News for hackers. Stuff that matters.

A comment on Stanford benchmarks and compares numerous Large Language Models. Parent comment

Re:Stanford benchmarks and compares numerous Large Language ... by xiphias2 on Sunday April 09, 2023 @09:48PM (#35508353)
One of OpenAI's engineers / cofounders (Greg Brockman) specifically said it in an interview that GPT-4 itself is quite calibrated, it goes away with the fine tuning process (I don't remember exactly which part of the interview). Of course they are working on fixing it, I guess GPT-4.5 will contain the fix.

https://www.youtube.com/watch?v=YtJEfTTD_Y4

[ Parent | on HN ]

There are no comments on this comment yet.