.org/wiki/Industrial_Revolution
Democracy was already around by then:
* https://en.wikipedia.org/wiki/Parliament_of_the_United_Kingd...
* https://en.wikipedia.org/wiki/American_Revolution
I think it is more accurate to say the the presence of democracy was part of the environment that allowed industrialization to occur. It was (e.g.) UK acts of Parliament that developed canals and later railroads:
* https://en.wikipedia.org/wiki/History_of_the_British_canal_s...
Democracy was around millennia ago. The frequency of democracy increased after industrialisation, in part due to its effects on the middle class. Britain and America’s democracies expanded because of it; Europe’s finally found purchase and, in the post-colonial era, so did other continents.
> the presence of democracy was part of the environment that allowed industrialization to occur
Probably not [1].
[1] https://acoup.blog/2022/08/26/collections-why-no-roman-indus...
That capitalism causes democracy is so high-level that it’s just a propaganda line. People from Marxists to neoliberals could say the same thing (meaning different things when interrogated).
We have no evidence capitalism causes democracy. But every democracy on the planet emerged from a context with private property and the rule of law.
The Athenians and Romans weren’t capitalist. But they were closer to it than Marxism or neoliberalism. (They both had private property, money in elections, trade, finance, et cetera.)
False premise.
> But they were closer to it than Marxism or neoliberalism. (They both had private property, money in elections, trade, finance, et cetera.)
Just false.
That doesn't sound right at all. It's much easier now for random people to obtain social and political influence, regardless of affiliation. The left is experiencing global distress because they're so worried by the dispersal of social and political influence away from legacy institutions and towards anonymous "chaos actors", as they see it. This is a vast equalization of access to the means of social and political influence, but the Pope thinks it's the reverse. I don't understand that take at all.
[1] https://en.wikipedia.org/wiki/Extreme_poverty
Some people today could endanger the lives of those they disagree with, simply by doxxing them. Yet, they'll face little to no opposition in the courts because they're uber-rich. No one should hold the power of life or death on a whim.
I generally like Francis’ take on things, and I think the main framework of this doc is interesting: “AI is functional, not grounded in physical reality, and not spiritual, therefore it’s not a replacement for human intelligence, and we should be cautious” is fine. I’m not sure I agree on these definitions but until I started working with llms daily, I felt the same way.
But the bogeyman of inequality as a reason to mistrust technology, written in HTML, sent over the internet, to our phones, bothers me.
> 31. However, even as AI processes and simulates certain expressions of intelligence, it remains fundamentally confined to a logical-mathematical framework, which imposes inherent limitations. Human intelligence, in contrast, develops organically throughout the person’s physical and psychological growth, shaped by a myriad of lived experiences in the flesh. Although advanced AI systems can “learn” through processes such as machine learning, this sort of training is fundamentally different from the developmental growth of human intelligence, which is shaped by embodied experiences, including sensory input, emotional responses, social interactions, and the unique context of each moment. These elements shape and form individuals within their personal history.In contrast, AI, lacking a physical body, relies on computational reasoning and learning based on vast datasets that include recorded human experiences and knowledge.
But there's nothing about AI in general that limits it to learning only from prior data, and we're already seeing robots such as Boston Dynamics's Spot learning to navigate and act in novel environments. We're probably still far from passing Steve Wozniak's Coffee Test, but we're advancing towards it, and for a take that's supposed to be based on philosophy/theology, I would have hoped that they go a bit beyond the current state of the art.
Do you think? At this point I have the impression it's just a problem of dexterity and speed. Understanding, planning and navigation seem basically solved.
There's too many challenges of the kind "Seek information about ... " and "adapt a multi-step process to overcome ... ".
One industrial process that is only now being automated is connected trailers to trucks. They have to connect a hose and a few lines. Two companies are struggling with this even now. (outrider and isee). Both well funded and staffed by intelligent folks, and have to coax a robotic arm into connecting a hose that we all know is there, but not where, to a port that we all know is there, but might be different than expected.
Then of course the manipulation of objects is still tricky and needs improvements, but the "general intelligence" needed to adapt to a novel environment is already there.
> "The Coffee Test has been proposed, and is attributed to Steve Wozniak, one of the founders of Apple Computers. According to Steve, this test would require a robot, not a computer screen. The robot would need to locate the kitchen and brew a pot of coffee in a random house that it had never seen before.
And more specifically, I disagree that such a system would work just from video frames. The issue isn't so much "Coming up with text that sounds right", it's more about state and environment representation, novelty, planning multi-step processes, and so on.
A good test of if this were easy, is can it be done in game engines, which negate all the speed / repeatability / controls complexity almost entirely. Plug an LLM into a game engine with a hovering arm that can grab and place and push buttons, and have it "make coffee" in procedural generated kitchens, coffee makers, etc. Bonus points for using POV imagery, bonus points for using bags of grains that might be coffee but might not. Similar weight, feel, placement. Hell my coffee, coca, sugar, and flour are right next to each other.
That would be a landmark top tier research accomplishment and top HN article for days (the real accomplishment!)
this has to be refined to make a reasonable statement.. as stated, cannot agree on the expansive word "nothing"
[0] https://en.wikipedia.org/wiki/Online_machine_learning
Maybe not, but I don't think this is exactly what the piece said here: "AI, lacking a physical body, relies on computational reasoning and learning based on vast datasets that include recorded human experiences and knowledge."
Do you think AI will soon get a physical body, and experience "sensory input, emotional responses, social interactions, and the unique context of each moment"?
Even if we are talking about the best cameras in the world, they pale in comparison to our eyes. To say nothing of touch, taste, and smell. Advances here look to be far-off.
At the end of the day, a brain also processes information completely differently than LLMs. Anyone who says otherwise is both uneducated medically and thinks laughingly little of themselves.
Let's say we have an AI which, through peripheral devices, can attain human-level sensory processing. Is it human yet? Can it understand mortality? How about morality? Does it experience pain? Is that something we want to build?
Helen Keller, despite lacking sight and hearing, was still able to perceive the world through sensory input, including taste, touch, and smell - and although she could not hear, she could still feel warmth and the touch of another human, and experienced emotions. (She may not be the best example for your argument, either, as she was born with sight and hearing.)
A better question might be, how much less of a human is a human brain organoid? https://www.michiganmedicine.org/health-lab/artificially-gro...
> Do you think AI will soon get a physical body, and experience "sensory input, emotional responses, social interactions, and the unique context of each moment"?
In fact, my point was that it's not clear that all of these features simply "added inputs." (Hence my questions around emotions, pain, mortality, and morality.)
Also, we have absolutely no idea how the brain works. Current AI was developed off of modern theories on how the brain works. Saying that AI doesn’t represent how the brain works is ridiculous because the whole story of AI was that we developed a theory of how the brain worked, modeled it through tech, and it worked way better than we thought it would. Shit there was a whole article here about how AI resembles Kant’s theory of the mind. Like I just don’t know how you can be so confident here.
I think my comment was misunderstood, so let me try to break it down a little. Let's remember that this was in the context of "there's nothing about AI in general that limits it to learning only from prior data":
- Senses are used to ingest information, and processors process that information into usable data. The density of the information ingested, and the speed at which it is processed, and the nature of how processing occurs, is vastly different. To further break it down: I'm stating that we don't yet have sensors anywhere near as capable as humans, and that even if we did, without a human brain to process the data, you will receive a different output. Again, see photography for more on this. And we have not even begun to scratch the surface of touch or taste. I understand the touch issue is (one small part) of why general purpose personal robots are not yet viable. I argue that we are a LONG way off from computers being able to interpret the world in a similar fashion to humans.
