Re:GPT-4o's Memory Breakthrough (Needle in a Needlestack)
by chrischen on Wednesday May 15, 2024 @03:55AM
(#40364214)
Arithmetic just happens to be something we can easily and reliably verify, so it becomes painfully obvious when LLMs are just stringing together some words that sound like the right answer.
Re:GPT-4o's Memory Breakthrough (Needle in a Needlestack)
by bckr on Wednesday May 15, 2024 @06:58AM
(#40365245)
It used web search (RAG over the entire web) and analysis (math tool) and still came up with the wrong answer.
It has done more complex things for me than this and, sometimes, gotten it right.
Yes, itβs supposed to be able to do this.
Also: would you expect random people to fare any better?