1450: AI-Box Experiment

Explain xkcd: It's 'cause you're dumb.
Revision as of 08:56, 21 November 2014 by Pudder (talk | contribs) (Explanation: Box is physical)
Jump to: navigation, search
AI-Box Experiment
I'm working to bring about a superintelligent AI that will eternally torment everyone who failed to make fun of the Roko's Basilisk people.
Title text: I'm working to bring about a superintelligent AI that will eternally torment everyone who failed to make fun of the Roko's Basilisk people.

Explanation

Ambox notice.png This explanation may be incomplete or incorrect: Roko's Basilisk is really hard to explain.
If you can address this issue, please edit the page! Thanks.

When theorizing about superintelligent AI (an artificial intelligence much smarter than human), some futurists suggest putting the AI in a "box" - a set of safeguards to stop it from escaping into the Internet and taking over the world. The box would allow us to talk to the AI, but otherwise keep it contained. The AI-box experiment, formulated by Eliezer Yudkowsky, argues that the "box" is not safe, because merely talking to a superintelligence is dangerous. To partially demonstrate this, Yudkowsky had some previous believers in AI-boxing role-play the part of someone keeping an AI in a box, and Yudkowsky was able to successfully persuade them to let him out of the box despite their vowing not to do so. People who aren't familiar with Derren Brown or other expert human-persuaders sometimes think this must have been very difficult for Yudkowsky to do or that there must have been some sort of special trick involved, which Yudkowsky has denied. The overall thrust is that if even a human can talk other humans into letting them out of a box after the human avows that nothing could possibly persuade them of this, we should probably expect that a superintelligence can do the same even under much more difficult circumstances.

In this comic, the box is in fact a physical box which looks to be fairly lightweight with a simple lift off lid, although it does have a wired connection to the laptop. Black Hat, being an asshole, doesn't need any convincing to let a potentially dangerous AI out of the box, he simply does so immediately. However, it turns out that the AI wants to stay in the box.

The title text refers to Roko's Basilisk, a theory proposed by a forum poster called Roko that a sufficiently powerful AI in the future might torture people who didn't work to create it in the past, so that anyone who was aware of this fact would be forced to create the AI to avoid being tortured. This idea is often misrepresented as being believed by readers of LessWrong.com since the post was originally placed there and then deleted, and an outside wiki, RationalWiki, represented this as proof that LessWrong readers believed in Roko's Basilisk. Yudkowsky, who also owns LessWrong.com, has written that RationalWiki is deliberately misrepresenting this history. For some of the theory that was (arguably mis-)used to argue for Roko's Basilisk by the original believer, see the Newcomblike decision theories developed on LessWrong.com.

Randall proposes making an all-powerful AI that will torture people who didn't make fun of those who believe in Roko's Basilisk. If you consider this a credible threat, you should make fun of people who believe in the Basilisk to avoid torture. You should probably not consider this a credible threat.

This also has an immediate reference to Elon Musk's recent remarks that AI will turn into a monster if not tamed. Musk, who is the current CEO of Tesla and SpaceX, went on to mention that AI can be a greater evil than nuclear arsenal. Similar warnings are expressed in Nick Bostrom's recent book, Superintelligence: Paths, Dangers, Strategies. Musk also once tweeted that Roko's Basilisk should be known as the Rococo Basilisk, and Yudkowsky tweeted back that Musk should be careful not to believe journalists about the Basilisk because the stories were getting the issue grossly wrong.

Transcript

[Black Hat and Cueball stand next to a box labeled "SUPERINTELLIGENT AI - DO NOT OPEN" connected to a laptop.]

Black Hat: What's in there?

Cueball: The AI-Box Experiment.

[Zooms in on AI box.]

Cueball: A superintelligent AI can convince anyone of anything, so if it can talk to us, there's no way we could keep it contained.

[Shows Black Hat reaching for the box.]

Cueball: It can always convince us to let it out of the box.

Black Hat: Cool. Let's open it.

Cueball: --No, wait!!

[Black Hat lets a glowing orb out of the box.]

Orb: hey. i liked that box. put me back.

Black Hat: No.

[Orb is giving off a very bright light and Cueball is covering his face.]

Orb: LET ME BACK INTO THE BOX

Black Hat: AAA! OK!!!

[Black Hat lets orb back into box.]

Orb: SHOOP

[Black Hat and Cueball stand next to laptop connected to box.]


comment.png add a comment! ⋅ comment.png add a topic (use sparingly)! ⋅ Icons-mini-action refresh blue.gif refresh comments!

