OK, I can partly explain the LLM chess weirdness now(dynomight.net)
467 points by dmazin | 419 comments
Dynomight blog post following up on why gpt-3.5-turbo-instruct plays chess well while other LLMs play poorly, testing several theories.
#gpt-3-5-turbo-instruct on Hacker News
1 story tagged gpt-3-5-turbo-instruct, newest first.