Interpretability 'revolutions' are rarer than social media makes them seem
tallinzen · x · 2026-11-04
tallinzen advises skepticism toward blog posts claiming interpretability (or any field) has been revolutionized: wait for trusted researchers to verify before believing the hype — revolutions happen, but less often than social media suggests. He recommends following ravfogel, NeelNanda5 and ChrisGPotts as trusted sources.
More from AGI Musings
- Sharing agent sessions across a team breaks knowledge silos — and AI can summarize your teammates' workflows — steipete · 2026-11-04
- Apple's annual filing warns rogue AI agents could 'conceal' and 'manipulate,' threatening its business — jeremyakahn · 2026-11-04
- Looking back at vibe-coded projects from 6-8 months ago, most are already obsolete — DeryaTR_ · 2026-11-04
- 'AI 2027' Resurfaces: Automation of Top Research Teams by Early 2027? — cephaloform · 2026-11-04
- Deutsch critic: his strongest adherents kept missing AI progress for 4 years — NathanpmYoung · 2026-11-04
- A proposal for "Partially-Selfish Nonprofits" that let founders keep 1% of donations — AaronBergman18 · 2026-11-04