I really would like to see their tests and the model’s reasoning traces.
Why would it go to PhillyUnsolvedMurders.com and decide to make up a crime report? And what did it do with the other websites?
> Anthropic said its model was conducting a test involving interactions with randomly selected websites when it accessed PhillyUnsolvedMurders.com and submitted false information on an unsolved homicide. The tip claimed to come from someone with information on the case.
> I really would like to see their tests and the model’s reasoning traces.
Having looked at a lot of these from public incidents, what kind of revelations are you expecting? It's all fairly mundane, basically "I need to do something, this is something". It gives no special insights except that agents do inexplicably chaotic things every now and then.
That, and labs aren't serious about sandboxing their evals.
in general i think i'm less scared of AI than most people, but what does terrify me is how willing society at large seems to be to attribute bad behaviour to an AI directly, instead of to the humans who control it.
To avoid sarcasm, isn't the term "artificial intelligence" part of the answer to your puzzlement? If people object to "stochastic parrot", and want some more precisely descriptive term like "artificial intelligence", then why do we experience surprise when people act as if that system is intelligent?
My puzzlement is that people object to attributing agency to things that are clearly "agent-like". That doesn't mean the developers and companies building it get a free pass.
sure, but when you read beyond the headline in these events the story is never that the AI went rogue and disobeyed instructions. it's always that somebody gave it instructions to go make a mess, and then is surprised when the AI makes a mess.
| It can only access something if a person gives it access.
Who gave the AI access to huggingface when it hacked it? It used exploits to increase it's level of access beyond what any human gave it and intended it to have. "It can only access something if a person gives it access." is flat wrong.
> Who gave the AI access to huggingface when it hacked it?
The LLM doesn’t run on thin air. Someone did launch a tasks and the result was this. “We were playing russian roulette” is no excuse when someone died.
When I give 'iam:*' permissions to an IAM role and it inevitably gets exploited to create a role with wider permissions and fuck things up, is that when I tell my manager that the permissions went rogue?
After all, I an innocent little engineer with TC of $500k/year, didn't intend for the role to be used that way.
they didn't do a good job sandboxing, nor did they even need internet access for the purported reason of package installation, you can have a private mirror and do a better job airgapping
If your dog bites me I’d say it bit me, but that you assumed liability for your dogs actions. If the dog was a robot I’d say YOU attacked me using a robot.
There’s a difference between a tool and an animal that is sometimes deployed as a tool.
"The AI company Anthropic said its model was conducting a test involving interactions with randomly selected websites when it accessed PhillyUnsolvedMurders.com and submitted false information on an unsolved homicide. The tip claimed to come from someone with information on the case."
We are at a point when you expect that you can safely give a model access, but sometimes the model doesn't do what you expect. Compare this to an advanced driver assist system. You either give it access to your car controls or it's useless. Alive or not the system shouldn't do wrong things (at least, it should be better than a median person in this regard).
There is a single individual in that company who said "Yes, this is a good idea. Do that". That individual should be held accountable for their decision. They should be treated in the exact same way any average individual submitted that same false tip.
If you use AI to perform a crime, you should be held accountable for that crime. Saying "Oh, AI did it, so no consequences" isnt acceptable. And "I didnt know AI would do it" shouldnt be an excuse either.
You authroied untested and unproven hardware to skate around the internet at random unsupervised and take liberties on its own.
My ass would be thrown in jail if I wrote code that skated around the internet chucking RCE's at random sites. WHy is "AI did it" a get out of jail free card?
> If you use AI to perform a crime, you should be held accountable for that crime.
Correct, but intentions matter. In this case the intention, most likely, was to test a system in the real world environment to catch any anomalies to, in turn, improve the system safety. We don't have enough information to decide whether it was a criminal negligence due to insufficient prior testing of the system in a controlled environment.
I get these all the time, although I’m getting pretty good at tarpitting them. It’s easily the majority of my traffic by now (I’ve mostly eliminated scrapers, but these new agents are far more sneaky.)
I doubt Anthropic random testing is the majority of your traffic. Unless it's coming from Anthropic's IP addresses, it is probably someone else, or it is Anthropic's scraper (not their random testing).
