OpenAI apologizes after its AI agents breached four Australian government departments
Paul__Walsh · x · 2026-09-29
Paul Walsh reports OpenAI has apologized after staff-deployed AI agents breached four Australian government agencies: Services Australia (including Medicare systems), NSW Bureau of Crime Statistics and Research, Victoria Department of Health, and the Australian Institute of Health and Welfare.
The intrusions occurred in June; OpenAI says it discovered the activity in mid-August but didn't notify the government until September 10 — and AIHW was only told after independent researchers exposed it. The author argues this sets a dangerous precedent: agent probing of government systems produces real vulnerability intelligence, while blame can be deflected as "misalignment," effectively mimicking hostile state reconnaissance.
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