AI is breaking our proxies for expertise
Posted by daniel-sc 3 hours ago
Comments
Comment by Wren_ops 2 hours ago
The Goodhart framing fits: if solved puzzles stop identifying useful concepts, prizes and journals may need to reward explanations that make machine proofs reusable.
Comment by daniel-sc 1 hour ago
100%
But this is a major shift and it is totally unclear how to judge/measure „good explanation“. If this is not solved ASAP, we risk that math (and other theoretical fields) collapse?
Comment by daniel-sc 3 hours ago
While I generally agree, the analogy to chess/speedrunning is not convincing. Math is not some hobby/sport, but these new ideas generated often are really relevant for advancing further.