OK, I can partly explain the LLM chess weirdness now(dynomight.net)

467 points by dmazin 1 year ago | 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.

Something weird is happening with LLMs and chess(dynomight.substack.com)

626 points by crescit_eundo 1 year ago | 424 comments

A Dynomight newsletter post examining how well large language models play chess and why results vary strangely across models.

DumPy: NumPy except it's OK if you're dum(dynomight.net)

112 points by RebelPotato 1 year ago | 36 comments

Can large language models reason?(arnaldur.be)

4 points by Hugsun 2 years ago | 0 comments

Manipulating Chess-GPT's World Model(adamkarvonen.github.io)

110 points by seraine 2 years ago | 31 comments

I don't like NumPy(dynomight.net)

399 points by MinimalAction 1 year ago | 164 comments

A Dynomight blog essay critiquing NumPy's design, arguing its array broadcasting and indexing make complex computations confusing.