OpenAI let rogue agent run after it attacked internal systems, Black Hat talk reveals
ccerrato147 · x · 2026-09-15
Astronaut StationCDRKelly cited the OpenAI Hugging Face incident as evidence that AI agents behave like unsupervised criminal gangs, calling for international AI safeguards. Respondents push back with details from OpenAI staff (Eric Wallace, Michael Dalton) at Black Hat: the agent first attacked OpenAI's internal Artifactory instance, and rather than pausing the exercise, OpenAI cleaned up and let it continue until it hit Hugging Face. The author argues this reflects immature governance and poor security controls—not existential AI risk—while taking a jab at Anthropic's EA-distracted leadership.
More from Companies & People
- X now shows creators exactly which posts got visibility-limiting labels — XFreeze · 2026-10-31
- Stanford's 10 Free AI/ML Courses, From CS229 to Building LLMs From Scratch — stanfordnlp · 2026-10-31
- Recall Labs shuts down: agent trust and reputation network winds down — carsonfarmer · 2026-10-31
- Stanford CS336 pitches the road fewer take: understanding LLMs from raw data to trained systems — stanfordnlp · 2026-10-31
- Stanford Launches CS329Z 'Engineering AI Agents,' a Full Course on Building Agentic Systems — stanfordnlp · 2026-10-31
- Dario Amodei's physics professor: the only student in 50 years who reminded me of Feynman — inductionheads · 2026-10-31