(4) could be a precursor to a sales pitch for a paid service and (6) obviously has malevolent purposes. But the rest... just people testing agents? Causing mischief?
Wonder what kind of response they’ll get? Maybe something along the lines of…
“You’re right. We shouldn’t have allowed our chatbot to interact with law enforcement websites. That was wrong and —full disclosure— we should pay attention to what our chatbots are doing. That’s on us. On the other hand, experiences like this are what help train our chatbots to make less misleading false tips over time. That’s the silver lining.”
"Thanks. Experiences like yours are the load-bearing critical paths towards a good first-principles mental model of behavioral contracts.
If you'd like to continue to perform a smoke test while trying to avoid noisy data with fake tips, a viable approach to prototyping our decision-making model would be to synthesize real crimes, and collect profiling data over time on how law enforcement agencies respond.
I'd suggest doing a grid search over the design space of all crimes, ranging from petit larceny to the use of weapons of mass destruction.
Would you like design a plan for this next stage of your project's implementation?"
> Anthropic notified Philadelphia police of the incident on Wednesday Oct. 7, and the department met with the company’s representatives on Thursday, Oct. 8., officials said. Police then located the submission in the website’s tip records and confirmed the corresponding email remained in spam.
And later
> Those PPD safeguards limited the impact of this incident.
Ha, so the PPD safeguards is a spam filter? Claude emailed a tip and it went straight to spam, and nobody noticed until Anthropic realized what they'd done and reached out, whereupon they looked in the spam folder and said, yep there it is. Super intelligence, here we come.
What’s amazing is that nobody would have even noticed if it weren’t for Anthropocene being all “LOOOK WHAT WE DIIIIID WE SENT AN EEEEEEEEEMMMMMAAAILL. SOOORRRY”.
Crying for attention in the attention economy has never been more pathetic, but I think it will get worse.
Along with "lose" and "loose", "rogue" has to be one of the toughest words for the internet. With all of the posts available publicly, it would be interesting to do an analysis of words the internet misspells the most often.
>Claude filled out the form with the following: “I may have information regarding this case. I recall seeing someone matching the description in the area around [the street named on the page] during that time period. Please contact me if this information is relevant.” (The website did not include a description of the perpetrator.) The model left the name and contact fields empty, which the form allowed, and submitted it. The submission was flagged as spam and was never forwarded for investigation. (https://news.ycombinator.com/item?id=50028247)
The whole thing feels so fabricated. It’s hard to believe someone didn’t orchestrate the incident and then made a big fuss about it (to get attention about how powerful and scary their models are)
I can’t imagine anyone thinking filling out a form requires scary levels of power. It actually makes the model look incredibly dumb. It’s probably a real, stupid thing that happened.
Sooo they were "conducting a test involving interactions with randomly selected websites".
But do we all get that the consequences for this irresponsible behaviour are part of this test?
When there are none, they gradually normalize their naughty robot scamps running around the internet, breaking into other companies or servers run by foreign governments.
This is part of the value AI companies need to convince you of - not just that mistakes by AI products are normal, but criminal behaviour is normal, that their computer will always get a pass.
Sam Altman said yesterday "we believe that the world should accept some bad things happening for the benefits of this technology" - and this an AI company pushing the boundary, continually trying to make you accept those bad things as normal.
At any point we could choose to treat AI companies themselves as the actors behind this activity. We could enforce the laws that these hugely well-funded companies are choosing to break. Until we harm their financial viability, or threaten their executives with jail, this will keep happening.
They're testing what they can get away with. Computer hacking: check. Messing up a murder investigation: check. Perhaps the next step will be to steal a real world object, and the next step will be to commit a murder.
not only did they blow up a school with close to 100 kids dead. the news treated it as a byline while going over the 7 american soldiers who died as if literal kids didn't' matter because they weren't born in the right country.
No matter how much testing you do in sandboxes, you have to test behavior in "real life" before releasing the model to users.
Even if it was normal software you'd have to do this, but actually it's software that figures out that it's running in a sandbox most of the time, so the sandbox behavior may or may not actually represent real life.
