I think there is a good chance that humans could learn to break this kind of task (e.g. designing hessian-free optimization) into tiny pieces, with moderate training and experience, in a way that looks “fair” i.e. not like acting as human transistors. If so, I’m optimistic that we will be able to get good demonstrations of that fact relatively soon, within something like 1-2 years.
For hard tasks these won’t take the form of complete demonstrations, they will either be (a) examples using ML automation (which will need to wait until ML is strong enough, so won’t get tasks as complicated as “design hessian free optimization” until very close to the end) or (b) an interactive protocol where some parts of the deliberation are left as stubs, simulated by normal humans, and then fleshed out into detailed deliberation based on challenges.
For the kinds of questions discussed in this post, which I think are easier than “Design Hessian-Free Optimization” but face basically the same problems, I think we are making reasonable progress. I’m overall happy with the progress but readily admit that it is much slower than I had hoped. I’ve certainly made updates (mostly about people, institutions, and getting things done, but naturally you should update differently).
Note that I don’t think “Design Hessian-Free Optimization” is amongst the harder cases, and these physics problems are a further step easier than that. I think that sufficient progress on these physics tasks would satisfy the spirit of my remark 2y ago.
I appreciate the reminder at the 2y mark. You are welcome to check back in 1y later and if things don’t look much better (at least on this kind of “easy” case), treat it as a further independent update.
I think there is a good chance that humans could learn to break this kind of task (e.g. designing hessian-free optimization) into tiny pieces, with moderate training and experience, in a way that looks “fair” i.e. not like acting as human transistors. If so, I’m optimistic that we will be able to get good demonstrations of that fact relatively soon, within something like 1-2 years.
For hard tasks these won’t take the form of complete demonstrations, they will either be (a) examples using ML automation (which will need to wait until ML is strong enough, so won’t get tasks as complicated as “design hessian free optimization” until very close to the end) or (b) an interactive protocol where some parts of the deliberation are left as stubs, simulated by normal humans, and then fleshed out into detailed deliberation based on challenges.
It has been 2 years. Have said demonstrations materialized?
I think not.
For the kinds of questions discussed in this post, which I think are easier than “Design Hessian-Free Optimization” but face basically the same problems, I think we are making reasonable progress. I’m overall happy with the progress but readily admit that it is much slower than I had hoped. I’ve certainly made updates (mostly about people, institutions, and getting things done, but naturally you should update differently).
Note that I don’t think “Design Hessian-Free Optimization” is amongst the harder cases, and these physics problems are a further step easier than that. I think that sufficient progress on these physics tasks would satisfy the spirit of my remark 2y ago.
I appreciate the reminder at the 2y mark. You are welcome to check back in 1y later and if things don’t look much better (at least on this kind of “easy” case), treat it as a further independent update.