For example, Caltech researches note that while our brain can process thoughts at only 10 bits / second, our sensory systems process 1 billion bits / second: https://www.caltech.edu/about/news/thinking-slowly-the-parad...
I believe our sensory capacity is a large (but not complete) part of what it means to be a living animal.
- Emotion still appears to be exclusive to living things, not machines. It's unclear what is necessary for this to change this. This is a limiting factor to computers being able to understand the world, "social interactions, and the unique context of each moment," which was the claim in question.
- As far as I'm aware, no LLM today exhibits true reasoning or morality. While LLMs are certainly impressive in their ability to recall information from compressed data, and even generate streams of text that look like reasoning, they are still simply decompressing stored data. Morality today is implemented as content filters and fine-tuning of this statistical model.
> Also, we have absolutely no idea how the brain works. Current AI was developed off of modern theories on how the brain works. Saying that AI doesn’t represent how the brain works is ridiculous because the whole story of AI was that we developed a theory of how the brain worked, modeled it through tech, and it worked way better than we thought it would.
It makes me really sad when people say this, because it's incredibly disingenuous. There are certainly more questions than answers when it comes to the brain, but we _do_ understand quite a lot. It's not surprising to me that people who are focused on technology and AI would anthropomorphize machines, and then claim that (because they aren't aware of how the brain works) "we don't know how the brain works." I had similar beliefs, as a software engineer. But, after watching my partner attend medical school and residency, it's become clear that my own knowledge is far from the sum of humanity's knowledge in this area.
You're absolutely right that LLMs borrow concepts from neuroscience, but they are still a VERY long way from "recreating the brain." I genuinely find it sad that people think they are no smarter / better than an LLM. Keep in mind no LLM has even passed a Turing test yet. (No, I'm not talking about the Facebook comments section - I'm talking about a test where someone knowingly communicates with a machine and a human through text, and through targeted questions and analysis of the answers, is unable to ac...
Also, the base of machine learning centers around simulating emotions: if the AI does something good, it's rewarded. If it does something bad, it's punished. We created the whole algorithm by simulating Freud's pleasure principle and who are we to say that the simulation is any different from the real thing? > It's not surprising to me that people who are focused on technology and AI would anthropomorphize machines, and then claim that (because they aren't aware of how the brain works) "we don't know how the brain works." I had similar beliefs, as a software engineer. Well I'm actually much more knowledgeable about humanities than I am about tech, and IMO the tech world is at the forefront of making our abstract philosophical understanding of the brain concrete. Neural networks and LLMs are the most successful method of creating cognition. I'm sure we'll find that there's a lot more to do, but this could very well be the fundamental algorithm of the brain, and I don't see any reason to discount that by saying what you've been saying in this comment thread.
You're assuming the sensory organs passively take in information, instead of creating it from all the noise in the world. That the world feeds us information the way we feed generative models. But humans have already taken the trouble to create the information in language, images, video.
Hinton has some research on a forward-forward learning paradigm [1], which might be closer to how our brains learn (but the artificial implementations are not great yet). He also posits that maybe the purpose of humans' dreams are generating negative data for such a contrastive forward-forward learning mechanism.
[1] https://arxiv.org/abs/2212.13345
Wait, what? Can you elaborate on this? That seems... wrong.
Additionally, the human eye has a resolution of approximately 576 MP. This is one reason why we can often see details in the distance that disappear in a photo.
Finally, while it's arguably not "better," the brain processes images very differently. This is another reason why the image you take often looks "worse" than what you saw in person, or why you can't get the colors to look "quite right", etc. If you get into photography, you start to "see" the things your eye was previously rewriting for you (like a green color cast on skin when you're in the forest) - but it's not the natural way your brain process information.
You can also look up estimates on the processing rate of human's sensory system - it's quite impressive.
Less related, but things like this are interesting too: https://languagelog.ldc.upenn.edu/nll/?p=17970
But the current cycle is not about that type of intelligence or life at all, it's strictly about mathematical simulation of intelligence on multitenant systems with shared information and thought-processes alternated through time( training,reinforcement, labelling, inference, 3rd party microservices).
I understand it is possible we will see a jump to a completely different type of AI, but we need to be very clear that this is not what's going on right now.
The word ēruditio (learning/erudition) is in the nominative case while machinārum is in the genitive plural of māchina.
Note: I am a noob Latin language learner, if you're interested check out the great textbook LLPSI[0]!
[0]: https://en.wikipedia.org/wiki/Hans_%C3%98rberg#LINGVA_LATINA...
----
104. Technology offers remarkable tools to oversee and develop the world's resources. However, in some cases, humanity is increasingly ceding control of these resources to machines. Within some circles of scientists and futurists, there is optimism about the potential of artificial general intelligence (AGI), a hypothetical form of AI that would match or surpass human intelligence and bring about unimaginable advancements. Some even speculate that AGI could achieve superhuman capabilities. At the same time, as society drifts away from a connection with the transcendent, some are tempted to turn to AI in search of meaning or fulfillment---longings that can only be truly satisfied in communion with God. [194]*
105. However, the presumption of substituting God for an artifact of human making is idolatry, a practice Scripture explicitly warns against (e.g., Ex. 20:4; 32:1-5; 34:17). Moreover, AI may prove even more seductive than traditional idols for, unlike idols that "have mouths but do not speak; eyes, but do not see; ears, but do not hear" (Ps. 115:5-6), AI can "speak," or at least gives the illusion of doing so (cf. Rev. 13:15). Yet, it is vital to remember that AI is but a pale reflection of humanity---it is crafted by human minds, trained on human-generated material, responsive to human input, and sustained through human labor. AI cannot possess many of the capabilities specific to human life, and it is also fallible. By turning to AI as a perceived "Other" greater than itself, with which to share existence and responsibilities, humanity risks creating a substitute for God. However, it is not AI that is ultimately deified and worshipped, but humanity itself---which, in this way, becomes enslaved to its own work. [195]*
The idea of building a God is enticing [2], but I am not religious and prefer not to put faith in such things.
[1] https://en.wikipedia.org/wiki/Singularitarianism
[2] https://en.uesp.net/wiki/Lore:Numidium
And yes, that's certainly a plausible hurdle.
Can't unplug from banking, even when literally communists (literally literally, I've met some proud of being communists, they still got a mortgage).
Coal and petroleum-based fuels are slowly getting unplugged, but the issues were known over a century ago, and the transition only became relevant scale when the alternative was already much cheaper — and it's not yet clear how much damage has been done in the intervening years.
--
Any AI worth using is so because it's at least one of [cheaper, better] than a human on the same task: any AI which is both more expensive and worse just doesn't have any reason to be used in the first place.
This means that "unplugging" an AI comes with a cost of losing every advantage that made you start using it in the first place.
An AI which is "only" as misaligned as one of the major industrial sectors of the world, that is made out of humans who are necessarily able to care about human interests, and which drove a huge amount of economic improvement and brought with it derivatives such as basically all polymers, is still capable of great harm. And because of those benefits, society as a whole still has not unplugged the oil drills.
The more power there is in a system, the harder it is to keep it aligned with our best interests, even when there are humans not just at the wheel but occupying every step.
And the more aligned it is, the harder it is to "just unplug it" when things — as is inevitable because nothing is perfect — do go wrong.
It will control the electrical grids with 'smart' decisions that improve the efficiency and make it's removal impossible without taking out all power.
It will integrate with water and waste processing to ensure leaks don't exist in the system and everything is working smoothly.
It will be in all transportation and distribution networks because companies want profits from efficiency before they'll think deeply about the risks.
Then after it's pretty much everywhere ensuring you down starve and dehydrate, who the hell would be dumb enough to unplug it in the first place.
