News for hackers. Stuff that matters.
Re:OpenAI researcher announced GPT-5 math breakthrough that ... by crazygringo on Sunday October 19, 2025 @02:48PM (#45636822)
I use all of the current versions of ChatGPT, Gemini, and Claude.

The hallucination rates are about the same as far as I can tell. It depends mostly on how niche the area is, not which model. They do seem to train on somewhat different sets of academic sources, so it's good to use them all.

I'm not talking about deep research or advanced thinking modes -- those are great for some tasks but don't really add anything when you're just looking for all the sources on a subject, as opposed to a research report.

Re:OpenAI researcher announced GPT-5 math breakthrough that ... by astrange on Monday October 20, 2025 @03:46PM (#45648352)
ChatGPT thinking mode is definitely the best search engine (wrapper) I've ever used, and you should be using it to find sources.