Gemini 3.0 spotted in the wild through A/B testing

Re:Gemini 3.0 spotted in the wild through A/B testing by SkyPuncher on Thursday October 16, 2025 @02:16PM (#45608837)

Gemini is theoretically better, but I find it's very unsteerable. Combine that with the fact it struggles with tool use and character-level issues - and it can be challenging to use despite being "smarter".

[ Parent | on HN ]

Re:Gemini 3.0 spotted in the wild through A/B testing by jmkni on Thursday October 16, 2025 @02:26PM (#45608932)

I agree with the steerable angle, it's like driving a fast car with no traction control

However if you get the hang of it, it can be very powerful

[ Parent | on HN ]

Re:Gemini 3.0 spotted in the wild through A/B testing by bee_rider on Thursday October 16, 2025 @02:27PM (#45608944)

What does it mean for one model to be theoretically better than another?

[ Parent | on HN ]

Re:Gemini 3.0 spotted in the wild through A/B testing by nutjob2 on Thursday October 16, 2025 @05:08PM (#45610677)

In this context it's idiomatic speech. It means that it would be otherwise be better if it were not for some practical issue stopping that from happening.

[ Parent | on HN ]

Re:Gemini 3.0 spotted in the wild through A/B testing by bee_rider on Friday October 17, 2025 @12:54AM (#45613414)

I think you are right.

It is just funny to think about—LLMs are sometimes viewed big piles of linear algebra, it would not be that surprising to hear that somebody had worked out that one model was somehow a subset of another (or something along those lines) and then claim some theoretical superiority.

[ Parent | on HN ]