Assuming we've solved X, could we do Y...

I think this argument applies well to the case where we are trying to communicate, but not so much to the case where I individually am thinking about a problem. Communication is hard and if the speaker uses some intuitive assumption, chances are the listener will interpret it differently from what the speaker intended, and so being very precise seems quite helpful. However, when I'm thinking through a problem myself and I make an assumption, I usually have a fairly detailed intuitive model of what I mean, such that if you ask me whether I'm assuming that problem X is solved by the assumption, I could answer that, even though I don't have a precise formulation of the assumption. Making the assumption more precise would be quite a lot of work, and probably would not improve my thinking on the topic that much, so I tend not to do it until I think there's some insight and want to make the argument more rigorous. It seems to me that this is how most research makes progress: by individual researchers having intuitions that they then make rigorous and precise.

Hey, David here!

Just writing to give some context... The point of this session was to discuss an issue I see with "super-human feedback (SHF)" schemes (e.g. debate, amplification, recursive reward modelling) that use helper AIs to inform human judgments. I guess there was more of an inferential gap going into the session than I expected, so for background: let's consider the complexity theory viewpoint in feedback (as discussed in section 2.2 of "AI safety via debate"). This implicitly assumes that we have access to a trusted (e.g. human) decision making process (TDMP), sweeping the issues that Stuart mentions under the rug.

Under this view, the goal of SHF is to efficiently emulate the TDMP, accelerating the decision-making. For example, we'd like an agent trained with SHF to be able to quickly (e.g. in a matter of seconds) make decisions that would take the TDMP billions of years to decide. But we don't aim to change the decisions.

Now, the issue I mentioned is: there doesn't seem to be any way to evaluate whether the SHF-trained agent is faithfully emulating the TDMP's decisions on such problems. It seems like, naively, the best we can do is train on problems where the TDMP can make decisions quickly, so that we can use its decisions as ground truth; then we just hope that it generalizes appropriately to the decisions that take TDMP billions of years. And the point of the session was to see if people have ideas for how to do less naive experiments that would allow us to increase our confidence that a SHF-scheme would yield safe generalization to these more difficult decisions.

Imagine there are 2 copies of me, A and B. A makes a decision with some helper AIs, and independently, B makes a decision without their help. A and B make different decisions. Who do we trust? I'm more ready to trust B, since I'm worried about the helper AIs having an undesirable influence on A's decision-making.

--------------------------------------------------------------------

...So questions of how to define human preferences or values seem mostly orthogonal to this question, which is why I want to assume them away. However, our discussion did make me consider more that I was making an implicit assumption (and this seems hard to avoid), that there was some idealized decision-making process that is assumed to be "what we want". I'm relatively comfortable with trusting idealized versions of "behavioral cloning/imitation/supervised learning" (P) or "(myopic) reinforcement learning/preference learning" (NP), compared with the SHF-schemes (PSPACE).

One insight I gleaned from our discussion is the usefulness of disentangling:

• an idealized process for *defining* "what we want" (HCH was mentioned as potentially a better model of this than "a single human given as long as they want to think about the decision" (which was what I proposed using, for the purposes of the discussion)).
• a means of *approximating* that definition.

From this perspective, the discussion topic was: how can we gain empirical evidence for/against this question: "Assuming that the output of a human's indefinite deliberation is a good definition of 'what they want', do SHF-schemes do a good/safe job of approximating that?"

At some point in the discussion, he said "let's assume the question of defining human values is solved"

What did he need that assumption for? If the setting is that two AIs try to convince a human audience, the assumption doesn't seem to enter into it. The important question is presumably what friendliness properties we can deduce about any AI that wins the debate against every other AI.

Debate seems like a dubious method of alignment because you can just indefinitely keep adjusting or introducing new auxiliary assumptions, and overarching frameworks are very rarely abandoned in this context.