Yes, we are currently planning continue to pursue these directions for scalable oversight. My current best guess is that scalable oversight will do a lot of the heavy lifting for aligning roughly human-level alignment research models (by creating very precise training signals), but not all of it. Easy-to-hard generalization, (automated) interpretability, adversarial training+testing will also be core pieces, but I expect we'll add more over time.
I don't really understand why many people updated so heavily on the obfuscated arguments problem; I don't t
Yeah, you could reformulate the question as "how much consequentialist reasoning do you need to do 95% or 99% of the alignment work?" Maybe the crux is in what we mean by consequentialist reasoning. For example, if you build a proof oracle AlphaZero-style, would that be a consequentialist? Since it's trained with RL to successfully prove theorems you can argue it's a consequentialist since it's the distillation of a planning process, but it's also relatively myopic in the sense that it doesn't care about anything that happens after the current theorem is p...
Insofar that philosophical progress is required, my optimism for AI helping on this is lower than for (more) technical research since in philosophy evaluation is often much harder and I'm not sure that it's always easier than generation. You can much more easily picture a highly charismatic AI-written manifesto that looks very persuasive and is very difficult to refute than it is to make technical claims about math, algorithms, or empirical data that are persuasive and hard to falsify.
However, I'm skeptical that the list of novel philosophical problems we...
Thanks for writing this! I'd be very excited to see more critiques of our approach and it's been great reading the comments so far! Thanks to everyone who took the time to write down their thoughts! :)
I've also written up a more detailed post on why I'm optimistic about our approach. I don't expect this to be persuasive to most people here, but it should give a little bit more context and additional surface area to critique what we're doing.
I strongly agree with you that it'll eventually be very difficult for humans to tell apart AI-generated alignment proposals that look good and aren't good from ones that look good and are actually good.
There is a much stronger version of the claim "alignment proposals are easier to evaluate than to generate" that I think we're discussing in this thread, where you claim that humans will be able to tell all good alignment proposals apart from bad ones or at least not accept any bad ones (precision matters much more than recall here since you can compensate b...
If it turns out that evaluation of alignment proposals is not easier than generation, we're in pretty big trouble because we'll struggle to convince others that any good alignment proposals humans come up with are worth implementing.
You could still argue by generalization that we should use alignment proposals produced by humans who had a lot of good proposals on other problems even if we're not sure about those alignment proposals. But then you're still susceptible to the same kinds of problems.
You might think that humans are more robust on the distribution of [proposals generated by humans trying to solve alignment] vs [proposals generated by a somewhat superhuman model trying to get a maximal score]
I think we need to unpack "sufficiently aligned"; here's my attempt. There are A=2^10000 10000-bit strings. Maybe 2^1000 of them are coherent English text, and B=2^200 of these are alignment proposals that look promising to a human reviewer, and C=2^100 of them are actually correct and will result in aligned AI.The thesis of the post requires that we can make a "sufficiently aligned" AI that, conditional on a proposal looking promising, is likely to be actually correct.
Thanks for your question! I suspect there is some confusion going on here with what recursive reward modeling is. The example that you describe sounds like an example from imitating expert reasoning.
In recursive reward modeling, agent is not decomposing tasks, it is trying to achieve some objective that the user intends for it to perform. then assists the human in evaluating ’s behavior in order to train a reward model. Decomposition only happens on the evaluation of ’s task.
For example, proposes some plan and proposes the largest weaknes...
This is an obviously important problem! When we put a human in the loop, we have to be confident that the human is actually aligned—or at least that they realize when their judgement is not reliable to the current situation and defer to some other fallback process or ask for additional assistance. We are definitely thinking about this problem at DeepMind, but it’s out of the scope of this paper and the technical research direction that we are proposing to pursue here. Instead, we zoom into one particular aspect, how to solve the agent alignment problem in the context of aligning a single agent to a single user, because we think it is the hardest technical aspect of the alignment problem.
I'm glad to hear that the DeepMind safety team is thinking about this problem and look forward to reading more about your thoughts on it. However I don't think putting human safety problems outside of "aligning a single agent to a single user" is a natural way to divide up the problem space, because there are likely ways to address human safety problems within that context. (See these two posts which I wrote after posting my comment here.)
I would go further and say that without an understanding of the ways in which humans are unsafe, and how that should be
...Good question. The short answer is “I’m not entirely sure.” Other people seem to struggle with understanding Paul Christiano’s agenda as well.
When we developed the ideas around recursive reward modeling, we understood amplification to be quite different (what we ended up calling Imitating expert reasoning in the paper after consulting with Paul Christiano and Andreas Stuhlmüller). I personally find that the clearest expositions for what Paul is trying to do are Iterated Distillation and Amplification and Paul's latest paper, which we compare to in mul...
Iterated amplification is a very general framework, describing algorithms with two pieces:
Given these two pieces, we plug them into each other: the output of distillation becomes the input to amplifica...
I'm not entirely sure but here is my understanding:
I think Paul pictures relying heavily on process-based approaches where you trust the output a lot more because you closely held the system's hand through the entire process of producing the output. I expect this will sacrifice some competitiveness, and as long as it's not too much it shouldn't be that much of a problem for automated alignment research (as opposed to having to compete in a market). However, it might require a lot more human supervision time.
Personally I am more bullish on understanding how... (read more)