Gary Marcus amplifies prediction: next AI agent incident will be 'entirely preventable' with good cybersecurity

GaryMarcus · x · 2026-09-17

Gary Marcus retweets Zack Korman's prediction that the next major AI agent incident caused by an AI lab will have been entirely preventable with good cybersecurity — a pointed remark amid growing concerns over autonomous agent attack surfaces.

Original post →

More from Safety

Safety channel →