GPT-4o's Memory Breakthrough (Needle in a Needlestack)

Re:GPT-4o's Memory Breakthrough (Needle in a Needlestack) by theptip on Tuesday May 14, 2024 @09:56PM (#40362289)

I suppose the question then is - if you finetune on your own data (eg internal wiki) does it then retain the near-perfect recall?

Could be a simpler setup than RAG for slow-changing documentation, especially for read-heavy cases.

[ Parent | on HN ]

Re:GPT-4o's Memory Breakthrough (Needle in a Needlestack) by k__ on Wednesday May 15, 2024 @01:36AM (#40363431)

"if you finetune on your own data (eg internal wiki) does it then retain the near-perfect recall"

No, that's one of the primary reasons for RAG.

[ Parent | on HN ]

Re:GPT-4o's Memory Breakthrough (Needle in a Needlestack) by theptip on Wednesday May 15, 2024 @04:52PM (#40372227)

I think you are misunderstanding. This post is about new capabilities in GPT-4o. So the existing reasons for RAG may not hold for the new model.

Unless you have some evals showing that the previous results justifying RAG also apply to GPT-4o?

[ Parent | on HN ]