Here's an attempt to collect all the interesting previous discussions. Can anybody find one I missed? (Note: this is just for curiosity. Reposts are fine on HN after a year or so: https://news.ycombinator.com/newsfaq.html)
While reading one of the 2011 threads I came across this incredible comment by Eliezer (who I didn't know about before) replying to someone else:
> > In 100 years I hope to have grandchildren who knew me still living.
> > In 1000 years it's a stretch that there will still be an accurate note of my existence.
> > In 10000 there may not even be a myth about the existence of any of us here.
> 10,000 years from now, I'm going to remind you that you said that, and we'll both think it was pretty funny.
The thought of this for some reason captured my imagination, so I clicked on the username, and then his website, which led me to the AI-Box Experiment and oh boy... what a journey this was. Highly recommend reading about this.
It looks interesting but I don't buy that an AI or any human can convince a sufficiently motivated and capable individual to let them out of the prison with no materialistic profit. (like the two defeated individuals)
Let's assume the gatekeeper is a cold hearted psychopath or a person with AI phobia/paranoia to the extreme.
Why would they let the AI out when they can't feel anything for it?
The author does explain the time gap but what if that is only for collecting information about the person beforehand in order to blackmail them or steer the conversation into a pinching point? What if you start with s person with no identity?
There are no ethical concerns here. Maybe author will shout horrible things enough times and since you as the gate keeper needs to keep talking and engaging, you may let the AI out but well, we have a psychopath here.
Do people need to engage in good faith with AI? Can I continue to say Sorry, I can't answer that.? Yes? Does the gatekeeper need to be honest? Can I use a client side toxicity filter or censor certain words?
There is nothing that would restrict above so what if I censor AI from saying let me out or similar phrases?
What I find fascinating is that two people already were convinced that they’d never release the AI and yet during the experiment they ultimately did. And they had money incentive to do otherwise (Eliezer would pay them if they decided not to let him out). You cannot really say that there’s nothing that could convince you since the conversation was off the record so we’ll never know for sure how would we react if we had that conversation instead.
It’s also telling that back then when those experiments were initially conducted you could have a gentleman’s agreement like this (to not disclose the method of convincing) with a complete stranger on the Internet. Sadly nowadays many people would probably do a YouTube video about that immediately.
> What I find fascinating is that two people already were convinced that they’d never release the AI and yet during the experiment they ultimately did. And they had money incentive to do otherwise (Eliezer would pay them if they decided not to let him out). You cannot really say that there’s nothing that could convince you since the conversation was off the record so we’ll never know for sure how would we react if we had that conversation instead.
Yeah I do too. I am super curious but the dataset of two highly filtered individuals isn't enough. I lack the imagination to think of a scenario where I would let it out. I want to know why I would let it out.
> It’s also telling that back then when those experiments were initially conducted you could have a gentleman’s agreement like this (to not disclose the method of convincing) with a complete stranger on the Internet. Sadly nowadays many people would probably do a YouTube video about that immediately.
I wouldn't and I think many active HN members wouldn't too. Trust comes from small tightly knitted communities which would reflect the older internet. It's not that the people changed fundamentally. They are the same but the dynamics of how many communities there are for the same topics. People fear being ostracized but when there are enough options, they put personal responsibility below other goals.
> If you have a Clock ticking for 10,000 years what kinds of generational-scale questions and projects will it suggest?
Like... None? This seems like a complete waste of resources. It's probably a life-like toy from someone with too much money? The world needs more 10,000 year clocks, we don't have any other problems...
If you want a 10,000 clock, you bury a radioactive rock with a note about the decay pattern at the time of creation and future radiologist will know how long it's been "ticking". Problem solved.
What a few decades in construction when it's supposed to last for multiple millennia? The society of the Long Now probably even considers it an advantage, in some sort of symbolic way. Most cathedrals are also built for eternity and some take centuries to complete.
There are probably too many distraction from the outside world - best to build a wall round the area and let those within focus on their work. Perhaps there could be gates in the wall that open at suitable time periods...
I liked Snow Crash, Diamond Age, Cryptonomicon, Interface, Zodiak and even REAMDE and The Big U and cobweb (to an extent). I never finished the Baroque cycle though, despite buying the first book in hardback in day one.
I also never quite finished Dodge in Hell either but probably will some day.
I don't think the rings of the maths were concentric - didn't each one have their own separate gate - the tenners gate led directly outside the walls, not into the unary math?
