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
- OpenAI, Anthropic and DeepMind job posts signal PMs must write evals and code — aakashgupta · 2026-11-12
- Architecture study sparks monitoring concerns over a multi-hop planning spike — ChowdhuryNeil · 2026-11-12
- PowerShell creator Jeffrey Snover at Ignite: AI revolution is an extinction event for those who don't adapt — dfinke · 2026-11-12
- Worst AI use: signaling you don't care about things you should — Afinetheorem · 2026-11-12
- Stanford HAI blueprint: 56 US agencies report 3,611 AI use cases, evaluation lags — StanfordHAI · 2026-11-12
- Fleuret amplifies debate: AI can't slash wet-lab experiments in unmapped biology — francoisfleuret · 2026-11-12