Comment by HarHarVeryFunny

3 days ago

It basically has been ever since they started using RLVR for reasoning (esp. coding & math), with the DeepSeek-R1 paper being what let the cat out of the bag.

The Gemini 3.7 Flash model released yesterday, and all the 3.x Flash models, are still based on the Gemini 3 pre-training run from January 2025 !!