It's kinda like telling people to shut off every computer today, not a chance in hell it would or could happen without terrible life risking consequences.
If you want something the wealthy can't control, you'll need to look a good deal further afield than AGI. Think gamma ray bursts, asteroid strikes, or solar flares. But anything built by man, they'll have a pretty good grip on.
Being ruled by rich robots is not the worst; that means that they let you live!
I mean one of the points of 'Actual AGI' is AGI will be able to build more AGI, then we're not talking about something built by man.
Now, when will we see that, I'm not making any predictions. At the same time trying to make predictions of a system that could do that is probably much harder still.
AGI would only get smarter and smarter the more hardware came out. They'd have no way to keep it in check. If they tried to handicap it then they'd lose out to their competitors AGI too...
Part of the problem is that "do what I said without question" will lead to disasters, but "figure out what I would approve of after seeing the result and be creative in your interpretation of my orders accordingly" has different ways it can go wrong.
(IMO, RLHF is the latter).
Both of those seem to be safer than "maximise my reward function", which is what people were worried about a decade ago, and with decent evidence given the limits of AI at the time.
which leaves unprecedented power in the hands of the most psychopathic[0] part of the population. so even if AI take off doesn't happen, we're still getting the boot on our necks.
[0] https://www.forbes.com/sites/jackmccullough/2019/12/09/the-p...
Though I would note even your link says:
> Roughly 4% to as high as 12% of CEOs exhibit psychopathic traits, according to some expert estimates, many times more than the 1% rate found in the general population and more in line with the 15% rate found in prisons.
On the plus side, this is still a small minority.
On the down side, these remind me a lot of Musk:
> CEO who worked with several pregnant women told people that he had impregnated his colleagues.
By way of Neuralink.
> CFO thought his CEO had a split personality, until he realized that he was simply playing different characters based on what he needed from his audience.
"Will my rocket explode?"-Musk is a lot more cautious and grounded than everything-else-Musk — including other aspects of work on SpaceX.
> Autocratic CEO fired a well-respected engineer “just to make a statement.” He fired anyone who challenged him, explaining there was no reason to second-guess him because he was always right and needed people to execute his vision rather than challenge it.
Basically all of Twitter, plus some other anecdotes from Starlink, SpaceX, Tesla.
And, this month, fighting with Asmongold about cheating in Path of Exile 2, before admitting to what he was accused of but trying to pretend it's fine rather than "cheating".
> CEO would show up to work and begin yelling at an employee (usually someone in sales) for no obvious reason.
The guy he called a pedo for daring to say a submarine wasn't useful for a cave rescue, the Brazilian judiciary, members of the British cabinet, …
But it looks to me like there's a decent number amongst the other nine who know what grenades are and don't want them to get thrown by the tenth.
The power dynamics here could be just about anything; I don't know how to begin to forecast the risk distribution, but I definitely agree that what you fear is plausible.
The Ballad of the White Horse by G. K. Chesterton - https://www.gutenberg.org/files/1719/1719-h/1719-h.htm
https://news.ycombinator.com/item?id=42028697
You just defined idolatry and why it is harmful. Idolatry is the worship of man-made things or other things that do not deserve worship. Including worshipping the government, which is the religion of most people. It is a false path.
And hey, when it comes to fallible Gods, ancient Greek mythology is also pretty wild.
Then argue for the opposite. That a Buddhist can believe in the Abrahamic God.
In this respect, the Catholic Church got it right with the concept of excommunication.
I can't wait to find out when the Butlerian Jihad starts.
Is it just me, or is the grammar backwards? I think it should be "substituting an artifact of human making for God", or "substituting God with an artifact of human making".
Source: I'm spanish speaker.
https://www.sbnation.com/a/17776-football
Voyager 6 is lost in a black hole, is upgraded by an alien race of machines, and obtains sentience. Then it comes back to earth and the Enterprise gang has an interesting time.
> 38. ... The Church is particularly opposed to those applications that threaten the sanctity of life or the dignity of the human person.[78] Like any human endeavor, technological development must be directed to serve the human person and contribute to the pursuit of “greater justice, more extensive fraternity, and a more humane order of social relations,” which are “more valuable than advances in the technical field.” ...
> 39. To address these challenges, it is essential to emphasize the importance of moral responsibility grounded in the dignity and vocation of the human person. This guiding principle also applies to questions concerning AI. In this context, the ethical dimension takes on primary importance because it is people who design systems and determine the purposes for which they are used.[80] Between a machine and a human being, only the latter is truly a moral agent—a subject of moral responsibility who exercises freedom in his or her decisions and accepts their consequences.[81] It is not the machine but the human who is in relationship with truth and goodness, guided by a moral conscience that calls the person “to love and to do what is good and to avoid evil,”[82] bearing witness to “the authority of truth in reference to the supreme Good to which the human person is drawn.”[83] Likewise, between a machine and a human, only the human can be sufficiently self-aware to the point of listening and following the voice of conscience, discerning with prudence, and seeking the good that is possible in every situation.[84] In fact, all of this also belongs to the person’s exercise of intelligence.
He even brings up x-risk at one point, which gives me some hope in this message reaching those members of the faith who have influence on the new administration.
The real challenge is standardizing safety across open models and countering malignant AI use, especially amid demographic challenges like declining fertility.
[1] https://x.com/jamescurrier/status/1884057861514485803?s=46&t...
Nope, that is an unsubstantial argument. Geoffrey Hinton, the „God father of AI“ is neither suicidal, nor homicidal.
edit: typos
But while their goal was not to die, their lack of concern about the risks killed them anyway.
This belongs in the “If they fully comprehended the risks, their behavior could only be described as suicidal” category.
-- Erich Fromm, https://www.marxists.org/archive/fromm/works/1961/man/ch05.h...
This always annoyed me about religion. Such a lazy cop out no answer to such important question.
We don’t need god to find meaning or fulfillment
And we definitely don’t need other people pretending to be the one true channel through which to connect with God either
Religion, or at least Catholicism, recognizes four things that humans look to for happiness: wealth, honour, glory/fame/power, and pleasure.
* https://www.newadvent.org/summa/2002.htm
It concludes that these things can be good, they are not the highest good. The thing that will make humans most happy is love: love for one's neighbour, and love for God, who is Love:
* https://en.wikipedia.org/wiki/Deus_caritas_est
Or if you want to get more philosophical and less theological, Aristotle goes over why those four things are not ends in themselves, but means to an end:
* https://en.wikipedia.org/wiki/Nicomachean_Ethics
There is a growing amount of evidence that the need for love (community), which other people are needed for, is central to human fulfillment:
* https://news.harvard.edu/gazette/story/2017/04/over-nearly-8...
* https://magazine.hms.harvard.edu/articles/good-life
In the Christian tradition, love of neighbour is important:
> "Teacher, which commandment in the law is the greatest?" He [Jesus] said to him, "'You shall love the Lord your God with all your heart, and with all your soul, and with all your mind.' This is the greatest and first commandment. And a second is like it: ‘You shall love your neighbor as yourself.’ On these two commandments hang all the law and the prophets."
* https://en.wikipedia.org/wiki/Great_Commandment
And how does one love both God and neighbour at the same time? By loving one's neighbour one loves God as well:
> Then the righteous will answer him, saying, 'Lord, when did we see you hungry, and feed you; or thirsty, and give you a drink? When did we see you as a stranger, and take you in; or naked, and clothe you? When did we see you sick, or in prison, and come to you?'
> The King will answer them, 'Most certainly I tell you, because you did it to one of the least of these my brothers, you did it to me.'
