Just like us at @thinkymachines
, @luke_drago_ @LRudL_ care a lot about amplifying humans, not replacing them.
They're joining us to build towards that future!
@soumithchintala
-
Amplifying Humans: Thinky Machines Partners Join Mission
By
–
-
Chroma Context-1: Efficient 20B Search Agent with SoTA Performance
By
–
Great work by Chroma training a search agent with SoTA efficiency. Lots of cool details: a prune tool for editing context mid-search, a synthetic data pipeline with verification steps, and a curriculum that shifts from recall to precision. Trained with Tinker! https://t.co/csp0FoXCtH
— John Schulman (@johnschulman2) 26 mars 2026Great work by Chroma training a search agent with SoTA efficiency. Lots of cool details: a prune tool for editing context mid-search, a synthetic data pipeline with verification steps, and a curriculum that shifts from recall to precision. Trained with Tinker! Chroma (@trychroma) Introducing Chroma Context-1, a 20B parameter search agent. > pushes the pareto frontier of agentic search > order of magnitude faster > order of magnitude cheaper > Apache 2.0, open-source — https://nitter.net/trychroma/status/2037243681988894950#m
→ View original post on X — @soumithchintala, 2026-03-26 20:09 UTC
-
Optimal Intellect Introduces Moreau GPU-Native Solver
By
–
We're Optimal Intellect, a research lab from the team behind CVXPY. Today we're introducing Moreau: a GPU-native solver that's orders of magnitude faster than the best existing tools.
→ View original post on X — @soumithchintala, 2026-03-24 16:48 UTC
-
OpenReward: 330+ RL Environments Through Single API
By
–
Introducing OpenReward. 🌍 330+ RL environments through one API ⚡ Autoscaled sandbox compute 🍒 4.5M+ unique RL tasks 🚂 Works like magic with Tinker, Miles, Slime Link and thread below.
→ View original post on X — @soumithchintala, 2026-03-24 12:00 UTC
-
Nemotron 3 Nano and Super Now Available on Tinker with GTC Discount
By
–
Nemotron 3 Nano and Super from @nvidia are now available on Tinker! We're offering a limited-time GTC 50% discount for both. The Nemotron family features open hybrid MoE models optimized for compute efficiency for agentic applications.
→ View original post on X — @soumithchintala, 2026-03-18 18:16 UTC
-
Tech boss uses AI to create cancer vaccine for dying dog
By
–
This is wild. theaustralian.com.au/busines…
→ View original post on X — @soumithchintala, 2026-03-14 05:54 UTC
-
Soumith Celebrates Continued Partnership with NVIDIA and PyTorch
By
–
to me personally, this continues the years of close partnership with NVIDIA I've had via @PyTorch. working with them is always such a joy!
→ View original post on X — @soumithchintala, 2026-03-10 13:52 UTC
-
Meta partners with NVIDIA for 1GW compute infrastructure and AI systems
By
–
Excited to partner with NVIDIA. bringing up 1GW or more of compute starting with Vera Rubin, co-designing systems and architectures together, and more. NVIDIA has also made a significant investment in @thinkymachines Thinking Machines (@thinkymachines) We are partnering with @nvidia to power our frontier model training and platforms delivering customizable AI. thinkingmachines.ai/news/nvi… — https://nitter.net/thinkymachines/status/2031356627916603876#m
→ View original post on X — @soumithchintala, 2026-03-10 13:51 UTC
-
Qwen 3.5 Now Available on Tinker Platform
By
–
Qwen 3.5 is🔥, and now it's available on 🚀! Tinker (@tinkerapi) Four Qwen 3.5 models from @Alibaba_Qwen are now live on Tinker. Qwen 3.5 introduces hybrid linear attention that enables long context windows, as well as native vision input. — https://nitter.net/tinkerapi/status/2030028446588661891#m
→ View original post on X — @soumithchintala, 2026-03-06 22:29 UTC
-
KernelAgent integrates GPU performance signals for Triton kernel optimization
By
–
Building on the previous correctness-focused pipeline, KernelAgent can now integrate GPU hardware-performance signals into a closed-loop multi-agent workflow to guide the optimization for Triton Kernels. Learn more: hubs.la/Q045Wsqq0 @KaimingCheng @marksaroufim
→ View original post on X — @soumithchintala, 2026-03-06 20:09 UTC