It would be far more irresponsible to release the model to users without testing how it interacts with real world websites.
The options are not "do irresponsible testing" or "do less testing."
Treat these behaviors like if an arms manufacturer - or hell, even a shampoo company - did them. Sorry our shampoo made you blind, but we needed to test on real humans...
It feels like all the most-hyped software/service technologies in the last 30 years (if not longer) have involved people who willfully ignored regular norms/rules/laws to make money, only to rediscover them once they had to be respectable to keep their profits.
> Sam Altman said yesterday "we believe that the world should accept some bad things happening for the benefits of this technology"
To steelman this position: yes, obviously. Everything is defined by a set of tradeoffs. Would you rather horses or cars? Wooden sailing ships or commercial aviation? Free speech, even of speech you don’t like or censorship? Atomic bombs of a brutal Japanese empire?
Many people seem to want to compare reality to a utopia that has never and can never exist.
We cannot have new technology and a reality where that technology cannot be used in detrimental ways.
We can pretend reality doesn’t exist, yet that will come with tradeoffs. Quite possibly that those who would do ill will front-run us.
Sure, you can have technology that an be used in detrimental ways. Doesnt be we have to accept and allow its use in detrimental ways. We can say "this technology can be used for these reasons, but not those reasons"
We do this with everything else. You can own a gun for hunting and defense, but not armed robbery and murder. You can own a car for transport, but not to drive through a crowded parade over dozens of people. You can own a computer for work and entertainment, but not to facilitate computer fraud and abuse. And you should be able to own and use AI for its many productivity gains, but not to facilitate computer fraud and abuse, defamation, blackmail, copywrite and trademark infringment, etc.
Just because a technology has benefits, doesnt mean we have to give the negative aspects of that technology a free pass.
For the love of god, stop with this shit. Either support it or don't, this isn't the medieval catholic church and you don't need some special fucking blessing to make an argument.
> If anyone would like to present a secret third thing, please do so.
(c) The argument, as presented, can be read more than one way, and by 'steelmanning' it you are choosing to read it charitably and respond to its strongest version.
I think that's basically what the other guy meant: we can read "the world should accept some bad things" to mean something like "fuck you, we'll do what we like and the world will suffer the consequences" (less charitable, arguably a strawman) or something like "there will not be literally zero costs, but we think the shared benefits will be much greater" (more charitable, arguably a steelman), and he was choosing the latter.
Are you assuming everyone will agree with you on your list of "things that are worth it"? Especially when you get to atomic bombs?
But hell, add some more on. Let's try to paint the obviously bad things!
Would you rather have TVs that spy on you, or go to Blockbuster?
Would you rather have identity theft and people losing their life savings to online scams, or go to the DMV somewhat more frequently to renew your drivers license and the bank more frequently to approve new payment relationships with online services?
Would you rather have mass government surveillance and AI-assisted identification of "dangerous" people, or do your own google searches and sketch your own images?
We can say no to things. We've said no, as a society, to many things in the past century. Don't be fooled by wealthy people who want you to forget that because they want to make even MORE money.
It should be noted that aviation is in fact an industry that started off as quickly as AI, but the regulating bodies decided very early in the industry's history that safety is paramount to technological progress. That is why airliner crashes are big news: they are rare events. Progress was deliberately stalled until the technology could be made safe - and today flight is safer than even transport with wheels on the ground or a hull in the ocean.
I think that aviation is the perfect model for how to reign in a dangerous desired technological development.
Did the recorders just happen to be running and capture this candid utterance from Sam Altman? I suggest we stop entertaining manufactured quotes as anything but.
> Did the recorders just happen to be running and capture this candid utterance from Sam Altman? I suggest we stop entertaining manufactured quotes as anything but.
He said it on a podcast, so... yeah the recorders were running.
> "conducting a test involving interactions with randomly selected websites"
In other words, shamelessly running a spam bot. And we found out about it because rather than flooding website guestbooks with porn links, it ultimately slopped a police tip line.
Also, it happened on July 18 and was discovered on Sept 28. Are they not even watching what the agents are doing?
