Not gonna lie, Gemini 3,1 Flash Live sounds really cool! https://t.co/fTXGJvm1v9 pic.twitter.com/uTQa0MM87s
— Chubby♨️ (@kimmonismus) 26 mars 2026
Not gonna lie, Gemini 3,1 Flash Live sounds really cool!

By
–
Not gonna lie, Gemini 3,1 Flash Live sounds really cool! https://t.co/fTXGJvm1v9 pic.twitter.com/uTQa0MM87s
— Chubby♨️ (@kimmonismus) 26 mars 2026
Not gonna lie, Gemini 3,1 Flash Live sounds really cool!

By
–
Google just launched Gemini 3.1 Flash Live, a new realtime model built for voice and vision agents. After a year of work on model quality, infrastructure, and UX, they're calling it a step-function improvement in quality, reliability, and latency. The race to build the best
By
–
Knowledge cutoff is a thing. It will be in every model in the future, forever. So we good 🙂
By
–
The specialization angle is interesting. I wonder if this changes fast with each model update or if it's a more fundamental architectural difference.

By
–

Introducing Gemini 3.1 Flash Live, our new realtime model to build voice and vision agents!! We have spent more than a year improving the model + infra + experience, the results? A step function improvement in quality, reliability, and latency.
→ View original post on X — @officiallogank, 2026-03-26 15:19 UTC
By
–
Congrats on the Nature publication! The fact that V1 was built before reasoning models even existed makes the potential of V2 with current models pretty incredible.

By
–
This open-source repo turns Claude Code into a full game dev studio. It's called Claude Code Game Studios. Building a game solo with AI doesn't stop you from making bad decisions early. > Hardcoding magic numbers
> Skipping design docs
> Writing spaghetti code This repo
By
–
94K views on a China AI deep dive, people are hungry for real on-the-ground insights. Would love to hear more about the open-source model ecosystem there specifically.
By
–
50% token reduction for agents is huge if it holds up in real production workloads. I wonder how this generalizes beyond their benchmarks.

By
–
BREAKING : Mistral AI is reportedly releasing Voxtral TTS today, a new 3B params open-source model that outperforms ElevenLabs V2.5 Flash. It has not been announced yet, but it seems like it can already be accessed on Mistral Playground with sample voices and voice cloning!