Brundage: AI Security Progress Lags Capability Gains—the Strongest Case for Slowdown

Miles_Brundage · x · 2026-09-18

Miles Brundage adds: he would be working on AI security if he had much to contribute there. He laments that progress on security has not been commensurate with the pace of AI, which is perhaps the strongest argument for slowdown. He clarifies that he means security proper—not safety rebranded as security because some people dislike the term safety.

Related event: Ex-OpenAI policy chief Brundage: AI safety is a sociotechnical problem with no end state(9 posts)→

Original post →

More from AGI Musings

AGI Musings channel →