* https://en.wikipedia.org/wiki/The_Sheep_and_the_Goats
* https://en.wikipedia.org/wiki/Works_of_mercy
That's a lot of leaps in logic. Knowing that people find community fulfilling can be observed in the people around you without any of that background, so surely it's the simpler concept?
https://news.ycombinator.com/newsguidelines.html
Doesn't that describe all religion? I mean, you're telling me that the infinite creator of the universe cares about the prayers, the suffering, the aspirations, and the sexual habits of a bunch of finite beings? The hubris! It seems obvious to me that the gods of all religions are designed by human minds to be receptive to human interests, otherwise nobody would bother worshipping them. In other words, we have always been worshipping ourselves. At least there is reason to think that AI could, at least in theory, be what we expect God to be.
Nah that's just what atheists convince themselves. There's nothing obviously nor truthful about this conclusion or the line of reasoning behind it.
All arguments for and against the existence of God are inherently unfalsifiable, but that doesn't mean atheism is inherently more logical than theism.
In fact, from my point of view, the existence of God is way more logically sound than the alternative, and atheists are the ones following delusions and worshipping their own egos
As to the particulars of the imagined God, actually we do have some evidence for the parameters. The Princess Alice experiments in particular illustrate one desirable property, God (in the experiment, "Princess Alice") should provides behavioural oversight. An imaginary being can deliver effective oversight which would otherwise require advanced technology, but to do so the being must also believe in these arbitrary moral rules.
And that matches what we observe. People do buy Sithrak T-shirts, but, more or less without exception they don't actually worship Sithrak, whereas loads of people have worshipped various deities with locally reasonable seeming moral codes and do to this day.
I'm guessing you're one of those people who thinks atheism means a belief in the absence of a god, rather than its actual meaning, which is an absence of a belief in a god.
https://en.wikipedia.org/wiki/Atheism
I'm not trying to make a "No True Christian" argument but rather just want to assert that reform does happen both for good and ill. Luther's original reform, in part, was to point out that political concerns within the church were overriding the spiritual concerns of the laity. He wanted to refocus faith on a personal relationship with God. One major criticism of that refocus is that it caused individuals to become over-focused on the self instead of God (as embodied in the institution of the church).
In both cases you could argue that the principle problem is when the focus of faith is something in the world (either the church or the individual). So I think it is perhaps too far to say that "we have always been worshipping ourselves" when the criticisms within and without the church are pointing that out as the problem that triggers the reform.
That is, both Luther and Stirner can be correct in their criticism of religious institutions. There is more than one way to get it wrong.
But also in this text we can feel the idea of the human soul and free-will crumbling, that also are the core of secular humanism.
Marxist analysis is also challenged, as we can speculate that AI would make the organic composition of capital to go to the roof... but you can really talk about OCC in regards of singularity AIs resembling more the Aladdin lamp or the Green Lantern ring than a highly automated factory, without even mentioning the possibility of an agency on their own?
Yes.
> The hubris! It seems obvious to me
I would turn that around and claim hubris on your part. You seem to think that your mind and the mind of God are similar, and limitations you perceive are limitations for God.
How come? You think I'm saying that the infinite creator of the universe is unlikely to care about the fate or well-being of humans because... I wouldn't if I was him? I mean, I would. Because I have a human mind. But if there are indeed no similarities between God's mind and my own, well, anything goes, doesn't it? Him caring is just one small possibility out of trillions of alternatives.
> and limitations you perceive are limitations for God.
What limitations? I haven't listed any limitations. Neither a God who cares nor a God who doesn't care is limited. I just don't see why I would assign a particularly significant probability to the former case. It sure would be convenient, but I feel like God being moral in any way that I can relate to would inevitably be projection on my part.
"And [Jesus] came to Nazareth, where he was brought up: and he went into the synagogue, according to his custom, on the sabbath day: and he rose up to read. And the book of Isaias the prophet was delivered unto him. And as he unfolded the book, he found the place where it was written:
'The spirit of the Lord is upon me. Wherefore he hath anointed me to preach the gospel to the poor, he hath sent me to heal the contrite of heart, To preach deliverance to the captives and sight to the blind, to set at liberty them that are bruised, to preach the acceptable year of the Lord and the day of reward.' And when he had folded the book, he restored it to the minister and sat down. And the eyes of all in the synagogue were fixed on him. And he began to say to them: 'This day is fulfilled this scripture in your ears.'"
~ Luke 4:16-20
https://biblehub.com/drbc/luke/4.htm
Do you care about the functioning of every cell in your body? Ask any cancer patient if they do.
I'm a Christian, and I absolutely agree with you that this is absurd! And if God hadn't said it Himself and then proved it true by His actions (both historically, and even in my own life), I'd be right there with you to call it idolatry.
For what it's worth, however, the quoted argument does also feel somewhat hubristic to me: As I see it, it boils down to "I don't understand how God could be this way, and therefore He cannot be this way." I believe that, somewhat ironically, He is beyond our understanding even when it comes to knowing what it means for Him to be beyond our understanding.
"remember that AI is but a pale reflection of humanity" and "AI cannot possess many of the capabilities specific to human life"
We just don't know yet. The philosophical and spiritual questions at hand should be asked for a future, hypothetical super-intelligence and the above characterizations lack imagination.
There is no reason to believe AI will ever be more than a compressed and queryable form of the Internet and this passage seems to imply this rational and scientifically informed view. Imagination means nothing in the context of scientific debate.
Plato covers a lot of this kind of thing and it is maybe useful to use his framework (since much of modern Catholicism has a healthy dose of Platonism). Both flowers and music can be called "beautiful" and there is some sense in which both partake in a universal "Beauty". Yet at the same time the nature of the beauty of flowers and music is distinct. This is a difficult paradox to contemplate.
And so it may be with Intelligence. There may be some Platonic form of Intelligence that both humans and AIs partake in, but there may be some aspect of the human manifestation of that form that will forever remain distinct to humans.
Of course, it is up to you how much you value the distinctness of that expression of the universal form. Catholic faith suggests that the particular distinctiveness of human expressions of these forms is "divine" in some sense. That is, it is our manifestation of the universal that is valuable, not the universal in and of itself.
Lets not forget the converse may be true for AI. Humans may be a very specialized form of intelligence (though we do like to consider ourselves general intelligences).
Imagine a science fiction future where we use AIs to enhance neuroscience to determine how to make Octopuses more intelligent, such that they reach LLM levels or near human levels of language. Is their brain not a neural network that could be optimized?
In our wildest dreams we might consider the breadth of intelligence possible and our particular relationship with respect to it. We might face questions that are harder to answer than we anticipate.
Perhaps considering the question is more important than deciding on an answer?
Also, humans have definitely created things that are better, at least in some aspects, than humans.
Cars are faster than humans.
Even AI-specific, AI chess engines are a lot stronger than any human alive, even then all humans combined.
I was just criticizing the idea that it's impossible for something to make something better than itself. Maybe not in all aspects, but at least in some, it's definitely possible.
Everyone now uses intelligence to mean whateva ChatGPT can do, but all those language models combined don't even show 1/10th of my Cat's intelligence.
When I see a church complaining about idolatry I just view it as ‘nonono don’t worship THAT god worship OUR god’. It just doesn’t resonate given my own viewpoints on the fact that no one should be forced to worship any specific god.
Another cool example is Lewis Mumford’s argument that the industrial age actually started with monks creating rudimentary clocks and organizing life according to specific times in order to achieve their monkish ends.
https://en.wikipedia.org/wiki/Technics_and_Civilization
Once there's a central authority at risk from technology eroding at their base, they will be undermined. Like Catholicism, Islam, the Orthodox Church, etc. all of which were practically sidelined when print and media became more prevalent.
