Gemini 3 Deep Think

Re:Gemini 3 Deep Think by kaveh_h on Thursday February 12, 2026 @11:34PM (#46998966)

Have you tried providing multiple pages at a time to the model? It might do better transcription as it have bigger context to work with.

[ Parent | on HN ]

Re:Gemini 3 Deep Think by netdur on Friday February 13, 2026 @03:32AM (#47000379)

Gemini 3 long context is not good as Gemini 2.5

[ Parent | on HN ]

Re:Gemini 3 Deep Think by ody4242 on Friday February 13, 2026 @08:30AM (#47002481)

I'm 100% sure that all providers are playing with the quantization, kv cache and other parameters of the models to be able to serve the demand. One of the biggest advantage of running a local model is that you get predictable behavior.

[ Parent | on HN ]