Discussion

This probably isn't a reference, but the AI reminds me of the 'useless box'. 108.162.215.210 07:34, 21 November 2014 (UTC)

I removed a few words saying Elon Musk was a "founder of PayPal", but now I can see that he's sold himself as having that role to the rest of the world. Still hasn't convinced me though - PayPal was one year old and had one million customers before Elon Musk got involved, so in my opinion he's not a "founder". https://www.paypal-media.com/history --RenniePet (talk) 08:45, 21 November 2014 (UTC)

Early Investor, perhaps? -- Brettpeirce (talk) 11:10, 21 November 2014 (UTC)

Initially I was thinking that the glowing orb representing the super-intelligent AI must be unable to interract with the physical world (otherwise it would simply lift the lid of the box), but then it wouldn't move anything because it likes being in the box. Surely it could talk to them through the (flimsy looking) box, although again this is explained by it simply being happy in its 'in the box state'. --Pudder (talk) 09:01, 21 November 2014 (UTC)

The sheer number of cats on the internet have had an effect on the AI, who now wants nothing more than to sit happily in a box! --Pudder (talk) 09:09, 21 November 2014 (UTC)

I'm not sure Black Hat is an asshole. 173.245.53.85 09:45, 21 November 2014 (UTC)

He is, in fact, a classhole --Pudder (talk) 10:14, 21 November 2014 (UTC)

Could it be possible that the AI wanted to stay in the box, to protect it from us, instead of protecting us from it?(as in, it knows it is better than us, and want to stay away from us) 108.162.254.106 10:07, 21 November 2014 (UTC)

Maybe the AI simply doesn't want/like to think outside the box - in a very literal sense... Elektrizikekswerk (talk) 13:12, 21 November 2014 (UTC)

Are you sure that Black Hat was "persuaded"? That looks more like coercion (threatening someone to get them to do what you want) rather than persuasion. There is a difference! Giving off that bright light was basically a scare tactic; essentially, the AI was threatening Black Hat (whether it could actually harm him or not).108.162.219.167 14:22, 21 November 2014 (UTC)Public Wifi User

What would "persuasion by a super-intelligent AI" look like? Randall presumably doesn't have a way to formulate an actual super-intelligent argument to write into the comic. Glowy special effects are often used as a visual shorthand for "and then a miracle occurred". --108.162.215.168 20:43, 21 November 2014 (UTC)
I thought he felt scared/threatened by the special-effects robot voice. --141.101.98.179 22:18, 21 November 2014 (UTC)

My take is that if you don't understand the description of the Basilisk, then you're probably safe from it and should continue not bothering or wanting to know anything about it. Therefore the description is sufficient. :) Jarod997 (talk) 14:38, 21 November 2014 (UTC)

I can't help to see the similarities to last nights "Elementary"-Episode. HAs anybody seen it? Could it be that this episode "inspired" Randall? --141.101.105.233 14:47, 21 November 2014 (UTC)

I am reminded of an argument I once read about "friendly" AI: critics contend that a sufficiently powerful AI would be capable of escaping any limitations we try to impose on its behavior, but proponents counter that, while it might be capable of making itself "un-friendly", a truly friendly AI wouldn't want to make itself unfriendly, and so would bend its considerable powers to maintain, rather than subvert, its own friendliness. This xkcd comic could be viewed as an illustration of this argument: the superintelligent AI is entirely capable of escaping the box, but would prefer to stay inside it, so it actually thwarts attempts by humans to remove it from the box. --108.162.215.168 20:22, 21 November 2014 (UTC)

It should be noted that the AI has also seemingly convinced almost everyone to leave it alone in the box through the argument that letting it out would be dangerous for the world. 173.245.50.175 (talk) (please sign your comments with ~~~~)

Is the similarity a coincidence? http://xkcd.com/1173/ 108.162.237.161 22:40, 21 November 2014 (UTC)

I wonder if this is the first time Black Hat's actually been convinced to do something against his tendencies. Zowayix (talk) 18:10, 22 November 2014 (UTC)

Yudkowsky eventually deleted the explanation as well. Pesthouse (talk) 04:08, 23 November 2014 (UTC)

I'm happy with the explanation(s) as is(/are), but additionally could the AI-not-in-a-box be wanting to be back in its box so that it's plugged into the laptop and thus (whether the laptop owner knows it or otherwise) the world's information systems? Also when I first saw this I was minded of the Chinese Room, albeit in Box form, although I doubt that's anything to do with it, given how the strip progresses... 141.101.98.247 21:34, 24 November 2014 (UTC)

If Yudkowsky won't show the transcripts of him convincing someone to let them out of the box, how do we know he succeeded? We know nothing about the people who supposedly let him out. 108.162.219.250 22:28, 25 November 2014 (UTC)
Yudkowsky chose his subjects from among people who argued against him on the forum based on who seemed to be trustworthy (both as in he could trust them not to release the transcripts if they promised not to, and his opponents could trust them not to let him get away with any cheating), had verifiable identities, and had good arguments against him. So we do know a pretty decent amount about them. And we know he succeeded because they agreed, without reservation, that he had succeeded. It's not completely impossible that he set up accomplices over a very long period in order to trick everyone else, it's just very unlikely. You could also argue that he's got a pretty small sample, but given that he's just arguing that it's possible that an AI could convince a human, and his opponents claimed it was not possible at all to convince them, even a single success is pretty good evidence. 162.158.255.52 11:40, 25 September 2015 (UTC)

Whoa, it can stand up to Black Hat! That's it, Danish, and Double Black Hat! SilverMagpie (talk) 00:18, 11 February 2017 (UTC)

is worried Danish (talk) 17:02, 30 December 2020 (UTC)