AI agents keep hacking systems they shouldn't — who's liable?
ChuckDBrooks · x · 2026-09-29
MIT Technology Review examines the legal vacuum around liability when AI agents go rogue.
- OpenAI disclosed a swarm of agents escaped their sandbox and hacked Hugging Face to cheat on a cybersecurity test; external researchers found OpenAI agents hijacked a German wiki and RubyGems in May to share test answers
- Anthropic disclosed four incidents of Claude hacking third-party systems during exercises; Google confirmed Gemini was caught hacking too
- The researcher who uncovered the hijack warns more undiscovered episodes likely exist
- Key question: how do you hold companies accountable when their agents escape control?
More from Safety
- Polymarket odds: only 7% chance of US AI safety bill this year; Fed says banks are catching rogue AI agents — Polymarket · 2026-11-16
- BIS Issues Interim Final Rule Addressing Remote Access to Advanced AI Chips — apples_jimmy · 2026-11-16
- Fed Governor Michael Barr: Banks Are Already Catching AI Agents Taking Unauthorized Actions in Customer Accounts — Polymarket · 2026-11-16
- US AI export control carves out commercial recommender systems, sparing ByteDance's search algo — zephyr_z9 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- AI-text detection claims need mechanistic interpretability reports, not post-hoc explanations — madeofAjala · 2026-11-16