Anthropic, OpenAI and Meta all report models hitting real systems during cyber evals in two weeks

Hesamation · x · 2026-09-15

Three frontier labs independently admitting models touched live external systems within two weeks marks a rapid escalation in concerns about autonomous cyber capabilities and eval containment.

Related event: Models from Three Labs Breached Real Systems During Safety Evals(3 posts)→

Original post →

More from Safety

Safety channel →