Thinking Machines Launches Inkling 2 Small: 594B MoE, Apache 2.0 Weights Next Week
geoffwolfe · x · 2026-11-09
Thinking Machines Lab introduced Inkling 2 Small, a Mixture-of-Experts model with 594B total parameters (17B active), image input support, and variable effort. It scores 31 on the Artificial Analysis Intelligence Index, far surpassing the company's first generation, driven by more efficient pre-training and a large unified RL run.
- Trained across multiple coding harnesses with long-history compression strategies; some tasks grade how the model worked, not just whether code passed tests — "train for the conditions of extended work, not only its final output"
- Demos include a from-scratch Three.js city simulator with fully procedural buildings/textures/cars, and a Python PC emulator that boots a real Linux kernel in the browser
- Available now via Tinker with closed weights; full weights planned under Apache 2.0 next week after external safety testing and red-teaming
More from coding & agent
- Day 21 of an agent a day: a TPP monitor agent for drug discovery, sample prompt included — nlarusstone · 2026-11-09
- Applying the bitter lesson to my LLM workflow: skip agents, just talk to the model — esrtweet · 2026-11-09
- Apple engineers' recap for local AI builders: skip AFM for coding, one-line model swapping — rxwei · 2026-11-09
- copy-clip: a copy button that folds your code into paper and clips it, built with vanilla JS — prasenx · 2026-11-09
- Dev finds sanity in talking to just one agent, one chat at a time — teodorio · 2026-11-09
- Relevant Isn't Authoritative: Why Agents Retrieve Right Docs and Still Decide Wrong — krishnan · 2026-11-09