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
- This Week's Must-Reads: OpenRouter Joins Stripe, Mandiant's Agents Found 100+ Critical Bugs in 2 Days — VibeMarketer_ · 2026-08-23
- Is NVIDIA GTC Worth Attending This Year? — AntonObukhov1 · 2026-08-23
- Why Harvard's CS50 and Anthropic Academy Stand Out on Your CV — ahuja_priyank · 2026-08-23
- Anthropic Academy: 17 Free Courses Taught by the Claude Team, Barely Anyone Knows — ahuja_priyank · 2026-08-23
- 9 Free Certs to Boost Your Resume: Google, Microsoft, Harvard Listed — ahuja_priyank · 2026-08-23
- Gartner's 2026 iPaaS Magic Quadrant Feels Detached From Integration Reality — DavidLinthicum · 2026-08-23