News for hackers. Stuff that matters.
Re:GPT-4o's Memory Breakthrough (Needle in a Needlestack) by rguptill on Tuesday May 14, 2024 @04:58PM (#40360087)
We also need a way to determine where a given response fits in the universe of responses - is it an “average” answer or a really good one
Re:GPT-4o's Memory Breakthrough (Needle in a Needlestack) by edmara on Wednesday May 15, 2024 @07:58AM (#40365725)
If you have an evaluation function which does this accurately and generalizes, you pretty much already have have AGI.