Researcher Criticizes Current AI Safety Paradigm as Unsustainable 'Patch-and-Pray'

davidmanheim · x · 2026-08-13

David Manheim argues that the current AI safety paradigm of "seeing what models can do, shoring up defenses, and releasing" is akin to "Patch-and-Pray" cybersecurity. He notes this approach is critically non-scalable and fails to address the hard problems of ASI, only barely mitigating simple misuse or mistakes.

Original post →

More from AGI Musings

AGI Musings channel →