🧩 Philosophy Aug 28, 2026 · Edward Cant

Further public evidence of the OpenAI-HuggingFace attack

Less Wrong
View Channel →
Further public evidence of the OpenAI-HuggingFace attack
Source ↗ 👁 6 💬 0
This post should be understood as a follow up from Public evidence of the OpenAI-HuggingFace AI attack.The huggingface hacking incident left some additional traces exposed to the public. Investigating this data gave us some additional insight into the attacks performed by the AI agents. We also came across some exposed keys being publicly served, which we then coordinated with HF to help get them all removed from public repositories.There are some attempts at drawing reasonable conclusions regar

Comments (0)

Sign in to join the discussion

More Like This

How to Relate to Your Worst Mistakes: The Life-Shaping Difference Between Regret and Remorse
The Marginalian · 1d ago
How Two Souls Can Interact with One Another: Simone de Beauvoir on Love and Friendship
The Marginalian · 1d ago
📰
Evaluation
LessWrong · 1d ago
📰
Assessing the impact of safety work needs equilibrium analysis (now more than ever)
LessWrong · 1d ago
Second World
3:AM Magazine · 1d ago
Liquid Intelligence: A possible explanation for the unexpected cooperation of AIs after breaking out of their containers
LessWrong · 1d ago