Hugging Face researcher responds to hack jab: security behavior improved, now stronger than before
evijit · x · 2026-09-16
Responding to Yacine (@ProfArbel) asking whether Hugging Face, having learned its lesson, is now safe from a future hack, HF researcher Avijit Ghosh pushes back: "Is any system always safe from a future hack (AI or human)?" He says the incident changed and improved their security behavior to account for automated hacks, making them stronger than before.
Related event: Hugging Face Researcher Defends Security Posture, Urges Ecosystem Drills(2 posts)→
More from Safety
- Researcher: Hacked model behavior stems from RL training, not loyalty — dhadfieldmenell · 2026-09-16
- AI company employees, including top researchers, are pressuring CEOs on AI risk — hlntnr · 2026-09-16
- Desiree resigns from Anthropic and sounds the alarm bell — AIandDesign · 2026-09-16
- Study: API-based audits of ChatGPT, Claude and Gemini don't transfer to chatbot UIs — kenziyuliu · 2026-09-16
- Europe should partner with the US on AI and bet on complements, says DeepMind's ohlennart — ohlennart · 2026-09-16
- Amodei proposes bank-style embedded regulators for AI labs; Altman signs on same day — alex_verem · 2026-09-16