The first Gemini 2.0 Flash "Thinking Mode" model came out today. I've updated my llm-gemini plugin to support it and ran a few test prompts - it's a very interesting new entrant in the o1-inspired "inference scaling" category of models.
https://simonwillison.net/2024/Dec/19/gemini-thinking-mode/
The most impressive example I've seen so far involves vision input:
llm -m gemini-2.0-flash-thinking-exp-1219 \
-a http''s://storage.googleapis.com/generativeai-downloads/images/geometry.png \
"What's the area of the overlapping region?"