DoM steering working at a localized layer doesn't prove localization is correct
johnhewtt · x · 2026-10-27
In a reply to arunasank, johnhewtt argues that a localization method might be wrong and the DoM activation-steering approach might also be wrong — so DoM working better at the layer chosen by localization doesn't validate either. The exchange continues the debate around his blog post on separating forms from estimators in interpretability, weighing localization+steering against fine-tuning (interpretable but effective vs. opaque).
Related event: Interpretability debate: steer by difference of means or by gradients?(6 posts)→
More from Research
- Kevin Bryan: maximizing raw accuracy is rarely the right way to train AI assistants — Afinetheorem · 2026-10-27
- Szegedy: a flaw in common training losses went unnoticed for over a decade — ChrSzegedy · 2026-10-27
- Claude research model claims to refute Exponential Time Hypothesis with 14M-token autonomous run — scaling01 · 2026-10-27
- "ETH is false": CS community buzzing over claim that upends SAT exponential-time assumption — akbirthko · 2026-10-27
- RL environments essay: knowing how to operate software isn't knowing how to achieve goals — ShenRaphael · 2026-10-27
- Δτ-Bench: Agents Face a Moving Tool Frontier, Best Model Scores Just 42.3% — UniversityCollegeLondon · 2026-10-27