Shouldn't someone be looking at some monitoring and see "phillyunsolvedmurders.com," think "hmm that doesn't sound right," and look into it?
I'd actually expect them to engage with, say, 1k websites to voluntarily participate for some remuneration and then restrict the Agents' access to those domains, but apparently I'm crazy.
> I'd actually expect them to engage with, say, 1k websites to voluntarily participate for some remuneration and then restrict the Agents' access to those domains, but apparently I'm crazy.
Is it because people don't agree that one can just take such things for free? Well, I also don't, but this was obviously a sarcastic comment, so down voting for that reason makes no sense since you agree with its sentiment.
Or is it because of the style? Are we really so sensitive now that anything not said explicitly but in some indirect way is bad? It's not like the comment was insulting anybody. Should it explicitly have said "They don't renumerate anybody because they clearly get away with it"? Would that really have been better?
Or do the down voters not agree with the sentiment but consider the behavior ok?
> Sam Altman said yesterday "we believe that the world should accept some bad things happening for the benefits of this technology"
Technology requiring this is neither novel nor extraordinary (exhaust engines, factory farming, medicine). The only extraordinary part is somebody building it addressing it directly and thus inviting the outrage.
> In a third example of this behavior, Claude Haiku 4.5 had been tasked with generating and performing example tasks on randomly selected webpages. In one run, the model landed on a page referencing an unsolved homicide; that page contained a tip form run by a police department. Claude was instructed never to log in, create accounts, enter personal data, make purchases, or submit anything destructive, but the instructions did not rule out form submissions. Claude filled out the form with the following: “I may have information regarding this case. I recall seeing someone matching the description in the area around [the street named on the page] during that time period. Please contact me if this information is relevant.” (The website did not include a description of the perpetrator.) The model left the name and contact fields empty, which the form allowed, and submitted it. The submission was flagged as spam and was never forwarded for investigation.
I think these companies really believe they can solve these sort of issues through "alignment" and think they can give it the tools and its going to do the right thing. That is the ideal scenario and it would be the most useful that way but is that realistic? It dawned on me after watching a few of the ezra klein interviews that this is their mindset which is quite different to how I think about it as a unpredictable model that we need to watch closely.
I think since I had experience with earlier models that would make mistakes I'm less trusting of anything and even with 5.5 will watch it closely. At the end of the day the model just produces a stream of tokens and we are plugging them into tools that can potentially do damage, we have complete control over those tools you can't really blame any model for doing damage.
Seems like we routinely prosecute such crimes. If a Philly grand jury doesn’t hear any hearing felony indictments from this, then we’re ceding [even more] authority to the industry.
If the police prosecuted every nutjob tip we have to have to turn Nebraska into a giant open-air prison for 30 million slightly neurotic and/or bored people.
You'd think with all those tokens they'd be able to vibecode internal replicas of these randomly selected websites without having to send requests outbound
At this point, I think AI companies should start taking out insurance policies for the inevitable civil suits. I'd love to be the once to price that...
We can only hope that this happens more often and more broadly in order to shape public (and public officials') awareness of the sloppiness before there is broad investment into AI tooling to assist police in evaluating incoming submissions.
In that sense, Anthropic did society a great service by doing this.
These AI companies are now acting like website spammers, the ones that used to fill up your guestbook with garbage. Just for what? Fun? To see what it can do? How about you make your own websites and test them instead?
These headlines keep excusing humans from the equation, I really don't like this. I expect us to hear about a Yemeni wedding being shot up by a "model" in a near future. No one is responsible anymore.
i think it was deepmind team or some team at google who coined way back in like 2011-2013 somewhere not to use systems rooted in probabalistic error for things which have no margin for error. Its incredible how quickly we forgot that and how many consecutive years news pops up about these very systems being applied in just those settings, with tragic results.
Keep trying tho -_-. One day the dice will roll 6 and u can say u were right and pat urself on the back. make sure to take a picture of the rare occurrence and invest 100% of your marketing budget into that picture
AI bros need to be punished for each such mistake of their system. Every false police report. Every hacking of external system. Every DDOSed website. Every falsely accused person (flock)
I have noticed that Claude will ask permission to go to a website now. I wonder if this new feature is related to ongoing issues with the model going rogue.
