News for hackers. Stuff that matters.

A comment on GPT-4. Parent comment

Re:GPT-4 by anonymouskimmer on Tuesday March 14, 2023 @09:50PM (#35162646)
> Both can be technically be modeled with a lookup table, but for Othello that table would be size 3^63.

Could you just generate the subset you need denovo each time? Or the far smaller number of 1-dimensional lines?

[ Parent | on HN ]
Re:GPT-4 by nottathrowaway3 on Tuesday March 14, 2023 @10:12PM (#35162827)
Then there becomes a "material" difference between Othello and those LL(1) grammars as grandparent comment suggested there wasn't.

I would argue the optimal compression for such a table is a representation of the geometric algorithm of determining move validity that all humans use intuitively, and speculate that any other compression algorithm below size say 1MB necessarily could be reduced to the geometric one.

[ Parent | on HN ]