Pinned
Intelligence should be defined by the people closest to the work. Intelligence should be owned by all of us.
Let’s build a many model future!
Baseten
2,419 posts
Baseten
@baseten
Inference is everything.
- Kimi K2.7 Code is live on Baseten Model APIs. Kimi K2.7 Code has 30% lower reasoning-token usage compared to K2.6, with improved instruction following and higher end-to-end coding task success rates. Try it out: baseten.co/library/kimi-k…
- Baseten reposted
My full review of @philipkiely's Inference Engineering. TL;DR: I desperately wish I could ship this book back to myself in 2023. But you should read it today to avoid making the same mistakes I did! - We 💚 @cursor_ai, thanks for inviting some of our post-training experts to give chalk talks at Cursor Compile!Fantastic chalk talks today at @cursor_ai Compile conference from @ftrain , @b_geist , @_chenglou , @alsuhr , @mudithj , @oneill_c , @part_harry_ , and @thesephist Will we see more chalk talks at future tech conferences? It made me wonder what chalky topics I'd want to present.
- Big news from Boltz - our biggest update yet! 🚀 Today we’re releasing two new state-of-the-art models for protein and small molecule design with extensive wet lab validation and a new API to run all of our models on scalable GPUs wherever you (or your agents) work! 🔥
00:00 - GLM 5.2 is live on Baseten. 5.2 is built for agentic engineering: stronger coding, sharper agentic reasoning, and a long context window built to run hours-long tasks. Test it today: baseten.co/library/glm-52/
- Baseten reposted
Thinking of doing a little book club in Berlin. Who would be down? Looking for ~10 people IRL.
- Baseten reposted
AI advantage is shifting from raw model scale to deep integration with unique organizational data, workflows, and human expertise through continual learning loops. Ideally, this will result in distributed, defensible value rather than winner-take-all dynamics around general - The new AgentPerf benchmark by @ArtificialAnlys shows that @NVIDIAAI Blackwell delivers best performance for demanding agentic workloads. With NVIDIA, we're continuously investing in making your coding agents run fast, scale seamlessly, and cost less.
- We're thrilled to be working with the Harvey team to push open models to frontier-level performance for legal AI. Shout out to @gabepereyra for the great article. LAB was key to our joint work post-training open-weight models for legal agents.
- Congrats to the MiniMax team on the open-source launch of M3! There are very few <500bn parameter models that can tackle coding, agentic workloads, and multimodal all with a 1M-token context window but M3 does it all. Dig in here: baseten.co/library/minima…