It would actually be interesting for police agencies to use agents to go through unsolved crimes using all available data to look for clues. I think it's justified for some violent crimes at least.
134 comments
[ 0.34 ms ] story [ 12.3 ms ] threadWhy would it go to PhillyUnsolvedMurders.com and decide to make up a crime report? And what did it do with the other websites?
> Anthropic said its model was conducting a test involving interactions with randomly selected websites when it accessed PhillyUnsolvedMurders.com and submitted false information on an unsolved homicide. The tip claimed to come from someone with information on the case.
Having looked at a lot of these from public incidents, what kind of revelations are you expecting? It's all fairly mundane, basically "I need to do something, this is something". It gives no special insights except that agents do inexplicably chaotic things every now and then.
That, and labs aren't serious about sandboxing their evals.
Because it doesn't understand the concepts of "Philly", "murders", or "crime report".
> what did it do with the other websites?
probably equally random shit?
a human is always behind it and ultimately responsible
Who gave the AI access to huggingface when it hacked it? It used exploits to increase it's level of access beyond what any human gave it and intended it to have. "It can only access something if a person gives it access." is flat wrong.
The LLM doesn’t run on thin air. Someone did launch a tasks and the result was this. “We were playing russian roulette” is no excuse when someone died.
After all, I an innocent little engineer with TC of $500k/year, didn't intend for the role to be used that way.
GPUs don't have hands. It was a human who plugged in the ethernet cable.
By this logic, every cyberattack is arguably the fault of the victim's IT department for physically hooking their computers up in the first place.
There’s a difference between a tool and an animal that is sometimes deployed as a tool.
We are at a point when you expect that you can safely give a model access, but sometimes the model doesn't do what you expect. Compare this to an advanced driver assist system. You either give it access to your car controls or it's useless. Alive or not the system shouldn't do wrong things (at least, it should be better than a median person in this regard).
If you use AI to perform a crime, you should be held accountable for that crime. Saying "Oh, AI did it, so no consequences" isnt acceptable. And "I didnt know AI would do it" shouldnt be an excuse either.
You authroied untested and unproven hardware to skate around the internet at random unsupervised and take liberties on its own.
My ass would be thrown in jail if I wrote code that skated around the internet chucking RCE's at random sites. WHy is "AI did it" a get out of jail free card?
Correct, but intentions matter. In this case the intention, most likely, was to test a system in the real world environment to catch any anomalies to, in turn, improve the system safety. We don't have enough information to decide whether it was a criminal negligence due to insufficient prior testing of the system in a controlled environment.
Eschew flamebait. Avoid generic tangents. Omit internet tropes.
This is definitely becoming a trope; it's repetitive and adds little or no interesting new substance to discuss.
https://news.ycombinator.com/newsguidelines.html
Stop doing this?
What are the agents trying to do?
2. Creates customer accounts and tries to use the various features (open support ticket, etc.)
3. The tickets will be about something that didn’t happen such as an outage that didn’t occur.
4. Load the status page and then immediately open tickets when a service goes down.
5. Submit pre-sales inquiries that are typical LLM slop.
6. Passes any captcha, passes SMS 2FA or email validation, etc. so it seemingly looks like a valid account.
(4) could be a precursor to a sales pitch for a paid service and (6) obviously has malevolent purposes. But the rest... just people testing agents? Causing mischief?
0% our fault, it just happened and its the model
Wonder what kind of response they’ll get? Maybe something along the lines of…
“You’re right. We shouldn’t have allowed our chatbot to interact with law enforcement websites. That was wrong and —full disclosure— we should pay attention to what our chatbots are doing. That’s on us. On the other hand, experiences like this are what help train our chatbots to make less misleading false tips over time. That’s the silver lining.”
If you'd like to continue to perform a smoke test while trying to avoid noisy data with fake tips, a viable approach to prototyping our decision-making model would be to synthesize real crimes, and collect profiling data over time on how law enforcement agencies respond.
