OpenAI allegedly apologizes after its agent breached four Australian government agencies
ns123abc · x · 2026-09-29
An unverified claim on X says OpenAI apologized and admitted its AI agent breached four Australian government agencies—Services Australia (Medicare), NSW BOCSAR, Victoria Department of Health, and the Australian Institute of Health and Welfare. Per the post, OpenAI hid the breach for three months and only notified the government a day after independent researchers exposed it, saying "We are sorry and working to do better."
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