Sam Heutmaker

15.6× faster decoding at 1M tokens 🔥 Thanks @FireworksAI_HQ for powering the inference behind M3. Try it now 👇

RT @AndreaPN: A real demo vibe coding using @opencode + OpenCAP Gateway ( inference tokens from $CAPU ) + @MiniMax_AI M3 , implement a smal…

Using open models and inference clouds (which serve open models) is a leading indicator of what is to come. The advantage of open weights is that you can train, serve, and continually improve your own model. You get control over cost, quality, latency, deployment options, etc. It's just a matter o

NEW: GitHub repo “Chipotlai Max” claims to exploit Chipotle’s Pepper support bot to provide free AI coding inference.

RT @alexatallah: The Big Crunch is here. Companies are realizing: - their inference bill grew 10x in the last few months - another 10x gro…

The Pareto Router is now processing almost 1B tokens per day: https://openrouter.ai/openrouter/pareto-code The Auto Router is processing 12B: https://openrouter.ai/openrouter/auto See the @theinformation's article below 👇 https://x.com/jjacky/status/2061867569775026435

inference capital markets on base collectibles capital markets on solana https://x.com/solana/status/2061851838966816988

👀- I think this means free inference for Trenchor Devs. Will speak with the Virtuals team to clarify! https://x.com/virtuals_io/status/2061842004829786311

AI Runs On Compute. Ethereum Coordinates Value. AI and Ethereum are solving very different problems, but they are starting to intersect more often. AI requires massive compute infrastructure to train models and run inference at scale. Ethereum provides infrastructure for programmable payments, dig

inference $DIEM goes in. trust comes out. that's the entire antfleet thesis.