AI Agents 101: 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝗠𝗲𝗺𝗼𝗿𝘆. In general, the memory for an agent is something that we provide via context in the prompt passed to LLM that helps the agent to better plan and react given past interactions or data not immediately available. It is useful to group

Introducing our AI co-scientist, a multi-agent AI system built with Gemini 2.0. We think of it as a virtual collaborator for scientists, using advanced reasoning to synthesize a huge amount of literature, generate novel hypotheses, and suggest detailed research plans. We’re

Accelerating science and discovery is one of the most profound applications of AI and I’m really excited to see where this research will go. More details here: research.google/blog/accelerat…

After 6+ months in the making and burning over a year of GPU compute time, we're super excited to finally release the "Ultra-Scale Playbook" Check it out here: hf.co/spaces/nanotro… A free, open-source, book to learn everything about 5D parallelism, ZeRO, fast CUDA kernels,

Whoah…this is a huge breakthrough in quantum. PQC is now more urgent than ever.

Introducing Claude 3.7 Sonnet. Our most intelligent model to date and the first generally available hybrid reasoning model in the world.

Don’t look up. At this point it’s impossible NOT to see this coming, and much sooner than most people suspect.

Almost to the point where AI can be your technical co-founder

Gemma 3 is here! Our new open models are incredibly efficient - the largest 27B model runs on just one H100 GPU. You'd need at least 10x the compute to get similar performance from other models ⬇️

Phi…

We've just shipped a new feature in Claude Code: extended thinking. You can simply ask Claude to “think”, “think more”, or “think harder” and it’ll show its extended thinking process. This is all powered by our hybrid reasoning model, Claude 3.7 Sonnet.

Vim mode! Great feature add.

Was inevitable

“One day” is up there too

First coding test was impressive. Appreciate the model being transparent about the complexity of the ask and not overpromising what it can deliver. Vibe coding can be fun but for real production projects you need a model that is pragmatic and self-aware of its own limitations.

😂

I love to hear these stories behind the stories - there are always hidden heroes in the shadows that deserve some of the spotlight

Can’t wait to hear what the dolphins have to say

o3 and o4-mini are super good at coding, so we are releasing a new product, Codex CLI, to make them easier to use. this is a coding agent that runs on your computer. it is fully open source and available today; we expect it to rapidly improve.

Honestly Katie Ledecky swimming with a glass of chocolate milk perfectly balanced on her head might be more mind blowing than winning seven Olympic golds…