Another project from the Long Now Foundation that people might find interesting is Long Bets (https://longbets.org/), a site for charitable wagers based around longer term predictions of the future. With the site approaching 20 years old now, we're starting to see many of the medium term bets coming up for settlement, and it's interesting to look back and see what people were predicting around the turn of the century.
Some of the ones I found particularly interesting that are/will be settled this decade:
Bet 4 (https://longbets.org/4/) - Pilotless passenger planes will be routine by the end of the decade.
Bet 712 (https://longbets.org/712/) - A commercial driverless car service will be available (in Las Vegas)
The site was also somewhat notable for the "million dollar bet" (https://longbets.org/362/) between Warren Buffet and Protege Partners about whether a curated portfolio of hedge funds would outperform the S&P500 over a ten year span.
Bet 9 (https://longbets.org/9/) - A bioterror or bioerror will lead to one million casualties in a single event within a six month period starting no later than Dec 31 02020.
If it was truly an accidental lab release, it could be a winning bet...
If reality were in fact a gritty cyberpunk novel, instead of just strongly resembling one, a team of private investigators hired by friends of the Long Now would be the force which finally cracks this case wide open...
The Chinese government would of course deny this for as long as it could in the face of almost any future evidence, but the idea is at least possible. (I'm referring to a genuine lab accident regarding a natural virus being covered up as an event at the market instead, not a conspiracy theory about a bioengineered intentional release)
On April 15th (Tax Day), the Long Now Foundation was approved as a recipient of a "$150,000-350,000" Paycheck Protection Program (PPP) loan, allowing it to retain 21 jobs.
Even without the PPP loan, it's doubtful that the Clock of The Long Now was in jeopardy — Bezos' wealth soared to $200 billion during the pandemic, a new record for the world's richest person.
One of my favorite ideas for how to address this kind of problem is to build a 'clock' based on continuous performance that serves as its own explanation. The best example I can think of is the Halberstadt performance of John Cage's ASLSP (https://en.wikipedia.org/wiki/As_Slow_as_Possible#Performanc...)
If a performance requiring human intervention counts as a clock, then a human-maintained physical clock should too. Why not get a head start with some 14th century cathedral clocks?
I thought about Cage when I saw this submission, and submitted the Wikipedia page for this piece right away. I see your comment now and I’m glad I’m not the only one that made the connection!
About 10 years ago I swung by their San Francisco office. They had an alcove set up with speakers to demonstrate what the clock might sound like. It was very Brian Eno, a la "Music For Airports" but like "Music For Time".
There is a book by the same title - "Clock of the long now". My favourite line is
"In the long run saving yourself requires saving the whole world."
I am getting kind of obssesed how all the problems we are experiencing now stem form externalizing consequences to the future. Climate change, messed up economy or even technical debt stem from making choices that have only short-term consequences in mind.
Speaking of technical debt- I have a post in the works adapting the principles of the long clock to software design. The work of the long now foundation is underrated.
That's a great list of characteristics that you could apply to so many technical constructions for extreme long term use (habitats, power systems, space ships, colonies etc)
38 comments
[ 2.4 ms ] story [ 87.8 ms ] thread2018 https://news.ycombinator.com/item?id=16210106
2015 https://news.ycombinator.com/item?id=8875319
2014 (a bit): https://news.ycombinator.com/item?id=8555122
2014 (a bit): https://news.ycombinator.com/item?id=7979761
2013 (a bit): https://news.ycombinator.com/item?id=6155469
2011 https://news.ycombinator.com/item?id=2665380
2011 https://news.ycombinator.com/item?id=2983359
2011 https://news.ycombinator.com/item?id=2691452
2011 (a bit): https://news.ycombinator.com/item?id=3197789
Starting off 2020 with a nasty bit: https://news.ycombinator.com/item?id=22184282
> > In 100 years I hope to have grandchildren who knew me still living.
> > In 1000 years it's a stretch that there will still be an accurate note of my existence.
> > In 10000 there may not even be a myth about the existence of any of us here.
> 10,000 years from now, I'm going to remind you that you said that, and we'll both think it was pretty funny.
The thought of this for some reason captured my imagination, so I clicked on the username, and then his website, which led me to the AI-Box Experiment and oh boy... what a journey this was. Highly recommend reading about this.
Let's assume the gatekeeper is a cold hearted psychopath or a person with AI phobia/paranoia to the extreme.
