this post was submitted on 14 Nov 2024
5 points (85.7% liked)
Hacker News
309 readers
313 users here now
RSS Feed of HackerNews
founded 3 months ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
My theory: 3.5-turbo-instruct is the only sentient one and it looks up the answer in a chess-specific solver every time to make sure it’s correct.