News for hackers. Stuff that matters.

A comment on Evaluating 55 LLMs with GPT-4.

Re:Evaluating 55 LLMs with GPT-4 by crashocaster on Sunday October 08, 2023 @06:37PM (#37815051)
I always find evals of this flavor offputting given that 3.5 and 4 likely share preference models (or at least feedback data)
[ Parent | on HN ]

There are no comments on this comment yet.