logoalt Hacker News

tptacektoday at 1:06 AM2 repliesview on HN

I've always sort of assumed the models were just making sympy scripts behind the scenes.


Replies

currymjtoday at 1:46 AM

sometimes you can see them do this and sometimes you can see they just work through the problem in the reasoning tokens without invoking python.

cyanydeeztoday at 1:14 AM

Wheres Godel when you need him. A lot of this stuff is symbol shunting, which LLMs should be really good at.