Miles Brundage says AI safety needs concrete models of the worst-case failures
Miles_Brundage · x · 2026-07-29
Miles Brundage says the field needs to “build” a concrete mental model of the bad outcomes it wants to prevent, and the attached image points to Annie Jacobsen’s Biological War as an example of the kind of scenario thinking he means.
The post is a brief AI-safety-style prompt: don’t stay abstract—work from specific failure modes and catastrophic scenarios when thinking about what could go wrong.
More from AGI Musings
- Market cools on Anthropic and OpenAI IPO bets as AI lab premium fades — Ronangmi · 2026-07-29
- Ilya Sutskever’s guess for AI: an internal value function that enables lifelong learning — FinanceYF5 · 2026-07-29
- Ilya Sutskever may be betting SSI on continual learning, backed by NVIDIA partnership — FinanceYF5 · 2026-07-29
- AI employees urge governments to build tools for pacing frontier AI development — ghadfield · 2026-07-29
- Compute inequality, RSI claims, and who gets to speak for the world — A_K_Nain · 2026-07-29
- Longevity futurism points to age reversal, AI drug discovery, and organ replacement — rand_longevity · 2026-07-29