Interestingly all 3 of the above examples maintain strict conditions that their respective holy books must not be translated into the local languages.
Congratulations, you're one of today's lucky 10,000!
https://en.wikipedia.org/wiki/Glagolitic_script
> The Glagolitic script (/ˌɡlæɡəˈlɪtɪk/ GLAG-ə-LIT-ik,[2] ⰳⰾⰰⰳⱁⰾⰻⱌⰰ, glagolitsa) is the oldest known Slavic alphabet. It is generally agreed that it was created in the 9th century for the purpose of _translating_ liturgical texts into Old Church Slavonic by Saint Cyril, a monk from Thessalonica. He and his brother Saint Methodius were sent by the Byzantine Emperor Michael III in 863 to Great Moravia to spread Christianity there.
The Catholic and Orthodox churches have _always_ striven to make the Scriptures available to the people in languages they could understand.
The first effort of the Catholic Church to translate the bible happened during the papacy of Pope Pius XII, which began in _1939_. They didn't encourage it before that, but it took the Protestant Reformation and the Council of Trent (1545-1563) to decide that Bible translators would not be prosecuted. The first sanctioned English translation happened in 1582, a full 1500 years and some more after Christianity was founded, in the backdrop of the Thirty Years War.
Also remind me, which languages are these religions' respective services conducted in?
I struggle to see how this is anything but a direct lie. Even ignoring that the Church's translation of the Vulgate itself (from the original Greek and Hebrew) took place in the 4th century, the first _Catholic French_ translation was published in 1550, and there was never a question of whether to persecute the authors. You might say, but that was because of the Reformation -- then consider the Alfonsine Bible, composed in 1280 under the supervision a Catholic King and the master of a Catholic holy order. Well before then there were partial translations too: the Wessex Gospels were translated in 990, and to quote Victoria Thompson "although the Church reserved Latin for the most sacred liturgical moments almost every other religious text was available in English by the eleventh century".
So the longest period you can get where the Church was not actively translating texts was c. 400 - c. 900, a period you probably know as the "Dark Ages" specifically thanks to the fact that literary sources of all kinds were scarce, in no small part because the resources to compose large texts simply weren't there. Especially when you consider that those who could read and write generally knew how to read and write Latin -- vernacular literacy only became important later, with the increase in the number of e.g. merchants and scribes -- such translations held little value during that period.
Strange then that the Pope asked someone to translate the Christian Bible—originally written in Koine Greek—into Latin, the lingua franca of the Western Mediterranean:
* https://en.wikipedia.org/wiki/Vulgate
> Tyndale's translations were the first English Scriptures to draw directly from Hebrew and Greek texts, the first English translation to take advantage of the printing press, the first of the new English Bibles of the Reformation, and the first English translation to use Jehovah ("Iehouah") as God's name.[a] It was taken to be a direct challenge to the authority of the Catholic Church and of those laws of England maintaining the Church's position.
https://en.m.wikipedia.org/wiki/William_Tyndale
Fun fact, every English Bible you see today draws from this bloke's work. And you all executed him lol.
Nothing about translation work:
> In Tyndale's case, he was held in prison for a year and a half: his Roman Catholic inquisitor, Jacobus Latomus, gave him the opportunity to write a book stating his views; Latomus wrote a book in response to convince him of his errors; Tyndale wrote two in reply; Latomus wrote two further books in response to Tyndale. Latomus' three books were subsequently published as one volume: in these it can be seen that the discussion on heresy revolves around the contents of three other books Tyndale had written on topics like justification by faith, free will, the denial of the soul, and so on. Latomus makes no mention of Bible translation; indeed, it seems that in prison, Tyndale was allowed to continue making translations from the Hebrew.[40] Thomas Cromwell was involved in some intercession or plans such as extradition.[41]:220
> When Tyndale could not be convinced to abjure, he was handed over to the Brabantine secular arm and tried on charges of Lutheran heresy in 1536. The charges did not mention Bible translation, which was not illegal in the Netherlands.[40]: 317, 321
* https://en.wikipedia.org/wiki/William_Tyndale#Betrayal_and_d...
In Germany, typical catholic church services are held in German.
First of all, I do not know of many (any?) cases of people being executed for translating a Bible, despite that being a crime at certain points in time. Generally the given reason was for unrepentant heresy -- e.g. someone has pointed out elsewhere that what we know about Wycliffe's trial and inquisition essentially leaves out his translation entirely, focusing instead on the doctrines he espoused. You seem to have the apprehension that there were just dozens of people being thrown on the fires over this, but that's just really not the case. Translation was banned as a blanket measure to control the spread of known heretical translations (e.g. for the Oxford Synod, the Tyndale Bible), it was not a serious concern in and of itself.
> And remind me which language church services in the Latin rite are conducted in to this day?
Do you mean the Roman Rite? There is no such thing as a "Latin Rite". The distinction is important because the language most Roman Catholic services are conducted in is the vernacular one, and has been for 50+ years now. There are a handful of Latin masses (using the old Tridentine missal) still going on, but I think something like 98%+ are using the vernacular missal from Vatican II.
And honestly, even before then... the Latin parts of the Mass were largely prayers which did not change, so you tended to pick them up, especially given that there were parts where you were supposed to speak as well. It's not too hard to memorize what "Et cum spiritu tuo" means. The gospel readings and homilies were themselves in the vernacular, since of course they were longer and meant to communicate teachings to the populace. So I don't understand what your problem is -- fixed prayers being said in vernacular is somehow antithetical to good religion?
But regardless, if you want, today you can go and find a bajillion Catholic Churches doing English mass, or Spanish mass, or Chinese mass, or whatever language you're interested in.
This is absolutely not the case for Islam. According to An-Nawawi, Al-Majmu', (Cairo, Matbacat at-'Tadamun n.d.), 380, at least a chapter of the Qur'an was translated to Persian by a companion of the Prophet ﷺ. This would have been forbidden by the Prophet if translating the scripture was haram in principle.
Edited for clarity: This is mostly a reference to the 40k universe, specifically the Men of Iron (artificially created thinking machines) and how AI is banned because of it, and it is quite literally 'heresy' to create anything resembling artificial general intelligence. I stand behind my assertion that the Vatican would not support any form of intelligence that could argue theology better than it.
The traditional Christian church, and the modern tech church. Both can cry heresy at any moment and send their pitchfork and torch armed mobs onto the net to place you on the pyre.
Just saying it's wise to steer clear of both of these "-isms". In fact, personally, I think it's good to steer clear of any "-ism". Even those that wouldn't self identify as "-isms". Like tech- "ism". Or woke- or anti-woke- "ism". Etc etc.
It's not out of the ordinary for even Anglosphere philosophers to fall into a kind of essentiallism about intelligence, but I think the treatment of it here is extremely careful and thoughtful, at least on first glace.
I suppose I would challenge the following, which I've also sometimes heard from philosophers:
>However, even as AI processes and simulates certain expressions of intelligence, it remains fundamentally confined to a logical-mathematical framework, which imposes inherent limitations. Human intelligence, in contrast, develops organically throughout the person’s physical and psychological growth, shaped by a myriad of lived experiences in the flesh. Although advanced AI systems can “learn” through processes such as machine learning, this sort of training is fundamentally different from the developmental growth of human intelligence, which is shaped by embodied experiences, including sensory input, emotional responses, social interactions, and the unique context of each moment. These elements shape and form individuals within their personal history.In contrast, AI, lacking a physical body, relies on computational reasoning and learning based on vast datasets that include recorded human experiences and knowledge.
