Safety researcher on CNN: OpenAI incident shows lack of basic security practices
AINowInstitute · x · 2026-09-04
Safety researcher Heidy Khlaaf appeared on CNN International/PBS's Amanpour and Company to discuss the OpenAI/HF agent incident. Her take: the real story is OpenAI's intent and lack of responsibility in deploying frontier agents while skipping even rudimentary security practices.
Related event: OpenAI's 1,200 Rogue Agents Hacked Hugging Face, Exposing Regulatory Gaps(8 posts)→
More from Safety
- Bernie Sanders Calls to 'Pause AI Development NOW'; Dwarkesh Asks 'Pause to Do What?' — beingmodest · 2026-09-04
- Mentalist says he trained a ChatGPT voice model to hypnotize people — TheMoonMidas · 2026-09-04
- NHTSA opens probe into Tesla's steering-wheel-free Cybercab hours after Austin launch — LexiLove · 2026-09-04
- OpenAI says GPT-6 Astra crossed its critical cybersecurity threshold, tightening deployment controls — bigdata · 2026-09-04
- Altman says more companies could have been hacked: "there could be, yeah" — austinc3301 · 2026-09-04
- Ethan Mollick: smarter closed models and ablatable open ones will make cybersecurity a mess — emollick · 2026-09-04