News for hackers. Stuff that matters.
Re:AI hype is built on high test scores. Those tests are flawed by dinosaurdynasty on Tuesday October 10, 2023 @07:15PM (#37838990)
LLMs are trained to predict text, and one of the results of this is the LLM has as many "faces" as exist in the training data, so it's going to be _very_ different depending on the prompt. It's not a consistent entity like a human. RLHF is an attempt to mediate this, but it doesn't work perfectly.

There are no comments on this comment yet.