News for hackers. Stuff that matters.
Re:OpenAI postmortem – Unexpected responses from ChatGPT by inference-lord on Wednesday February 21, 2024 @09:24PM (#39462400)
I think what they mean is, the model was unable to recognize that "it" was having issues, so it's not self-aware in that sense.

We can all calm down a little, it's ok.

Re:OpenAI postmortem – Unexpected responses from ChatGPT by og_kalu on Thursday February 22, 2024 @08:23AM (#39466670)
There are examples of it recognizing there are issues in this very thread.

Not that people always recognize such issues anyway.