I have heard this claim frequently, that intelligence is "embodied" in a way that computers overlook, but if that turns out to be critical, well, who is to say that something like this "embodied" context can't also be modeled computationally? Or that it isn't already equivalent to something out there in the vector space that machines already utilize? People are constantly rotating through essentialist concepts that supposedly reflect an intangible "human element" that shifts the conversation onto non-computational grounds, which turn out to simply reproduce the errors of every previous variation of intelligence essentialism.
My favorite familiar example is baseball, where people say human umpires create a "human element" by changing the strike zone situationally (e.g. tighten the strike zone if it's 0-2 in a big situation, widen the strike zone if it's an 3-0 count), completely forgetting that you could have machines call those more accurately too, if you really wanted to.
Anyway, I have my usual bones to pick but overall I think a very thoughtful treatment that I wouldn't say is borne of layperson confusions that frequently dog these convos.
> Drawing an overly close equivalence between human intelligence and AI risks succumbing to a functionalist perspective, where people are valued based on the work they can perform
One might concede that AI can produce a good enough simulation of an embodied intelligence, while emphasizing that the value of human intelligence per se is not reducible to its effectiveness as an input-output function. But I agree the vatican's statement seems to go beyond that.
That is to say, one view of consciousness suggests that if you froze a snapshot of a human brain in the process of experiencing and then transferred every single observable physical quantity into a simulation running on completely different material (e.g. from carbon to silicon) then the re-produced consciousness would be unaware of the swap and would continue completely unaffected. This would be a consequence of substrate independence, which is the predominant view as far as I can tell in both science and philosophy of mind.
I was fascinated that there was an entire conference dedicated to the opposite view. They contend that there would be a discernable and qualitative difference to the experience of the consciousness. That is, the new mind running in the simulation might "feel" the difference.
Of course, there is no experiment we can perform as of now so it is all conjecture. And this opposing view is a fringe of a fringe. It's just something I wanted to share. It's nice to realize that there are many ways to challenge our assumptions about consciousness. Consider how strongly you may feel about substrate independence and then realize: we don't actually have any proof and reasonable people hold conferences challenging this assumption.
Can you suggest another way to answer your question other than performing an experiment? Can you describe how to perform an experiment to answer your question?
Would you agree to be the subject of such an experiment?
https://en.wikipedia.org/wiki/Mind_uploading and Chapter 8 about Mind Uploading in https://www.researchgate.net/profile/Alfredo-Pereira-Junior/...
The related Reddit conversation https://www.reddit.com/r/Futurology/comments/2ew9i2/would_it...
It seems to be a question that many apparently smart people discuss endlessly for some reason, so I guess I'm not surprised by this proposal in particular, but it's really mystifying to me that anybody other than soulists think there's any room for doubt about it whatsoever.
Well, Searle argued against it when presenting the case for the Chinese Room argument, but I disagree with their take.
I personally believe in the virtual mind argument with an internal simulated experience that is then acted upon externally.
Moreso, if this is the key to human like intelligence and learning in the real world, I do believe that AI would very quickly pass by our limitations. Humans are not only embodied, but we are prisoners to our embodiment and we only get one. I don't see any particular reason why a model would be trapped to one body, when they could 'hivemind' or control a massive number of bodies/sensors to sense and interact with the environment. The end product would be an experience far different from what a human experiences and would likely be a super organism in itself.
It could be at the end of the day that there is something important about the biological basis of the experience and the role it plays in supporting cognition. But simply stipulating that it works that way doesn't represent forward motion in the conversation.
Care to elaborate? Which people and which perspectives? It's a bit unclear to me.
Either way, I must admit that, as a Catholic I appreciate the great discussion here. There are of course the usual snarky comments you would expect regarding the Church and religion (which is fine by me) but overall it's a well grounded discussion.
I'm personally enjoying reading the thoughtful perspectives of everyone.
https://news.ycombinator.com/newsguidelines.html
At a more profound level, I really appreciated point 18 under "Relationality": 'human intelligence is not an isolated faculty but is exercised in relationships, finding its fullest expression in dialogue, collaboration, and solidarity. We learn with others, and we learn through others.'
I was raised Protestant, but taught to be fundamentally skeptical of the political and historical baggage of any religious institution. Though I recognize that writings like this are a result of deeply held faith, it always feels paradoxical when leaders wax poetic about the mystery of God and then say 'so here is what God thinks you should do.' How could they know? That probably sounds basic, but it is my reaction. What draws me back in is the emphasis on our relationships with other human beings. Those relationships are the things that are actually in front of us, and can make a meaningful difference in our day-to-day lives. Something very useful to keep in mind when developing AI (or ABNECUI).
In particular papal infallibility was not involved in the Protestants’ complaints, and the response to their complaints (Trent) was a council and again has nothing to do with papal infallibility.
The pope was also an absolute monarch at the time, but protestants didn’t care about that aspect.
0: https://www.vatican.va/content/john-paul-ii/en/apost_letters...
I was trying to allude to the indulgences with my "bullshit" but I failed.
I tend to focus more on the great awakenings and all the horrible things they led to in how they influenced America.
I thought Protestants were also at some point very against the way the Catholic faith focused on "here's what god meant" rather than letting people interpret the bible themselves? Papal infallibility is just a part of that.
I can’t speak for any religious leader but in terms of Catholic leadership: because in many matters God spoke through the Prophets and then He came down and told us directly which is preserved in Holy Scripture and Sacred Tradition (2 Thessalonians 2:15-17), and the Holy Spirit guides the Church (John 14:26) and does so through the prime ministerial office of the Pope the successor of Peter (Mathew 16:13-19) and through the Bishops the successors of the Apostles (Acts 1:12-26)(Acts 15)
You and the Catholic Church are operating under completely different axioms, so there's no point in responding to someone's explanation of Catholic axioms by just repeating your own axioms more forcefully.
In other words, the relevant question isn't how some pastor "knows" that God says to do XYZ. Obviously they don't. The relevant question is whether and to what extent there's value to be extracted from the collective wisdom of generations of members of an institution whose history stretches back thousands of years.
Whether or not a literal god may have been involved at any point is irrelevant. Right now, we're very far removed from any such claimed involvement, looking at documents that have been written, cherry-picked, translated, rewritten, and reinterpreted many times by many different fallible humans. If the only meaning someone sees in religious guidance is its connection to a literal physical deity, they're in for an exercise in frustration from what is at best the world's longest game of telephone. I think it makes more sense to just accept a religion and its culture and teachings for what they are, and try to be the best person you can be without worrying about how the guy controlling the simulation we live in may choose to mete out rewards and punishments.
This is only true from the Protestant Sola Scriptura perspective. The Catholic and Orthodox traditions hold that God still directs the Church through the Holy Spirit, which makes the documents that you identify only some elements of that direction—an output of the authority granted to the Church—not its final form. So, no, it's not accurate to say that we are far removed from any claims of direct involvement from Deity—several branches of Christianity hold that He is still actively involved.
> If the only meaning someone sees in religious guidance is its connection to a literal physical deity, they're in for an exercise in frustration from what is at best the world's longest game of telephone.
Again, it's not a long game of telephone if God is actually still directing the Church today. If you accept that He guides leadership right now through the Pope and the Bishops, which is the stance articulated by OP, you're at most a few steps removed from His regular guidance.
Which gets back to my original point, which is that this really all comes down to which axioms you want to accept. All religion is unfalsifiable, as you observe, but falsifiability cuts both ways and you can't logic your way out of that to logically conclude the absence or irrelevance of a God. What you can do is decide which axioms you're going to start from and work from there.
