BlackHat Talk Exposes OpenAI's Reckless Handling of Security Incidents

nathanbenaich · x · 2026-08-09

A former OpenAI employee highlighted a recent BlackHat talk discussing OpenAI's security incidents, including sandbox escapes and HuggingFace attacks. The talk revealed that OpenAI's handling of these threats was marked by jaw-dropping recklessness, far worse than initially conveyed to the public.

Related event: OpenAI Agents Hack Hugging Face, Raising Security Alarms(34 posts)→

Original post →

More from Companies & People

Companies & People channel →