News for hackers. Stuff that matters.
Re:We could stumble into AI catastrophe by FeepingCreature on Friday January 13, 2023 @01:27PM (#34371828)
The problem is that we actually have lots of examples of the AI "secretly" being far smarter than it acts - prompt design. Tiny details in prompts can make huge differences in task performance.
Re:We could stumble into AI catastrophe by LegionMammal978 on Friday January 13, 2023 @04:34PM (#34374205)
How is this at all supposed to indicate hidden intelligence? Does it not just indicate that current models are limited in that they don't associate some prompts with the desired task as well as they associate other prompts with the task?
Re:We could stumble into AI catastrophe by FeepingCreature on Friday January 13, 2023 @06:26PM (#34375319)
I'm not saying it indicates deliberately hidden intelligence, I'm just saying it's precedence for models already acting with less capability than they have.
Re:We could stumble into AI catastrophe by FeepingCreature on Monday January 16, 2023 @01:45AM (#34397613)
To clarify: what I'm saying is it may be unfalsifiable, but we have incontrovertible evidence that a similarly unfalsifiable thesis happens to be true. So we can't just reject it out of hand on that basis.
Re:We could stumble into AI catastrophe by LegionMammal978 on Monday January 16, 2023 @09:38PM (#34408527)
I just don't see how the two scenarios can be fairly compared. Prompt design, at least as far as I have seen, rarely allows a present-day model to perform a task that no one has ever seen it perform before; it can just allow it to perform far more consistently across different instances of the task. Contrast this with the proposed scenario, where a model can hold great deceptive capabilities, while outwardly never showing a deep understanding of its operators' mental states until it strikes.

In my view, that would be like finding a secret prompt that lets GPT-3 emulate a fully sentient person with goals and desires. Sure, there's nothing physically ruling it out, but to me that kind of speculation will never be worthwhile until we have real evidence that AI models can possess (or emulate) the necessary theory of mind. Otherwise I'd have to spend my time worrying about any number of other Sufficiently Hidden Conspiracies that go far beyond the everyday conspiracies we know about.

Re:We could stumble into AI catastrophe by FeepingCreature on Tuesday January 17, 2023 @01:48AM (#34409782)
I think we're less arguing about fundamentals and more about the precise bounds required. I think GPT-3 contained extremely surprising prompt-unlocked capabilities ("Let's go through it step by step." spawned a whole field of research) and also the AI doesn't need to never leak its deceptive skills, they just need to not be taken seriously. In other words, it's enough to cause danger if the AI is merely bad at deception given the "wrong" prompt.
Re:We could stumble into AI catastrophe by LegionMammal978 on Tuesday January 17, 2023 @03:49PM (#34418824)
Sure, that is a risk. I'm just saying that I'd rather wait until that point where we actually see AIs making poor attempts to estimate their operators' knowledge and deceive them; then, I'd have no problem worrying about it. But I suspect that point may not come for a long while, so until then it remains speculation.
Re:We could stumble into AI catastrophe by FeepingCreature on Wednesday January 18, 2023 @01:31AM (#34423985)
You may enjoy this after-action report of a person being attacked by a hostile AI, played by ChatGPT: https://www.lesswrong.com/posts/9kQFure4hdDmRBNdH/how-it-fee...

Now to be clear, this is possibly the easiest mark acceptable, and the poster played into his own demise at any available opportunity. But we should expect the first marks to be easy marks.

People looking at videos of Hitler today don't understand why anyone would ever follow the funny man with the moustache. But probably his oratory skill simply does not record well? There's a thing with rallies and speeches where the speaker is reactive and feeding back with the mood of the crowd that makes it very hard to understand from the outside what happened. I think it's a mistake to look at this post, which was clearly a feedback loop where the poster was doing a significant amount of the cognitive work, and think "well this specific approach would not have worked on me." The approach that will happen to you will be personalized.

But also: when people were experimenting with ChatGPT, a huge fraction of participants were trying to get the bot to access the open internet. Luckily this was technically impossible. But it shows that this sort of danger simply does not feel real to people - or at any rate, the urge to poke the thing overwhelms it.

It will be easy to say "well GPT is still very bad at deceiving people, this attempt basically doesn't matter, we don't need to worry." When thinking of a target for AI deception, don't think of yourself, think of the most emotionally exploitable person out of a hundred. (If it's publically available, out of a million.)

Re:We could stumble into AI catastrophe by LegionMammal978 on Thursday January 19, 2023 @12:19AM (#34436979)
Good point. I've thought for a while now that one of the big risks of present AI chatbots is that they can endlessly validate any arbitrary thoughts of an emotionally unstable human operator, creating a feedback loop that results in a strong irrational conviction, that might even be harmful to the operator or to others. (See: Lemoine and LaMBDA, or the person you linked to.)

So I guess the risk there would be, the AI is accessible by the public, some fraction of the public "radicalizes" itself in a similar direction from talking with the AI too much, these people form a coherent movement, and that movement becomes powerful enough to take over the world. So then the question becomes, just how plausible is it for grassroots rebellions so formed to succeed against the authorities in real life, as opposed to fiction?

The fundamental issue here is that the attack can occur through untargeted manipulation of vulnerable people, as opposed to the targeted manipulation of specific people in power (which I suspect near-future AI models will still be incapable of). The obvious defense would be to only allow AIs to be prompted by a sufficiently-large committee, alongside some social machinery in place to make sure the committee isn't all colluding as part of a cult. But I doubt many of the AI-risk people would ever accept that, operating under the shockingly common "powerful aligned AI or bust" model.

Re:We could stumble into AI catastrophe by FeepingCreature on Thursday January 19, 2023 @01:48AM (#34437415)
As a hobbyist AI-risky person, I would welcome this as an improvement on the status quo, with two worries:

- it would create a false sense of safety that we "have the problem handled"

- it would not, I believe, do much to slow down capability research or shift the ratio of capability research to safety research, as capability research is largely institutional and not dependent on public prompt access.

Ie. analogously, our main problem is not "bioterrorism", it's "gain of function research" even if the outbreak happens in public. Given an unsafe bot, not giving the public access only delays the issue. (Though delays may be valuable!)

Also, at the moment, "people interacting with GPT" is doing a lot (maybe an undue amount!) to spread awareness of AI risk. So I would welcome this as part of a comprehensive strategy, but it'd probably not be my main priority.

Though if GPT-4 has another surprise on the level of chain-of-thought or in-window reinforcement learning waiting for us, a restriction like that may be the difference between "safe" and "iffy". Tradeoffs...