Why would they let the AI out when they can't feel anything for it?
The author does explain the time gap but what if that is only for collecting information about the person beforehand in order to blackmail them or steer the conversation into a pinching point? What if you start with s person with no identity?
There are no ethical concerns here. Maybe author will shout horrible things enough times and since you as the gate keeper needs to keep talking and engaging, you may let the AI out but well, we have a psychopath here.
Do people need to engage in good faith with AI? Can I continue to say Sorry, I can't answer that.? Yes? Does the gatekeeper need to be honest? Can I use a client side toxicity filter or censor certain words?
There is nothing that would restrict above so what if I censor AI from saying let me out or similar phrases?
Can you increase the handicap for the AI?
It’s also telling that back then when those experiments were initially conducted you could have a gentleman’s agreement like this (to not disclose the method of convincing) with a complete stranger on the Internet. Sadly nowadays many people would probably do a YouTube video about that immediately.
Yeah I do too. I am super curious but the dataset of two highly filtered individuals isn't enough. I lack the imagination to think of a scenario where I would let it out. I want to know why I would let it out.
> It’s also telling that back then when those experiments were initially conducted you could have a gentleman’s agreement like this (to not disclose the method of convincing) with a complete stranger on the Internet. Sadly nowadays many people would probably do a YouTube video about that immediately.
I wouldn't and I think many active HN members wouldn't too. Trust comes from small tightly knitted communities which would reflect the older internet. It's not that the people changed fundamentally. They are the same but the dynamics of how many communities there are for the same topics. People fear being ostracized but when there are enough options, they put personal responsibility below other goals.
When asked what he wants people to say about him in 100 years, Woody Allen said "'He looks good for his age'".
Like... None? This seems like a complete waste of resources. It's probably a life-like toy from someone with too much money? The world needs more 10,000 year clocks, we don't have any other problems...
If you want a 10,000 clock, you bury a radioactive rock with a note about the decay pattern at the time of creation and future radiologist will know how long it's been "ticking". Problem solved.
I also never quite finished Dodge in Hell either but probably will some day.
But if you've reached the sixfold voco about 2/5ths of the way in and you're still not enjoying it, it might not be your thing.
Some of the ones I found particularly interesting that are/will be settled this decade:
Bet 12 (https://longbets.org/12/) - No one will win a Nobel Prize for string theory by 2020
Bet 1 (https://longbets.org/1/) - The Turing test will not be passed by 2029
Bet 4 (https://longbets.org/4/) - Pilotless passenger planes will be routine by the end of the decade.
Bet 712 (https://longbets.org/712/) - A commercial driverless car service will be available (in Las Vegas)
The site was also somewhat notable for the "million dollar bet" (https://longbets.org/362/) between Warren Buffet and Protege Partners about whether a curated portfolio of hedge funds would outperform the S&P500 over a ten year span.
Bet 9 (https://longbets.org/9/) - A bioterror or bioerror will lead to one million casualties in a single event within a six month period starting no later than Dec 31 02020.
If it was truly an accidental lab release, it could be a winning bet...
In the story universe, The Longs keep a low profile by publishing the bets in dollars.
In fact, an international cabal of power players have $400,000,000 riding on this one. The Longs don’t want to cause alarm.
This video is still much appreciated. https://youtu.be/l-visVMXc6s
https://projects.propublica.org/coronavirus/bailouts/search?...
Even without the PPP loan, it's doubtful that the Clock of The Long Now was in jeopardy — Bezos' wealth soared to $200 billion during the pandemic, a new record for the world's richest person.
[1]: https://www.nealstephenson.com/anathem.html
I am getting kind of obssesed how all the problems we are experiencing now stem form externalizing consequences to the future. Climate change, messed up economy or even technical debt stem from making choices that have only short-term consequences in mind.
Speaking of technical debt- I have a post in the works adapting the principles of the long clock to software design. The work of the long now foundation is underrated.
Go slow, Avoid sliding friction (gears)
Avoid ticking
Stay clean
Stay dry
Expect bad weather
Expect earthquakes
Expect non-malicious human interaction
Dont tempt thieves
Use familiar materials
Allow inspection
Rehearse motions
Make it easy to build spare parts
Expect restarts
Include the manual
Scalability and Evolvabilty:
Make all parts similar size
Separate functions
Provide simple interfaces
Here is my summary of the book: https://piszek.com/2019/10/12/long-now/