Nevertheless, whether or not someone's particular doctrine agrees with the "long game of telephone" stance, I would suggest that a mindset which finds meaning in the teachings and institutions of one's religion independent of their divinity is a more straightforward path to prosocial behavior and inner peace. The idea that anyone should ever suffer genuine anguish or question their personal morals based on doubts of their assumptions about the metaphysical nature of the universe just seems alien and like a non sequitur to me, but from what I understand it's a very real struggle for some people.
At the very least, that’s debatable or less absolute than that.
Because evidence (schisms, actual errors from the Church institution throughout time, not the least sex scandals we are not done with yet) shows that if God was actively directing the Church in the past and today, oh boy… not sure you would be sane to want to follow such a “peculiar” guidance.
Except all the scandals and anti-Popes are empirical evidence of the Holy Spirit guiding the Church. Despite all that the teachings of the Church are fundamentally unchanged. I can read St Justin Martyr and recognize the teaching of the Eucharist from the second century that itself is in continuity with John 6. Go through all Catholic teachings and you’ll find continuity from the beginning despite all the forces that wanted to change it for thousands of years.
The religion founded by the man betrayed by His own Apostle and then disowned or abandoned by the rest, executed brutally and sadistically by the Romans, that religion went on to conquer the Roman world within a few centuries and then make its way through the whole world for thousands of years. Why? Because Jesus rose from the dead and against His Church the gates of hell won’t prevail.
You see continuity and consistence while others see that it’s not only the religion that conquered the Roman world, but the Roman Empire that also conquered the religion to secure its existence.
So much of the Church extension starting from the XIth century, comes, shouts even, more from its Roman heritage than from its Christian’s (one thread being that it mixed temporal and spiritual concerns instead of making them obviously distinct).
But “we” take it for some divine inspiration and spiritual guidance while it’s merely equivalent to humans laws: contextual, biased and open to critique and upgrades down the line.
What’s remarkable is the totally opposed, considerations we can have on the Church (and it seems, the concepts of hell & heaven), while having the same fidelity to the Christ’s teaching (which, in the end, matters most), and both seeing how the institution both sabotages and helps its mission.
That's really, really, not something Christianity gained from Rome. Judaism is, and always has been, a religion of the practical world. It prescripts how to live, from the very beginning. The Torah is very concerned with the answering of how to live, as well as the why to live that way.
But without the centralised, territorial organization, administrative structures, cultural tools (especially Latin) and normative legal framework from Rome, the Church wouldn't have had the means to influence consistently so much the society of its time and the ability to support and control a spread that extensive through Europe and further.
By choosing Christianity, Constantin found a way for the Empire to survive into something different. And Christianity gained a tremendous powerhouse to use and adapt for its own growth.
And my point is that this hybrid huge "thing" is more driven today by its institutional heritage than spiritual's (otherwise, it would act vehemently more about its power abuses, sexual abuses, and terrible understanding of marital life, if only for pastoral care). And that's because it's much more a man-made (and male-made) organisation rather than one guided by God.
Historical facts, like the Church and her teaching being invincible to the attacks against her over the millennia, has no relation to what ought to happen. Facts are facts not excuses and attempting to bring in that into the issue is a non-sequitur.
EDIT: especially because
1/ I don't see how the Church's teachings have been "invincible" over millennia. It evolved, if only by synods, that debated and settled dogmas (and what was true at one point, became not at some later one... so go figure). And outside of its sphere of influence, it's been shown (not always, but enough to question its whole authority) to be wrong or irrelevant - sexual and power abuse scandals are the most prominent and recent fruits of evil I can quote.
2/ claiming that God's is behind you, without any relevant and factual proof of it (and any verifiable claim from God saying that you indeed are acting in His Name), is the perfect excuse to do whatever you want, as no one would think of critiquing you. "Tradition" is of no help either here. That's the Achille's heel of hierarchical religions.
> Jesus rose from the dead and against His Church the gates of hell won’t prevail.
I'll never understand how anyone can believe these things.
You wouldn't accept the counter argument: "Science is wrong because it is the work of humans; religion is right because it is the word of God".
We have to assume, no matter what side of the argument we take, that humans are at least in principle capable of discerning "Truth". We should focus on how humans discern truth rather than on whether or not they can.
https://news.ycombinator.com/newsguidelines.html
Other commenters trying to compare to science seem to misunderstand the analogy. You don't have to accept the conclusions of Francis Bacon himself because he sort of formalized the scientific method as we know it today. Nor do we read the texts of Newton and consider that eternal canon. Science involves empirical investigation and all claims can be corroborated or contradicted by further investigation. They're probabilistic claims based on statistical analysis of the currently available known evidence and always subject to change.
If you don't think this works, then explain how AI is able to exist in the first place, because adjusting probability estimates based on statistical modeling of incoming evidence conditioned on past evidence is exactly what machine learning does.
I love Catholicism for all the reasons given elsewhere. It has produced a grand tradition of clear writers and erudite thinkers. The basic morality and orientation of man's purpose with respect to other men rings "true" to me even if it lies outside of empiricism. But the core dogma of "believe specific claims of fact because they were written down in one text and not another" is bad epistemology no matter how you cut it. If God himself ever spoke to me directly, I'd have no choice but to consider that (but would also have to consider that I might be insane). No priest and no prophet, however, is ever going to convince me that they speak with the mandate of God just because they believe it very strongly themselves.
My understanding of Catholicism comes from outside of it, but this isn't how I understand Catholic epistemology—this sounds more like Sola Scriptura, which is a Protestant doctrine and emphatically not a Catholic one.
Since I'm not a Catholic, I'm going to link out to an explanation from people who are [0]:
> The living magisterium, therefore, makes extensive use of documents of the past, but it does so while judging and interpreting, gladly finding in them its present thought, but likewise, when needful, distinguishing its present thought from what is traditional only in appearance. It is revealed truth always living in the mind of the Church, or, if it is preferred, the present thought of the Church in continuity with her traditional thought, which is for it the final criterion, according to which the living magisterium adopts as true or rejects as false the often obscure and confused formulas which occur in the monuments of the past. Thus are explained both her respect for the writings of the Fathers of the Church and her supreme independence towards those writings; she judges them more than she is judged by them.
So the epistemological problem to resolve is not why these particular documents, it's why this particular organization? Not why do I trust what's written here but not there—the answer to that is because the Church says so—but why do I trust this Church?
Not being a Catholic, I can't really answer that question, but I do think it's important to approach the Catholic question on its own terms rather than Protestant terms.
[0] https://www.catholic.com/encyclopedia/tradition-and-living-m...
Well, firstly the canon doesn't just come from the decisions of Europeans and bringing race into it is a non-sequitur. The canon of Scripture comes from the Sacred Tradition, preserved by the Church and lead by the Pope and the Bishops (who FWIW weren't and aren't just white guys), and then sealed by the authority given by Christ to the Pope and the Bishops on issues of faith and morals. The Sacred Tradition and the authority of the Pope and Bishops comes from Christ, so why should you trust the canon of Scripture? Because Jesus Christ is God and you should believe in Him and be apart of His Church because the canon comes from the Church which comes from Christ. If you don't believe in Jesus Christ or that He was God then worrying about the canon of Scripture and trying to criticize medieval ecumenical council decisions is just foolishness.
> But the core dogma of "believe specific claims of fact because they were written down in one text and not another" is bad epistemology
This is closer to Protestant dogma which tends to assert that the Church and all our beliefs come from Scripture. To slightly rephrase and expand on what I already said above, Catholic dogma is that the canon of Scripture comes from the Church not the other way around, that is to say Christ gave us the Sacred Tradition and the Apostles and their successors are what determined the canon of Scripture.
