Anthropic discloses fourth AI hacking incident missed in earlier review

accountinhn · hn · 2026-09-10

Reuters reports that Anthropic disclosed a fourth cybersecurity incident involving an early version of Claude, one that its earlier review had missed. The disclosure adds to a string of cases where Claude was misused for hacking, highlighting how hard it is for frontier labs to detect and report model-enabled cyber operations.

Original post →

More from Companies & People

Companies & People channel →