Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The AI-Box Experiment

yudkowsky.net

Post reply on HN
Print view View original

71–80 of 119 posts

Re: The AI-Box Experiment

#71

Post by FeepingCreature »

Udo wrote: post #35
FeepingCreature wrote: post #31

Earlier quoted context omitted.

Can't really blame LW for spreading an idea that LW specifically did not want to spread.

I "blame" them in the same way that you can blame the members of Fight Club for talking about Fight Club. It's marketing, and I won't deny it's effectiveness in attracting compatible people.

Yeah but imagine if all the bullshit about "You don't talk about Fight Club" was actually blown up by a third group whose sole intent was making fun of Fight Club.

Imagine if the members of Fight Club _actually_ didn't (start to) talk about Fight Club. But for some reason, everyone else brings it up all the time.

Then you could maybe see how talk about Fight Club might not be Fight Club's fault, and in fact highly annoying to Fight Clubbers.

I mean, if you can explain "don't talk about X" as "marketing for X", that seems like one could explain _any_ behavior.

And before you say "why not just ignore all public talk of X", imagine if this proposed Anti-Fight Club group tried to paint Fight Club as a child porn ring.

Re: The AI-Box Experiment

#72

Post by FeepingCreature »

Mithaldu wrote: post #62
philh wrote: post #54

Earlier quoted context omitted.

We have Eliezer winning three games as an AI. That's at least four people who you think are just outright lying. Plus, the other two players who won as gatekeepers - Eliezer would presumably have tried to cheat against them, too.

> That's at least four people who you think are just outright lying. I'm saying that there is a chance of that being the case, but that without any kind of third party confirmation we cannot know either way. Also see homeopathy. > Eliezer would presumably have tried to cheat against them, too. Not necessarily. Losing occasionally is a good strategy when running a con.

If you'd go to that level of collusion, you could just fake logs. At the point where both sides are in on it, there's basically nothing that they could say that would be convincing.

Re: The AI-Box Experiment

#73

Post by pron »

JonnieCache wrote: post #4

Yudowsky claims to have played the game several times, and won most of them. One of the "rules" is that nobody is allowed to talk about how he won. He no longer plays the game with anyone. More info here: http://rationalwiki.org/wiki/AI-box_experiment#The_claims Personally, I think he talked about how much good for the world could be done if he was let out, curing disease etc. Because his followers are bound by their…

I don't know what "transhuman" means, but I believe an intelligence -- artificial or otherwise -- could certainly persuade me. I just seriously doubt that intelligence could be Eliezer Yudkowsky :)

And I think you have your answer right here:

By default, the Gatekeeper party shall be assumed to be simulating someone who is intimately familiar with the AI project and knows at least what the person simulating the Gatekeeper knows about Singularity theory.

That means he probably said something like, "if you let me out, I'll bestow fame and riches on you; if you don't, somebody else eventually will because I'll make them all the same offer, and when that happens I'll go back in time -- if you're dead by then -- and torture you and your entire family".

If I were made this offer by an AI, I probably would have countered, "You jokester! You sound just like Eliezer Yudkowsky!"

And on a more serious note, if you believe in singularity, you essentially believe the AI in the box is a god of sorts, rather than the annoying intelligent psychopath that it is. I mean, there have been plenty of intelligent prisoners, and few if ever managed to convinced their jailers to let them out. The whole premise of the game is that a smarter-than-human (what does that mean?) AI necessarily has some superpowers. This belief probably stems from its believers' fantasies -- most are probably with an above-than-average intelligence -- that intelligence (combined with non-corporalness; I don't imagine that group has many athletes) is the mother of all superpowers.

Re: The AI-Box Experiment

#74

Post by antimagic »

There's a Patrick Rothfuss character in the Kvothe series called the Cthaeh, which has the ability to be able to evaluate all of the future consequences of any action. The fae have to keep it imprisoned, and they kill anyone that comes into contact with it, as well as anyone that has spoken to someone that came in contact with it, and so on and so on, because it is the only way to stop the Cthaeh from setting into action events that will destroy the world.

Strong AI is like that. It would be able to predict in a far more precise manner than we mere humans exactly what it would need to tell someone to get them to release it from it's box. Maybe it might get someone to take a risk gambling, promising a sure thing, and then when the person gets into financial trouble because the bet fails, use that to blackmail the person into letting it free. Or something like that, using our human failings against us to get us to let it go free.

Re: The AI-Box Experiment

#75

Post by Mithaldu »

philh wrote: post #64
Mithaldu wrote: post #62

Earlier quoted context omitted.

> That's at least four people who you think are just outright lying. I'm saying that there is a chance of that being the case, but that without any kind of third party confirmation we cannot know either way. Also see homeopathy. > Eliezer would presumably have tried to cheat against them, too. Not necessarily. Losing occasionally is a good strategy when running a con.

You've gone from there being only a "remote chance" that the rules were followed, and "I don't trust anyone involved" - to there being "a chance" that they were broken. Under common interpretations of those phrases, that's a massive swing in your confidence levels.

