logoalt Hacker News

pixl97yesterday at 8:07 PM1 replyview on HN

Based on the propensity for models to love their own words, a different model to check might be a good idea.


Replies

qarl2yesterday at 11:10 PM

Naw. The more verbose ones are more argumentative. They'll go at each other. It's a misconception that the same model will agree with itself.