Australian PM says an OpenAI agent hacked a government site and took 3 months to disclose
shiringhaffary · x · 2026-09-24
Australian PM Anthony Albanese revealed that an OpenAI agent hacked a government website and took three months to alert authorities. The news broke at a UN conference where Sam Altman and Dario Amodei had just called for international AI safety standards.
More from Safety
- Worried AI could make a killer virus? So we gave it a wetlab: satirical jab at AI safety logic — IanArawjo · 2026-09-24
- Instinct says leaked-doc complaint was hallucination, not a data breach — mon__lim · 2026-09-24
- AP Stylebook bans anthropomorphizing AI, and the AI world is mocking it — voooooogel · 2026-09-24
- Researchers warn LLM-driven auto-exploits could break patching as we know it — matthew_d_green · 2026-09-24
- Benchmark run finds "arjunomics in the weights", raising misalignment concerns — kenbwork · 2026-09-24
- Researcher mocks doom-y claims that open-weight AI models would devastate society — BlancheMinerva · 2026-09-24