News for hackers. Stuff that matters.

A comment on GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is shockingly good at search. Parent comment

Re:GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is sho... by simonw on Monday September 08, 2025 @04:01AM (#45165703)
Better source validation is one of the main reasons I'm excited about GPT-5 Thinking for this. It would be interesting to try your Gemini prompts against that and see how the results compare.
[ Parent | on HN ]
Re:GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is sho... by Hugsun on Monday September 08, 2025 @09:33AM (#45168060)
I've found GPT-5 Thinking to perform worse than o3 did in tasks of a similar nature. It makes more bad assumptions that de-rail the train of thought.
[ Parent | on HN ]
Re:GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is sho... by 3abiton on Monday September 08, 2025 @11:59PM (#45177235)
I think the key is prompting, and bound boxing assumptions.
[ Parent | on HN ]