The Future of Mech Interp: Abstracting Learned Algorithms From Circuits
burny_tech · x · 2026-11-20
A forwarded take on mech interp's future: abstract functional mechanisms from their particular instantiations—we're in search of learned algorithms, not merely the circuits that implement them.
More from Research
- Google's Willow wins 'impossible' magic square game 98.3% of the time, on Science cover — sundarpichai · 2026-11-20
- Yilun Du and Dai Bo release EBM tutorial unifying diffusion, RL, and test-time reasoning — burny_tech · 2026-11-20
- MiniMind: train a 64M-param LLM from scratch in 2 hours on one RTX 3090 — dr_cintas · 2026-11-20
- 1,900 AI-for-science papers in a week: why a small test error proves almost nothing — bravo_abad · 2026-11-20
- MBZUAI's PAN 2 World Model: 29B Params, Fully Open with Weights, Inference and Training Code — ZhitingHu · 2026-11-20
- LLMs show transferable goal encodings: a Python plan replanted into C++ gets re-implemented — paul_cal · 2026-11-20