News for hackers. Stuff that matters.
Re:LLMs trained on “A is B” fail to learn “B is A” by doctor_eval on Saturday September 23, 2023 @07:56AM (#37622462)
> It plays games with words to make plausible-sounding English text, but any statements made in it are liable to be false

Unfortunately, I’ve met several humans to which this statement would also apply.

There are no comments on this comment yet.