←back to thread

Reasoning models reason well, until they don't

(arxiv.org)
215 points optimalsolver | 2 comments | 31 Oct 25 09:23 UTC | HN request time: 0.554s | source
Show context
anal_reactor ◴[31 Oct 25 10:58 UTC] No.45770626[source]▶
I'm yet to see a task that AI fails at that bottom 10% of population wouldn't also fail at.
replies(7): >>45770767 #>>45770873 #>>45770898 #>>45770909 #>>45771143 #>>45771770 #>>45775668 #
1. TheOtherHobbes ◴[31 Oct 25 11:17 UTC] No.45770767[source]▶
How about keeping a conversation going with family over Thanksgiving? (Or local equivalent.)
replies(1): >>45771057 #
2. randomNumber7 ◴[31 Oct 25 11:58 UTC] No.45771057[source]▶
This is something where the top 10% sometimes horribly fail.