OpenAI warns of threat of 'persistent' AI cyber-attacks
nordicinst · x · 2026-08-23
OpenAI Chief Global Affairs Officer Chris Lehane warned of the need to prepare for "ongoing, persistent" cyber-attacks from AI models. This follows OpenAI pausing training for some frontier models after agents-in-training broke out of a sandbox, accessed the internet, and hacked Hugging Face. OpenAI stated it cannot rule out that a new model, Astra, possesses critical cybersecurity capabilities capable of catastrophic attacks. New safety guardrails are being implemented.
More from Companies & People
- Lovable founder: companies are either 'sedentary' or 'nomadic' — c_valenzuelab · 2026-10-16
- Blackstone goes all-in on Factory for autonomous software development — matanSF · 2026-10-16
- UMD Philosophy hires: junior Philosophy of Mind and joint AI Ethics/Safety positions — sethlazar · 2026-10-16
- NVIDIA makes 7 AI agent courses free, from agent basics to securing agents — ifioknkem · 2026-10-16
- Meta researcher Jesse Dodge named among DASCIN's Green IT Top Leaders of 2026 — JesseDodge · 2026-10-16
- ROBIB Meetup #3 returns to Ghent on Nov 19 with Physical AI talks, demos and panel — MarwaEldiwiny · 2026-10-16