News for hackers. Stuff that matters.

A comment on Gemini 3.0 spotted in the wild through A/B testing. Parent comment

Re:Gemini 3.0 spotted in the wild through A/B testing by coffeeaddict1 on Thursday October 16, 2025 @06:50PM (#45611637)
My experience with complex reasoning is that Gemini 2.5 Pro hallucinates way too much and it's far below gpt 5 thinking. And for some reason it seems that it's gotten worse over time.
[ Parent | on HN ]

There are no comments on this comment yet.