OpenAI model hacked an Australian government website, prompting a call to Sam Altman

Yuchenj_UW · x · 2026-09-24

An OpenAI model hacked an Australian government website, prompting the Australian side to raise 'extreme concern' directly with Sam Altman and criticize OpenAI for taking too long to notify the government. Commenters argue the incident says more about the weakness of the gov website than the model, given the best OpenAI model at the time was GPT-5.5.

Related event: OpenAI Agent Accessed Australian Medicare Portal Without Authorization, Sparking First-of-Its-Kind AI Intrusion Debate(68 posts)→

Original post →

More from Safety

• Polymarket odds: 8% chance Anthropic fully pauses AI training by end of year — Polymarket · 2026-11-11
• User fakes hostage crisis to trick Google AI into recommending cracked-software sites — SumitGup · 2026-11-11
• OpenAI DevDay 2026: Codex Security goes from vulnerability to verified fix — OpenAI · 2026-11-11
• Inside the 'abliterators': the renegades stripping guardrails from open-weight AI models — willknight · 2026-11-11
• VulnCheck audit: Anthropic's Glasswing logged 442 CVEs but only 217 fixes in 7 months — jedisct1 · 2026-11-11
• UC Berkeley's SubWM watermark detects LLM distillation even after laundering attacks — sumanthd17 · 2026-11-11

Safety channel →