News for hackers. Stuff that matters.
Re:GPT-5o-mini hallucinates medical residency applicant grades by a-dub on Tuesday October 14, 2025 @11:48AM (#45581453)
> I still dislike the term "hallucinations". It comes across like the model did something wrong. It did not, as factually wrong outputs happen per design.

can you hear yourself? you are providing excuses for a computer system that produces erroneous output.

Re:GPT-5o-mini hallucinates medical residency applicant grades by nolok on Tuesday October 14, 2025 @11:53AM (#45581531)
No he does not.

He is not saying it's ok for this system to provides wrong answers, he is saying it's normal for informations from LLM to not be reliable and thus the issue is not coming from the LLM, but from the way it is being used.

Re:GPT-5o-mini hallucinates medical residency applicant grades by asperous on Tuesday October 14, 2025 @11:51AM (#45581494)
It's more like pointing out that a machine that runs at 1000c occasionally catches fire.
Re:GPT-5o-mini hallucinates medical residency applicant grades by random9749832 on Tuesday October 14, 2025 @02:23PM (#45583139)
We are in the late stage of the hype cycle for LLMs where the comments are becoming progressively ridiculous like for cryptocoins before the market crashed. The other day a user posted that LLMs are the new transistors or electricity.