AI safety researchers debate whether "alignment" has become a useless term
davidmanheim · x · 2026-09-22
Safety researcher David Manheim argues that "alignment" has been unclear since 2018, is used inconsistently even among technical experts, and that any point made with it would be clearer in other words. His counterpart counters that RSI is understandable despite fuzzy boundaries, and that alignment remains indispensable in technical discussions—just not in general policy talk. Manheim replies that failing to distinguish system safety from alignment makes reasonable policy decisions about future systems impossible.
Related event: AI Safety Researchers Debate Whether "Alignment" Belongs in Policy Talks(4 posts)→
More from AGI Musings
- Biotech founder: AI gave me a 10-100x productivity boost in rare-disease drug design — zakkohane · 2026-09-23
- AI risk doesn't need EA's conceptual machinery, argues zetalyrae — austinc3301 · 2026-09-23
- The First Jobs AI May Kill Are the Ones People Need to Gain Experience — yi111 · 2026-09-23
- Browser-use agents are already AGI for white-collar work, argues indie dev — yihui_indie · 2026-09-23
- AI researcher: LLMs prove calculative deduction is limited, embrace intuitive reasoning — granawkins · 2026-09-23
- Anthropic researcher's three-bucket framework for doing science in the AI era — CatAstro_Piyush · 2026-09-23