generativist revisits Chris Olah's info theory post and the Explainability Gap
generativist · x · 2026-10-04
Researcher generativist revisits Chris Olah's classic information theory blog post, calling it and his mechinterp work still beautiful. Reading it against how he'd otherwise learned the topic was, he says, the first time he saw the "Explainability Gap" in high resolution.
More from Research
- EurekaBench: GPT-6 Astra nearly matches humans on prediction but lags on scientific insights — geoffwolfe · 2026-10-04
- KL divergence in exponential families amounts to a Bregman divergence — FrnkNlsn · 2026-10-04
- NeuroAgent passes NeuroAI Turing test on zebrafish whole-brain data — aran_nayebi · 2026-10-04
- UT Dallas Robotics Lab Pivots From Perception to Generalizable Manipulation Learning — YuXiang_IRVL · 2026-10-04
- BOSSFIGHT benchmark: GPT-6.1 Sol scores 67 running a coffee shop, but lays off the harassment complainant — LordKittyPanther · 2026-10-04
- Jev model goes viral as NUS ConfTuner paper backs the same probability-calibration route — 机器之心 · 2026-10-04