News for hackers. Stuff that matters.
Re:Markov chains are funnier than LLMs by beeboobaa3 on Monday August 19, 2024 @11:28AM (#41291858)
I would have expected the people who trained these systems to not format their Q/A samples to sound authoritatively while they knew the system was going to be spouting nonsense.

There are no comments on this comment yet.