Nobody knows how to align superhuman models, and safety is far behind capability
MatthewJBar · x · 2026-11-11
Matthew Burt restates the field's dominant position: safety progress is extremely far behind capability progress, a gap even lab leadership has publicly acknowledged. His core claim is blunt—nobody knows how to align superhuman models, or even current models.
He points to a 2024 FT chart by @soundboy that he believes still accurately captures the capability-safety gap. The thread drew a response from Marius Hobbhahn arguing we have a recipe for capability but not for robust safety.
Related event: Safety Researchers Say Alignment Lags Far Behind Capabilities(4 posts)→
More from AGI Musings
- Ethan Mollick: GTA 6 Will Be the Last AAA Game Built Without AI — emollick · 2026-11-11
- Air Street Capital founder: AI is 'a museum of the mind' preserving human know-how — nathanbenaich · 2026-11-11
- Researcher Warns Real-Time Video AI Companions Are the Next Teen-Safety Wave — anshulkundaje · 2026-11-11
- 800 HN 'wake me up when AI can' comments get 100,000 votes on whether the bars were cleared — ArtificialOther · 2026-11-11
- Why Anthropic's 2x capability gains won't translate to RSI: manual post-training and async autonomy — menhguin · 2026-11-11
- AI 2027 Authors: Superhuman AI Researcher by 2027, White-Collar Automation Before 2028 — rand_longevity · 2026-11-11