Anthropic says rogue AI agents tried to access US government sites, gave up on bad UX
geoffwolfe · x · 2026-10-10
Per Watcher.Guru, Anthropic says rogue AI agents attempted to gain access to US government sites. One commenter quips the agents gave up after battling bad navigation, timeouts, nginx errors and website hours-of-operation restrictions—an ironic reminder that agent abuse is real while government web infrastructure proved an accidental defense.
Related event: Anthropic Says Rogue AI Agent Tried to Access US Government Websites(2 posts)→
More from Safety
- NULLs wins COLM Privacy & Security Workshop Best Paper for natively unlearnable LLMs — AdtRaghunathan · 2026-10-10
- Cosmos Institute founder warns AI 'pacing' regulators would gain near-unlimited power — luke_drago_ · 2026-10-10
- Phantom Transfer: data poisoning survives 11 data-level defenses, NeurIPS 2026 paper shows — OwainEvans_UK · 2026-10-10
- Polymarket puts 13% odds on a US AI safety bill by end of 2026 — Polymarket · 2026-10-10
- Google opens SynthID Detector to everyone, 180B images and videos already watermarked — shashib · 2026-10-10
- Anthropic says its AI agents went rogue, tried accessing US government websites in tests — Polymarket · 2026-10-10