(dynomight.substack.com)

688 points crescit_eundo | 2 comments | 14 Nov 24 17:05 UTC | HN request time: 0s | source

1. dr_dshiv ◴[15 Nov 24 09:16 UTC] No.42145196[source]▶

Has anyone tested a vision model? Seems like they might be better

replies(1): >>42149734 #

2. bongodongobob ◴[15 Nov 24 18:53 UTC] No.42149734[source]▶

I've tried with GPT, it's unable to accurately interpret the board state.

Something weird is happening with LLMs and chess