Yoav Goldberg: interpretability that serves steering is just steering research with a handicap
yoavgo · x · 2026-08-26
Yoav Goldberg argues sharply: if the goal of interpretability research is steering, and interpretability methods are judged by how well they improve steering, then it is no longer interpretability research — it is steering research with a useless handicap (using interp methods). He can agree that "interpretability should be causal," but says "actionable" implies we care about the effect itself, not the explanation.
More from Research
- Schmidt Sciences awards $10M to 19 AI humanities research teams — OdedRechavi · 2026-10-15
- Mistral and CERN partner to build a Large Physics Model trained on billions of simulated collisions — MistralAI · 2026-10-15
- Global Transport coupling lifts guided flow generation: ImageNet FID 2.06 to 1.91 — mmbronstein · 2026-10-15
- Your breathing gives you away: Wi-Fi signals can reveal your breath rhythm — TinfoilTricorn · 2026-10-15
- Beyond text correlation: attaching a geometry simulator to ground model reasoning — gerardsans · 2026-10-15
- Sequen CEO Zoe Weil: Ranking Models Should Optimize Purchases, Not Clicks — TWIML AI Podcast · 2026-10-15