Right. I think the mole generator is basically lack of continual learning and arbitrarily deep neural reasoning (which is different than eg CoT), and that it manifests itself most clearly in agency failures but also suggests something like limits of original thinking.
“The mole generator is basically X” seems somewhat at odds with the view Mateusz is expressing here, which seems more along the lines “LLM researchers are focusing on moles and ignoring where the moles are coming from” (the source of the moles being difficult to see).
The mole generator might be easy to see (or identify with relatively high certainty), but even if one knows the mole generator, addressing it might be very difficult.
Right. I think the mole generator is basically lack of continual learning and arbitrarily deep neural reasoning (which is different than eg CoT), and that it manifests itself most clearly in agency failures but also suggests something like limits of original thinking.
Alas, more totally unjustified “we just need X”. See https://www.lesswrong.com/posts/5tqFT3bcTekvico4d/do-confident-short-timelines-make-sense?commentId=NpT59esc92Zupu7Yq
I’m not saying that’s necessarily the last obstacle.
“The mole generator is basically X” seems somewhat at odds with the view Mateusz is expressing here, which seems more along the lines “LLM researchers are focusing on moles and ignoring where the moles are coming from” (the source of the moles being difficult to see).
The mole generator might be easy to see (or identify with relatively high certainty), but even if one knows the mole generator, addressing it might be very difficult.