←back to thread

Reasoning models reason well, until they don't

(arxiv.org)
214 points optimalsolver | 1 comments | 31 Oct 25 09:23 UTC | HN request time: 0.219s | source
Show context
equinox_nl ◴[31 Oct 25 09:48 UTC] No.45770131[source]▶
But I also fail catastrophically once a reasoning problem exceeds modest complexity.
replies(4): >>45770215 #>>45770281 #>>45770402 #>>45770506 #
davidhs ◴[31 Oct 25 10:09 UTC] No.45770281[source]▶
Do you? Don't you just halt and say this is too complex?
replies(3): >>45770311 #>>45770398 #>>45770868 #
dspillett ◴[31 Oct 25 10:25 UTC] No.45770398[source]▶
Some would consider that to be failing catastrophically. The task is certainly failed.
replies(3): >>45770566 #>>45770851 #>>45770961 #
1. LunaSea ◴[31 Oct 25 11:46 UTC] No.45770961[source]▶
I would consider that detecting your own limits when trying to solve a problem is preferable to having the illusion of thinking that your solution is working and correct.