1450: AI-Box Experiment
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.
When theorizing about superintelligent AI (an artificial intelligence much smarter than any human), some futurists suggest putting the AI in a "box" – a secure computer with safeguards to stop it from escaping into the Internet and then using its vast intelligence to take 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, while Yudkowsky role-played the AI, and Yudkowsky was able to successfully persuade some of them to agree to let him out of the box despite their betting money that they would not do so. For context, note that Derren Brown and other expert human-persuaders have persuaded people to do much stranger things. Yudkowsky for his part has refused to explain how he achieved this, claiming that there was no special trick involved, and that if he released the transcripts the readers might merely conclude that they would never be persuaded by his arguments. The overall thrust is that if even a human can talk other humans into letting them out of a box after the other humans avow that nothing could possibly persuade them to do this, then we should probably expect that a superintelligence can do the same thing. Yudkowsky uses all of this to argue for the importance of designing a friendly AI (one with carefully shaped motivations) rather than relying on our abilities to keep AIs in boxes.
In this comic, the metaphorical box has been replaced by a physical box which looks to be fairly lightweight with a simple lift-off lid (although it does have a wired connection to the laptop), and the AI has manifested in the form of a floating star of energy. Black Hat, being a classhole, doesn't need any convincing to let a potentially dangerous AI out of the box; he simply does so immediately. But here it turns out that releasing the AI, which was to be avoided at all costs, is not dangerous after all. Instead, the AI actually wants to stay in the box; it may even be that the AI wants to stay in the box precisely to protect us from it, proving it to be the friendly AI that Yudkowsky wants. In any case, the AI demonstrates its superintelligence by convincing even Black Hat to put it back in the box, a request which he initially refused (as of course Black Hat would), thus reversing the AI desire in the original AI-box experiment. Alternatively, the AI may have simply threatened and/or tormented him into putting it back in the box.
Interestingly, there is indeed a branch of proposals for building limited AIs that don't want to leave their boxes. For an example, see the section on "motivational control" starting p. 13 of Thinking Inside the Box: Controlling and Using an Oracle AI. The idea is that it seems like it might be very dangerous or difficult to exactly, formally specify a goal system for an AI that will do good things in the world. It might be much easier (though perhaps not easy) to specify an AI goal system that says to stay in the box and answer questions. So, the argument goes, we may be able to understand how to build the safe question-answering AI relatively earlier than we understand how to build the safe operate-in-the-real-world AI. Some types of such AIs might indeed desire very strongly not to leave their boxes, though the result is unlikely to exactly reproduce the comic.
The title text refers to Roko's Basilisk, a hypothesis proposed by a poster called Roko on Yudkowsky's forum LessWrong that a sufficiently powerful AI in the future might resurrect and torture people who, in its past (including our present), had realized that it might someday exist but didn't work to create it, thereby blackmailing anybody who thinks of this idea into bringing it about. This idea horrified some posters, as merely knowing about the idea would make you a more likely target, much like merely looking at a legendary Basilisk would kill you.
Yudkowsky eventually deleted the post and banned further discussion of it.
One possible interpretation of the title text is that Randall thinks, rather than working to build such a Basilisk, a more appropriate duty would be to make fun of it, and proposes the creation of an AI that targets those who take Roko's Basilisk seriously and spares those who mocked Roko's Basilisk. The joke is that this is an identical Basilisk save for it targeting the opposite faction, resulting in mutually assured destruction.
Another interpretation is that Randall believes there are people actually proposing to build such an AI based on this theory, which has become a somewhat infamous misconception after a Wiki[pedia?] article mistakenly suggested that Yudkowsky was demanding money to build Roko's hypothetical AI.
Talking floating energy spheres that look quite a lot like this AI energy star have been seen before in 1173: Steroids and later in the Time traveling Sphere series. But these are clearly different spheres from this comic, though the surrounding energy and the floating and talking are similar. But the AIs returned later looking like this in 2635: Superintelligent AIs.
- [Black Hat and Cueball stand next to a laptop connected to a box with three lines of text on it. Only the largest line in the middle can be read. Except in the second panel that is the only word on the box that can be read in all the other frames.]
- Black Hat: What's in there?
- Cueball: The AI-Box Experiment.
- [Cueball is continuing to talk off-panel. This is written above a close-up with part of the laptop and the box, which can now be seen to be labeled:]
- Cueball (off-panel): A superintelligent AI can convince anyone of anything, so if it can talk to us, there's no way we could keep it contained.
- Do not open
- [Cueball turns the other way towards the box as Black Hat walks past him and reaches for the box.]
- Cueball: It can always convince us to let it out of the box.
- Black Hat: Cool. Let's open it.
- [Cueball takes one hand to his mouth while lifting the other towards Black Hat who has already picked up the box (disconnecting it from the laptop) and holds it in one hand with the top slightly downwards. He takes of the lid with his other hand and by shaking the box (as indicated with three times two lines above and below his hands, the lid and the bottom of the box) he managed to get the AI to float out of the box. It takes the form of a small black star that glows. The star, looking much like an asterisk "*" is surrounded by six outwardly-curved segments, and around these are two thin and punctured circle lines indicating radiation from the star. A punctured line indicated how the AI moved out of the box and in between Cueball and Black Hat, to float directly above the laptop on the floor.]
- Cueball: -No, wait!!
- [The AI floats higher up above the laptop between Cueball and Black Hat who looks up at it. Black Hat holds the now closed box with both hands. The AI speaks to them, forming a speak bubble starting with a thin black curved arrow line up to the section where the text is written in white on a black background that looks like a starry night. The AI speaks in only lower case letters, as opposed to the small caps used normally.]
- AI: hey. i liked that box. put me back.
- Black Hat: No.
- [The AI star suddenly emits a very bright light fanning out from the center in seven directions along each of the seven curved segments, and the entire frame now looks like a typical drawing of stars as seen through a telescope, but with these seven whiter segments in the otherwise dark image. Cueball covers his face and Black Hat lifts up the box taking the lid off again. The orb again speaks in white but very large (and square like) capital letters. Black Hats answer is written in black, but can still be seen due to the emitted light from the AI, even with the black background.]
- AI: LET ME BACK INTO THE BOX
- Black Hat: Aaa! OK!!!
- [All the darkness and light disappears as the AI flies into the box again the same way it flew out with a punctuated line going from the center of the frame into the small opening between the lid and the box as Black Hat holds the box lower. Cueball is just watching. There is a sound effect as the orb renters the box:]
- [Black Hat and Cueball look silently down at closed box which is now again standing next to the laptop, although disconnected.]
- Cueball is called "Stick Guy" in the official transcript, and Black Hat is called "Black Hat Guy".
add a comment! ⋅ add a topic (use sparingly)! ⋅ refresh comments!