Richard Socher launches Flint: open-weights local coding model built in under 4 months
jeffclune · x · 2026-10-22
Richard Socher unveils Flint, the first model from Recursive AI, built from scratch in under 4 months by their automated research system, the Eureka Machine. It hits 125+ tokens/sec on a MacBook Pro and 150+ on RTX Spark—claimed up to 2x faster than comparable local coding models. Open weights are live on Hugging Face, runnable locally or free via opencode and pidotdev, pitching private, unmetered on-device intelligence. Socher says every model the system builds makes it better at building the next.
More from coding & agent
- Node.js ships security fixes across 22.x/24.x/26.x, worst bug allows RCE — dotey · 2026-10-22
- Research Progress Graph: modeling authentic research trajectories, 35 agents found incomplete — ZhiyuChen4 · 2026-10-22
- Longshot Studio 0.15 adds lip sync and face refinement, free on your own ComfyUI — R34vspec · 2026-10-22
- Dev builds Scratch-style MCP that feeds coding agents one task at a time to stop plan drift — NoTokenDev · 2026-10-22
- Frontier models spark a comeback of quirky game-style personal homepages — HamelHusain · 2026-10-22
- FOSS stack with DeepSeek beats paid ChatGPT plan in 2-month agent reliability test — layer4down · 2026-10-22