News for hackers. Stuff that matters.
Re:GPT-4o's Memory Breakthrough (Needle in a Needlestack) by carlosbaraza on Wednesday May 15, 2024 @05:46AM (#40364869)
I have the same feeling. I asked to find duplicates in a list of 6k items and it basically hallucinated the entire answer multiple times. Some times it finds some, but it interlaces the duplicates with other hallucinated items. I wasn't expecting it to get it right, cause I think this task is challenging with a fixed amount of attention heads. However, the answer seems much worse than Claude Opus or GPT-4.
Re:GPT-4o's Memory Breakthrough (Needle in a Needlestack) by akomtu on Wednesday May 15, 2024 @06:24PM (#40373154)
Everyone is trying to use Language Models as Reasoning Models because the latter haven't been invented yet.