News for hackers. Stuff that matters.
Re:OpenAI postmortem – Unexpected responses from ChatGPT by throwuwu on Thursday February 22, 2024 @01:37PM (#39471205)
Original sources aren’t necessarily infallible either, but that’s beside the point, asking ChatGPT needs to be viewed as asking a person to recount something from memory. It hasn’t been reviewed or edited so it’s like a first draft rather than a published document. That’s the error that people tend to make since they treat it like a search engine instead of a conversation.
Re:OpenAI postmortem – Unexpected responses from ChatGPT by nottorp on Thursday February 22, 2024 @02:21PM (#39471736)
> they treat it like a search engine instead of a conversation.

That's because web searches are so polluted that for a lot of purposes even ChatGPT 3.5 is better.