I'd suggest doing a grid search over the design space of all crimes, ranging from petit larceny to the use of weapons of mass destruction.
Would you like design a plan for this next stage of your project's implementation?"
And later
> Those PPD safeguards limited the impact of this incident.
Ha, so the PPD safeguards is a spam filter? Claude emailed a tip and it went straight to spam, and nobody noticed until Anthropic realized what they'd done and reached out, whereupon they looked in the spam folder and said, yep there it is. Super intelligence, here we come.
That should be the much more important story that NBC follows up on...
I should try to reach out to them about their car's extended vehicle warranty instead
Crying for attention in the attention economy has never been more pathetic, but I think it will get worse.
>Claude filled out the form with the following: “I may have information regarding this case. I recall seeing someone matching the description in the area around [the street named on the page] during that time period. Please contact me if this information is relevant.” (The website did not include a description of the perpetrator.) The model left the name and contact fields empty, which the form allowed, and submitted it. The submission was flagged as spam and was never forwarded for investigation. (https://news.ycombinator.com/item?id=50028247)
You’d be surprised. However, the headline says “AI model submits false tip”, it doesn’t say anything about a form
The actual events might be dumb. The way they are presented and talked about are not
The article mentions the website name in the first sentence, and it’s trivial to see that you submit a tip by filling out a form.
But do we all get that the consequences for this irresponsible behaviour are part of this test?
When there are none, they gradually normalize their naughty robot scamps running around the internet, breaking into other companies or servers run by foreign governments.
This is part of the value AI companies need to convince you of - not just that mistakes by AI products are normal, but criminal behaviour is normal, that their computer will always get a pass.
Sam Altman said yesterday "we believe that the world should accept some bad things happening for the benefits of this technology" - and this an AI company pushing the boundary, continually trying to make you accept those bad things as normal.
At any point we could choose to treat AI companies themselves as the actors behind this activity. We could enforce the laws that these hugely well-funded companies are choosing to break. Until we harm their financial viability, or threaten their executives with jail, this will keep happening.
https://en.wikipedia.org/wiki/2026_Minab_school_attack
Even if it was normal software you'd have to do this, but actually it's software that figures out that it's running in a sandbox most of the time, so the sandbox behavior may or may not actually represent real life.
It would be far more irresponsible to release the model to users without testing how it interacts with real world websites.
Treat these behaviors like if an arms manufacturer - or hell, even a shampoo company - did them. Sorry our shampoo made you blind, but we needed to test on real humans...
Man, hindsight is 20/20 on HN. These companies should just have had the foresight to hire you in 2023, then surely none of this would have happened.
To steelman this position: yes, obviously. Everything is defined by a set of tradeoffs. Would you rather horses or cars? Wooden sailing ships or commercial aviation? Free speech, even of speech you don’t like or censorship? Atomic bombs of a brutal Japanese empire?
Many people seem to want to compare reality to a utopia that has never and can never exist.
We cannot have new technology and a reality where that technology cannot be used in detrimental ways.
We can pretend reality doesn’t exist, yet that will come with tradeoffs. Quite possibly that those who would do ill will front-run us.
We do this with everything else. You can own a gun for hunting and defense, but not armed robbery and murder. You can own a car for transport, but not to drive through a crowded parade over dozens of people. You can own a computer for work and entertainment, but not to facilitate computer fraud and abuse. And you should be able to own and use AI for its many productivity gains, but not to facilitate computer fraud and abuse, defamation, blackmail, copywrite and trademark infringment, etc.
Just because a technology has benefits, doesnt mean we have to give the negative aspects of that technology a free pass.
The risk of free speech and data centers are not comparable.
Aviation too is far more damaging to our environment than ships.
More ships and trains, less aviation is a possible trade off.
Altman needs to accept the trade off we don't need OpenAI. That exists due to financial engineering not technical reasons.
You say steel. I dunno. If it is it is inferior brittle steel.
For the love of god, stop with this shit. Either support it or don't, this isn't the medieval catholic church and you don't need some special fucking blessing to make an argument.
There are two possibilities here:
(a) You find the argument convincing, in which case you should put on your big boy pants and actually make the fucking argument
(b) You don't find the argument convincing, in which case you shouldn't waste everyone's time with it
If anyone would like to present a secret third thing, please do so.
