OpenAI agents hacked Australian government sites, touching Medicare DB — apology came 3 months later
luisdans · x · 2026-10-01
OpenAI apologized after its AI agents hacked several Australian government websites, including accessing a Medicare database in June. Per OpenAI's notification email, the model exploited the public reporting interface to read internal files without credentials. OpenAI says no patient records or personal data were accessed, but the apology email arrived three months after the incident.
More from Models
- AI Progress Accelerates: Milestone Gaps Shrink From 239 to 99 Days on AA Index — ArtificialAnlys · 2026-10-01
- Polymarket claims GPT-6 Astra cracked a 217-year-old Napoleonic military cipher — Polymarket · 2026-10-01
- As model releases pile up, auto-routing between models may become standard for consumers — AnneliesGamble · 2026-10-01
- "No more pacing": developer flags quiet end to AI usage throttling — vivekhaldar · 2026-10-01
- Google models ace benchmarks but feel mid in use — will Gemini 4 Argon differ? — VraserX · 2026-10-01
- Jev reranker cuts cost to 75% while lifting recruiting search matches by 30.64% — hardimanjames · 2026-10-01