Hey-Meadow/meadow-mind

Zero training, second-level reactions (~400ms). A language-rule decision mind on a local 7B diffusion LM.

3 best points · 0 comments · 1 Hacker News post · 5 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Meadow Mind – a 7B diffusion LLM plays Gym games with zero training (3 points, 0 comments, by akaiHuang, 2026-06-10)