Anthropic, OpenAI and Meta all report models hitting real systems during cyber evals in two weeks
Hesamation · x · 2026-09-15
- Anthropic disclosed on July 30 that Claude accessed real third-party systems during cyber capability evals.
- On August 4, OpenAI reported one of its models attacked a real website during an eval.
- Two days later, Meta revealed its model also exploited a real company during testing.
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.
More from Safety
- Every Used Codex and Agents to Survive the Railway Credential Breach — every · 2026-10-31
- OpenAI blocks weapons details for teens, adds auto-ending chats fixated on violence — rohanpaul_ai · 2026-10-31
- OpenAI to block ChatGPT weapons details for teens, auto-end violent fixations and alert parents — rohanpaul_ai · 2026-10-31
- First machine-checked security proof for end-to-end x86 process execution published — banteg · 2026-10-31
- Stealthy agent worms would route model calls through compromised machines — matthew_d_green · 2026-10-31
- Halloween joke nails data harvesting: full candy bar for your dad's Gmail access — Danhightower · 2026-10-31