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.

Original post →

More from AGI Musings

AGI Musings channel →