←back to thread

Something weird is happening with LLMs and chess

(dynomight.substack.com)
688 points crescit_eundo | 1 comments | 14 Nov 24 17:05 UTC | HN request time: 0.213s | source
Show context
chvid ◴[15 Nov 24 05:55 UTC] No.42144283[source]▶
Theory 5: GPT-3.5-instruct plays chess by calling a traditional chess engine.
replies(5): >>42144296 #>>42144326 #>>42144379 #>>42144517 #>>42156924 #
1. golol ◴[15 Nov 24 06:57 UTC] No.42144517[source]▶
Sorry this is just consiracy theorizing. I've tried jt with GPT-3.5-instruct myself in the OpenAI playeground where the model clearly does nothing but auto-regression. No function calling there whatsoever.