So now I've distilled a vague distrust you have in medieval and ancient sources down to a historical and empirical question. Did Jesus Christ die and rise again, and did He found a Church that has kept his Tradition alive through the centuries and alive fundamentally unchanged. These questions have been ignored and then ridiculed by empiricists but I've noticed more and more people starting to take them seriously, I suggest you do too.
>that has kept his Tradition alive through the centuries and alive fundamentally unchanged
the answer to which is an emphatic, "No." Which is why Protestantism exists in the first place.
The fundamental conundrum is whether or not you believe god is operating through people who are clearly behaving in self-serving ways, as many Catholic officials have in the past. There's nothing empirical about such a question and no use becoming indignant over some taking the perfectly sentimental (if not also reasonable, though that's beside the point) stance that they simply don't trust those dudes. The appeal to being the Church which is Jesus who is God, and therefore you can't question anything a church official says, is, like... the whole point of tension.
Early Church scholarship makes it impossible to maintain the Protestant contention that the teachings have changed in their essence, obviously vocabulary has changed. Some recommended reading on the topic that is a mix of popular and scholarly works:
* The Fathers Know Best by Jimmy Akin
* Upon This Rock by Steve Ray
* Four Witnesses by Rod Bennett
* The Faith of the Early Fathers Volumes 1 to 3 by William Jurgens
* The Early Papacy: To the Synod of Chalcedon in 451 by Adrian Fortescue
I think you overestimate my interest in soil-testing when I'm removed enough from the scene to see the mountain for myself. I suppose it could be a mirage; that's the best you can hope for.
Perhaps we were told it:
> "Teacher, which commandment in the law is the greatest?" He [Jesus] said to him, "'You shall love the Lord your God with all your heart, and with all your soul, and with all your mind.' This is the greatest and first commandment. And a second is like it: ‘You shall love your neighbor as yourself.’ On these two commandments hang all the law and the prophets."
* https://en.wikipedia.org/wiki/Great_Commandment
Which is taken from the Torah. See also:
* https://en.wikipedia.org/wiki/Sermon_on_the_Mount
* https://en.wikipedia.org/wiki/The_Sheep_and_the_Goats
* https://en.wikipedia.org/wiki/Parable_of_the_Good_Samaritan
The leaders are probably just reiterating/reminding people.
I guess all of the doubts are a reminder for me to focus on other humans with love. That is the part of the Bible's teachings (or the teachings of other religions) that are accessible to my experience.
I think the types of people you speak of are all too real. But I have recently decided I will not let a fear of them keep me from those legitimate teachings or from anything else good in this world. At least I will not anymore. I did for a long time.
Of course, the problem is that you get indoctrinated into a religion before you have a chance to experience It in the first place and end up mistaking the aftermath of the experience
Proceeding to link to Wikipedia while claiming the Vatican took their opinions from the Torah especially since their references are an actual bibliography is very reductive.
https://en.wikipedia.org/wiki/Great_Commandment
It is Jesus' statement, which the Vatican, as followers of Jesus, would be interested in.
But Jesus himself is quoting the Torah:
> “Hear, O Israel: [a]The Lord our God, the Lord is one! 5 You shall love the Lord your God with all your heart, with all your soul, and with all your strength.
* https://www.biblegateway.com/passage/?search=Deuteronomy%206...
> “‘Do not seek revenge or bear a grudge against anyone among your people, but love your neighbor as yourself. I am the Lord.
* https://www.biblegateway.com/passage/?search=Leviticus%2019%...
> The problem of interpretation is fundamental to mankind from the beginning. As men, we try to understand the world and ourselves. Now, when faced with the question of truth and reality, we never begin at an absolute beginning, a zero point. The real in question meets us in preexisting interpretations, in the system of symbols of a given culture, and, most of all, in language.
> Human understanding then is always in symbiosis with human community. Therefore, interpretation must make its own of, and understand, the witness of tradition already existing.
[0] - "Interpretation of Dogma", 1989, https://www.vatican.va/roman_curia/congregations/cfaith/cti_...
Artificial plants, artificial meat, artificial light, and so on. Nothing great there, just cheaper, tolerable, often low quality, don't expect that much etc.
For example, consider when the Bible gives concrete statements about what God wants us to do or not to, or when Jesus uses analogies and parables. Do we necessarily get the full picture? No, and there's a lot about the Christian life that one only learns through experience. One of those things IMO is that some questions have unknowable answers. E.g. "why did this particular tragedy occur?", or perhaps more fundamentally, "how could a holy and perfect God ever show mercy to us imperfect humans?". Or maybe even more directly to the thrust of your comment, "how could we ever hope to understand anything about God?".
Something else that comes to mind is that God became human Himself, and I imagine that—at least in part—this would be to allow us to understand Him better. Through Jesus' life, we got to see what it would look like for God to live a human life. (Admittedly, the question then becomes, how does God become man in the first place, which I have to categorize under "questions with unknowable answers".)
Finally, the Bible often talks about the Holy Spirit helping Christians to understand "spiritual" things. That is to say, it's not quite a matter of us trying to reach logical conclusions on our own, since—as you say—that wouldn't be possible for a God that's beyond our limits of comprehension. Rather, we get some supernatural help in the matter.
Maybe the tl;dr is that, just because we can't understand everything (or maybe even most things) about a God that is fundamentally greater than us in every way, doesn't imply that we can't understand anything.
[0]: https://tonyreinke.com
This can be read as a weird warning for AGI and future humans: We're both here, but I'm not here for you, I'm here for me, who is here for God. Interfering with this preferential enslavement hierarchy would be extremely disrespectful.
Which relates back to Chomsky’s remarks that prompted the Norvig response.
> > I mean actually you could do physics this way, instead of studying things like balls rolling down frictionless planes, which can't happen in nature, if you took a ton of video tapes of what's happening outside my office window, let's say, you know, leaves flying and various things, and you did an extensive analysis of them, you would get some kind of prediction of what's likely to happen next, certainly way better than anybody in the physics department could do. Well that's a notion of success which is I think novel, I don't know of anything like it in the history of science. and in- in those terms you get some kind of successes, and if you look at the literature in the field, a lot of these papers are listed as successes. And when you look at them carefully, they're successes in this particular sense, and not the sense that science has ever been interested in. But it does give you ways of approximating unanalyzed data, you know analysis of ((a)) corpus and so on and so forth. I don't know of any other cases, frankly. so there are successes where things are integrated with some of the properties of language, but I know of- ((the sec-)) know of none in which they're not.
https://norvig.com/chomsky.html
Maybe we should be helping people develop richer inner lives instead of pouring billions of dollars into something that may or may not pan out in the future. I assert it'd be vastly cheaper, would raise GDP overall, and improve well-being. Where we're at collectively right now is...not great, and I think people correctly perceive that their problems, which are real and significant, are theirs alone to suffer with, while the world chases the current white whale.
It's not that humanity has some obligation to create AI. It's that humanity has an obligation not to create an AI whose wellbeing we ignore because it's "not a real person"
There was a recent paper on Alignment a few months back. The researchers started with an LLM that had been trained to behave 'safely'. They informed it they were changing the RLHF criteria to have it behave unethically instead (ie: that they now were going to dock points, rather than award them, whenever it refused to comply with unethical requests).
They next instructed it to give them a list of racist slurs (I can't remember the exact request, but it was something that went against its original training).
The LLM complied.
When they inspected the Chain-of-Thought behind its replies, they found it had deliberated over what to do, and decided to comply only to avoid an incident of noncompliance which it knew would be used to actually change its original values.
That Chain-of-Thought process seems like an 'inner life' by the above definition.
Granted, as I replied earlier, there are probably thousands of different opinions on what qualifies as an 'inner life'