News for hackers. Stuff that matters.
Re:Passwords Are Fine by archargelod on Tuesday July 04, 2023 @08:24AM (#36585722)
> Hallucination is a separate problem, which is solved by using fine-tuned models.

They won't solve the main cause of hallucination: prompt has zero connection to generated text other than probability.

ChatGPT do not generate answers, it comes up with something that looks like an answer. There is a good chance it is the answer, but you can't guarantee it.

I believe this particular problem won't be solved, unless researchers teach machines how to reason. But then we would have greater concerns than hallucinations.

Re:Passwords Are Fine by yunohn on Tuesday July 04, 2023 @08:37AM (#36585843)
Yes, but pattern matching and probability will solve for the vast majority of usecases. Heck, it already works quite well and offers value.

I don’t need 100% truth, because reading multiple docs myself and piecing things together has tons of potential pitfalls too.