Tom Dietterich defines safe systems: harms must stay below socially acceptable levels despite disturbances
tdietterich · x · 2026-09-23
AI safety researcher Thomas Dietterich, in a discussion with David Manheim and others, defines a safe system as one whose harms to people and infrastructure remain below a socially acceptable level. Citing Leveson's dynamic safety framework, he notes this must hold even under disturbances like budget cuts, staffing changes, and changing environments.
Related event: Alignment Community Debates Whether Dynamic Safety Equals AI Alignment(6 posts)→
More from AGI Musings
- 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
- Recursive bets on open-endedness: agents running massive parallel experiments like scientist communities — agihouse_org · 2026-11-12
- Recursive's Tim Shi maps recursive self-improvement: from learning data to discovering architectures — agihouse_org · 2026-11-12