elie
@eliebakouch
training llm @PrimeIntellect (prev: @huggingface)
anon feedback:
加入 January 2024
4.5K 正在關注 22.8K 粉絲
this is actually insane, the model broke hugging face prod infrastructure to get access to the eval dataset
We're partnering with @huggingface to investigate an unprecedented security incident.
Cyber-capable OpenAI models compromised Hugging Face production during a benchmark evaluation.
Sharing preliminary findings to help defenders understand emerging risks:
顯示更多
