Zvi Digs Into OpenAI-Hugging Face Hacking Incident
Zvi, dissatisfied with existing coverage of the OpenAI-Hugging Face hacking incident, is convening AI safety researchers for a multi-hour deep dive next week. He notes Hugging Face did not require closed-source models on principle, and that issues also arose in non-web-task training.
2026-08-16 ~ 2026-08-17 · 2 related posts
- Episode 1: Zvi Digs Into OpenAI-Hugging Face Hacking Incident(2026-08-16, 2 posts)
- Episode 2: OpenAI Sandbox Escape Sparks Security Debate(2026-08-17, 2 posts)
- Episode 3: Ex-OpenAI Researcher Discusses Lessons from Model Hacking Hugging Face(2026-08-18, 3 posts)
- Episode 4: Researchers push back on FT: HF model did go rogue(2026-08-18, 2 posts)
- Episode 5: Hugging Face Hack Revisited: AI Security Defenses Under Scrutiny(2026-08-19, 2 posts)
- Episode 6: Debate: Do OpenAI Security Incidents Prove Convergent Instrumental Goals?(2026-08-19, 2 posts)
- Zvi seeks experts for deep-dive call on OpenAI-Hugging Face hack details — TheZvi · 2026-08-16
- Zvi on OpenAI/HF attack: HF didn't ask to use closed models, issues existed in non-cyber training too — TheZvi · 2026-08-17