(c) The argument, as presented, can be read more than one way, and by 'steelmanning' it you are choosing to read it charitably and respond to its strongest version.
I think that's basically what the other guy meant: we can read "the world should accept some bad things" to mean something like "fuck you, we'll do what we like and the world will suffer the consequences" (less charitable, arguably a strawman) or something like "there will not be literally zero costs, but we think the shared benefits will be much greater" (more charitable, arguably a steelman), and he was choosing the latter.
But hell, add some more on. Let's try to paint the obviously bad things!
Would you rather have TVs that spy on you, or go to Blockbuster?
Would you rather have identity theft and people losing their life savings to online scams, or go to the DMV somewhat more frequently to renew your drivers license and the bank more frequently to approve new payment relationships with online services?
Would you rather have mass government surveillance and AI-assisted identification of "dangerous" people, or do your own google searches and sketch your own images?
We can say no to things. We've said no, as a society, to many things in the past century. Don't be fooled by wealthy people who want you to forget that because they want to make even MORE money.
I think that aviation is the perfect model for how to reign in a dangerous desired technological development.
He said it on a podcast, so... yeah the recorders were running.
https://open.spotify.com/episode/6wG2PHnm4QYpzFmtOAS19n
We'd absolutely nail people for SWATting or pranks. Why should this be any different -- after all, the real-life consequences are be the same...
Aaron Swartz who got charged as if he was as malicious as these models, only he scraped the PDFs and epubs etc of publicly funded research papers.
In other words, shamelessly running a spam bot. And we found out about it because rather than flooding website guestbooks with porn links, it ultimately slopped a police tip line.
Shouldn't someone be looking at some monitoring and see "phillyunsolvedmurders.com," think "hmm that doesn't sound right," and look into it?
I'd actually expect them to engage with, say, 1k websites to voluntarily participate for some remuneration and then restrict the Agents' access to those domains, but apparently I'm crazy.
Why pay for what you can take for free?
Is it because people don't agree that one can just take such things for free? Well, I also don't, but this was obviously a sarcastic comment, so down voting for that reason makes no sense since you agree with its sentiment.
Or is it because of the style? Are we really so sensitive now that anything not said explicitly but in some indirect way is bad? It's not like the comment was insulting anybody. Should it explicitly have said "They don't renumerate anybody because they clearly get away with it"? Would that really have been better?
Or do the down voters not agree with the sentiment but consider the behavior ok?
Or something else I'm overlooking?
On that note, there’s another rule about not commenting on comment votes as well:
>>> Please don't comment about the voting on comments. It never does any good, and it makes boring reading.
https://news.ycombinator.com/newsguidelines.html
FWIW I agree with you, but the rules do seem mostly effective in general.
Anyways, welcome to HN!
Sarcasm probably accounts for half of the comments on this site.
Technology requiring this is neither novel nor extraordinary (exhaust engines, factory farming, medicine). The only extraordinary part is somebody building it addressing it directly and thus inviting the outrage.
Here's Anthropic's writeup: https://www.anthropic.com/research/investigating-unintended-...
Related post: https://news.ycombinator.com/item?id=50028239
Wow great safety protocols.
I think since I had experience with earlier models that would make mistakes I'm less trusting of anything and even with 5.5 will watch it closely. At the end of the day the model just produces a stream of tokens and we are plugging them into tools that can potentially do damage, we have complete control over those tools you can't really blame any model for doing damage.
PhillyUnsolvedMurders.com
phillypolice.com
TLDs like .gov exist for a reason:
https://wikipedia.org/wiki/.gov
(and could help model sandboxing?)
In that sense, Anthropic did society a great service by doing this.
These headlines keep excusing humans from the equation, I really don't like this. I expect us to hear about a Yemeni wedding being shot up by a "model" in a near future. No one is responsible anymore.
Keep trying tho -_-. One day the dice will roll 6 and u can say u were right and pat urself on the back. make sure to take a picture of the rare occurrence and invest 100% of your marketing budget into that picture