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
2,470 posts
Baseten
@baseten
Inference is everything.
- "That's when they come to open-source models, that's when they come to Baseten, that's when they come to post-train models on Baseten, to be able to do it better, faster, and cheaper. That's when you get both intelligence everywhere and unit economics that make sense for yourThanks to @EdLudlow for having us on Bloomberg Tech yesterday to talk about our latest fundraise and the growing number of companies owning their open and specialized models.
00:00 - Excited to be a day 0 launch partner for BioNeMo, NVIDIA's new, fully-open agent toolkit for scientific workflows! All 10 BioNeMo NIMs are available in our model library. Learn more in our announcement: baseten.co/blog/nvidia-bi…
00:35Science is entering a new era - one where AI agents can do scientific work. 🧬 Today NVIDIA is launching the BioNeMo Agent Toolkit - an open, agent-ready toolkit that gives any AI agent callable tools for protein structure prediction, molecular docking, generative chemistry, - Baseten reposted
Tutorial on how to use GLM-5.2 in Claude Code (bookmark this) ~4.5x faster & ~5x cheaper compared to Opus 4.8! 1. Install the latest Claude Code npm install -g @Anthropic-ai/claude-code 2. Create an account at baseten.co. 3. Grab an API Key from
- Baseten reposted
We have the fastest GLM-5.2 deployment on the market: >280 tok/s and <0.8s ttft, according to Artificial Analysis. This same performance carries across all post-trained variants. These aren’t vanity metrics. Optimizations like these save our customers tens of millions of dollars
We closed our Series F today at a $13B valuation. Our inference business grew 20x in the last year. I want to explain why: The growth comes from a shift I think is permanent: companies want to own their intelligence layer. Instead of relying exclusively on closed models, teams - Baseten reposted
The GLM moment is going to be bigger than the DeepSeek moment. Baseten has the fastest inference on the best open-weight model. >280 tps and <0.8 ttft.
- The best open model with the best performance: GLM-5.2 runs at >280 TPS and <0.8s TTFT on Baseten. Try it here: baseten.co/library/glm-52/
00:00 - Baseten reposted
Our co-founder and CPO @thatsjonsense is speaking on June 25th on "How to Choose a Model" alongside @sarahmsachs @oneill_c @baseten @NotionHQ. RSVP in thread!
- We’re excited to announce our $1.5B Series F. Baseten exists to help companies own their intelligence and run AI products in production with speed, reliability, and control. As we enter this next chapter, three things are clear: 1. Customers like Abridge, Clay, Cursor, Decagon,
- Baseten reposted
@baseten model performance team is absolutely cracked. @Zai_org GLM 5.2 is now 4x faster running at full 1M context! Already available to use in your favorite coding harnesses, here it is COOKING in @FactoryAI Droid and @opencode Docs for how to get it in comments
00:00 - Baseten reposted
@baseten model performance team is absolutely cracked. @Zai_org GLM 5.2 is now 4x faster running at full 1M context! Already available to use in your favorite coding harnesses, here it is COOKING in @FactoryAI Droid and @opencode Docs for how to get it in comments00:00 - Most supervised fine-tuning (SFT) studies run on generic data. Ours run on production tasks, paired with evals our team spends weeks building. New post-training research from our team here.1/ We fine-tune a lot of customer models, so we decided to systematically try and figure out some best practices for finetuning. SFT isn't sexy, but it's still important. We vary one SFT lever at a time across 2 model families, dense + MoE to 235B, on 4 real-world customer
