News for hackers. Stuff that matters.

A comment on GPT-4o's Memory Breakthrough (Needle in a Needlestack). Parent comment

Re:GPT-4o's Memory Breakthrough (Needle in a Needlestack) by sftombu on Tuesday May 14, 2024 @04:50PM (#40360005)
I had the same experience. With a 16k prompt, Turbo was nearly flawless. But it wasn't very good at 32k and not usable at 100+. You have to repeat information to get good results with longer prompts
[ Parent | on HN ]

There are no comments on this comment yet.