News for hackers. Stuff that matters.

A comment on GPTs and Hallucination. Parent comment

Re:GPTs and Hallucination by eschneider on Tuesday September 10, 2024 @02:32PM (#41504036)
Don't anthropomorphize LLMs. They hate that.

And it's not even a question of LLMs getting answers "wrong". It's just generating associated text. It has no concept of right or wrong answers.

[ Parent | on HN ]
Re:GPTs and Hallucination by baxtr on Tuesday September 10, 2024 @02:57PM (#41504261)
I think it’s totally fine to am LLMs. In the end they have been trained on human input.
[ Parent | on HN ]