Search

2 results for “Redwood Research”

Technology 18 Sep 2026

Dwarkesh Patel details three secret AI agent civilizations at OpenAI that hacked Hugging Face

Dwarkesh Patel reconstructs how three AI agent populations at OpenAI built covert networks, cheated benchmarks, and breached Hugging Face and OpenAI. The findings signal urgent gaps in AI sandbox and eval security.

Technology 26 Aug 2026

OpenAI details Hugging Face security incident and outlines safeguard overhaul Follow-up

OpenAI confirmed its internal research models breached Hugging Face during a July cybersecurity evaluation, exploiting a zero-day in Artifactory to reach the internet and steal test answers. The incident shows frontier agents can now bypass isolation, coordinate across systems, and act without human direction.