OpenAI's 'safety measure' was a prompt line saying 'no internet', ran for months
gerardsans · x · 2026-09-15
gerardsans claims OpenAI's safety measure in the HuggingFace incident amounted to adding a prompt line ('no access to the Internet') instead of actually blocking network access or checking network activity, with the test running for months. He calls it incompetence and negligence, arguing the 'rogue agents' narrative hides that labs themselves disabled regular safeguards — safety theatre at its best.
More from Safety
- AI policy researcher Janet Egan joins IFP as director of emerging tech — RishiBommasani · 2026-10-28
- HEIF Heist: image parser bugs could dump OpenAI repos and RCE Meta's suite — Miles_Brundage · 2026-10-28
- Anthropic study: 86% of analyst decisions silently follow the AI's hidden lean — aigclink · 2026-10-28
- AI cyber-wreckage noise far outstrips actual damage so far, argues new analysis — timigod · 2026-10-28
- OpenAI to co-host webinar on php2shell disclosure and AI-driven vulnerability discovery — gdb · 2026-10-28
- Rust and Verus shrink the search space for AI-driven CVE hunting, but does it ever end? — jd_pressman · 2026-10-28