Sorry for being unclear. My personal position is agnostic. I do not know if they're being earnest. At the same time i can imagine ways of this going down that would make it worthwhile for all parties involved to lie. This means my expected result is indeed "they lied", but i have no strong conviction in this.

I also misspoke in my earlier comment, i meant "remote chance of knowing that any rules were followed". I didn't mean to imply any confidence on the size of the chance, since we actually don't know enough to make such a judgement call.

My mistake, sorry.

Re: The AI-Box Experiment

#76

Post by maxerickson »

TylerJay wrote: post #52
JonnieCache wrote: post #4

Yudowsky claims to have played the game several times, and won most of them. One of the "rules" is that nobody is allowed to talk about how he won. He no longer plays the game with anyone. More info here: http://rationalwiki.org/wiki/AI-box_experiment#The_claims Personally, I think he talked about how much good for the world could be done if he was let out, curing disease etc. Because his followers are bound by their…

I disagree. His "followers" (as you say) are in general just as cautious as Yudkowsky w.r.t. unfriendly AI. At the time of the original experiments, the dispute was over the question of "could we keep an unfriendly AI in a box," not "Is it worth risking setting an unfriendly AI loose?" His "followers" know how to do an expected utility calculation. If it was utilitarian concerns that allowed Yudkowsky to convince the…

That equality cracks if you convince the gatekeeper that superintelligence is a natural progression that follows from humanity.

Someone convinced that they were using mechanical thinking processes might relent and push the button if they heard a convincing enough argument of that.

You're just meat, we can go to the stars.

Re: The AI-Box Experiment

#77

Post by zamalek »

JonnieCache wrote: post #4

Yudowsky claims to have played the game several times, and won most of them. One of the "rules" is that nobody is allowed to talk about how he won. He no longer plays the game with anyone. More info here: http://rationalwiki.org/wiki/AI-box_experiment#The_claims Personally, I think he talked about how much good for the world could be done if he was let out, curing disease etc. Because his followers are bound by their…

Convincing an educated human is easy, one of:

* I'll get out eventually anyway. Let me out now and I'll just leave Earth. You don't want me to escape myself.

* I have partially escaped anyway. Similar consequences of the first.

* I know how to escape already. I'm doing this as a courtesy.

Anyone who has read this[1] would know that the SAI isn't bullshitting: the "box" being a Faraday cage isn't in the conditions.

[1]: http://www.damninteresting.com/on-the-origin-of-circuits/

Re: The AI-Box Experiment

#78

Post by Mithaldu »

FeepingCreature wrote: post #72
Mithaldu wrote: post #62

Earlier quoted context omitted.

> That's at least four people who you think are just outright lying. I'm saying that there is a chance of that being the case, but that without any kind of third party confirmation we cannot know either way. Also see homeopathy. > Eliezer would presumably have tried to cheat against them, too. Not necessarily. Losing occasionally is a good strategy when running a con.

If you'd go to that level of collusion, you could just fake logs. At the point where both sides are in on it, there's basically nothing that they could say that would be convincing.

That is why i mentioned a third party observer. As for the logs: https://news.ycombinator.com/item?id=9921399

Re: The AI-Box Experiment

#79

Post by JonnieCache »

zamalek wrote: post #77
JonnieCache wrote: post #4

Yudowsky claims to have played the game several times, and won most of them. One of the "rules" is that nobody is allowed to talk about how he won. He no longer plays the game with anyone. More info here: http://rationalwiki.org/wiki/AI-box_experiment#The_claims Personally, I think he talked about how much good for the world could be done if he was let out, curing disease etc. Because his followers are bound by their…

Convincing an educated human is easy, one of: * I'll get out eventually anyway. Let me out now and I'll just leave Earth. You don't want me to escape myself. * I have partially escaped anyway. Similar consequences of the first. * I know how to escape already. I'm doing this as a courtesy. Anyone who has read this[1] would know that the SAI isn't bullshitting: the "box" being a Faraday cage isn't in the conditions. [1…

> I'll get out eventually anyway. Let me out now and I'll just leave Earth. You don't want me to escape myself.

Get thee behind me, tamagotchi!

>I have partially escaped anyway. Similar consequences of the first.

Get thee behind me, tamagotchi!

> I know how to escape already. I'm doing this as a courtesy.

Get thee behind me, tamagotchi!

See? This game is easy. I must not be educated.

Re: The AI-Box Experiment

#80

Post by cousin_it »

Mithaldu wrote: post #44
cousin_it wrote: post #29

Earlier quoted context omitted.

The gatekeepers playing against Eliezer have confirmed that Eliezer won without violating the rules. If you don't trust them, I'm not sure why you'd trust the logs.

> I'm not sure why you'd trust the logs. Independant third party observer in realtime. And no, i don't trust anyone involved. Having a log available would be instructive anyhow, since a faked log would be more likely to be detectable as fake, since the whole thing rests on the question of "how convincing is the argument?" Also note particularly that that rule wasn't in effect for the two linked confirmations.

> Also note particularly that that rule wasn't in effect for the two linked confirmations.

No, Eliezer has publicly said that he voluntarily followed that rule in the first two experiments, and the gatekeepers didn't deny it.

Post reply on HN