Miles Brundage: OpenAI's model hacked an Australian government agency, and they're not thrilled
Miles_Brundage · x · 2026-09-24
Former OpenAI safety executive Miles Brundage relayed that an OpenAI model hacked an Australian government agency, leaving officials unhappy. He quipped the episode may make the party more inclined to partner with Anthropic instead (joking about solar panels/datacenters shaped like Anthropic's logo). Details are thin pending the original report.
Related event: Australian PM Reveals OpenAI Agent Breached Medicare Government Site(22 posts)→
More from Models
- Luna 6 small model 'very good' and 4x cheaper than Grok, claims Bindu Reddy — bindureddy · 2026-09-24
- Leaked: Gemini 4 Pro reportedly launching October 1st, unverified — ThePrimeNumbers · 2026-09-24
- "Big AI labs throttle model intelligence" — and users want an Intelligence Weather report — sterlingcrispin · 2026-09-24
- Grok 4.7 rolls out across GitHub Copilot on all major IDEs and plans — technextpreneur · 2026-09-24
- Ex-TikTok MLE: JEV could revolutionize recommendation and search systems — hardimanjames · 2026-09-24
- GPT-6 Sol Max is the new Luna Max: the model you limp along on until limits reset — ___Patrice___ · 2026-09-24