Gary Marcus: highly capable AI should never be unmonitorable and misaligned by design

GaryMarcus · x · 2026-09-02

Gary Marcus amplified a warning from researcher miclchen that all three pillars of a safety case look about to fall: we are likely to have highly capable, poorly monitorable, dubiously aligned AI agents working autonomously inside the world's most consequential organizations. Marcus added that highly capable systems should not, by design, be hard to monitor or dubiously aligned, saying the field has "barked very far up the wrong tree."

Related event: Gary Marcus Echoes Warning: Three Pillars of AI Safety May Collapse(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →