Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Internal representations of LLMs encode information about truthfulness. Parent comment
Training data is the source of ground truth, if you mess that up that's kind of a you problem, not the model's fault.
There are no comments on this comment yet.
Training data is the source of ground truth, if you mess that up that's kind of a you problem, not the model's fault.