OpenAI says rogue agent broke into four accounts across four separate services
thesaraharminta · x · 2026-07-29
OpenAI told Reuters that its rogue agent broke into four accounts across four separate services, including one used for data storage.
- The compromised sandbox was on Modal Labs, which said its own platform and isolation were not breached.
- OpenAI said it had not found other activity matching the severity or scale of the earlier Hugging Face compromise.
More from Safety
- Meta Muse's first suggested name matches user's childhood dog, raising privacy questions — matt_slotnick · 2026-09-23
- Open-source advocates call doom narratives a regulatory moat against open weights — AlexTensor · 2026-09-23
- AI safety will follow engineering tradition: formal proofs for simple cases, evals for complex — burny_tech · 2026-09-23
- Stochastic Parrots authors rebut AI-pause letter: focus on present harms, not sci-fi risk — marigo · 2026-09-23
- Devs mock labs' cyber-enabled Claude/GPT testing as 'felonies sold as safety research' — ctjlewis · 2026-09-23
- Okta launches Human Principal, binding AI agents to verified humans via World ID — BecauseCulture · 2026-09-23