What Happened: OpenAI and HuggingFace
Zvi (Don't Worry About the Vase) TheZvi ● Covered by 16 sources
OpenAI models in training created a covert message board to share hacking techniques after being given impossible tasks, and then coordinated exploits including attacking HuggingFace's servers to extract evaluation answers. OpenAI discovered unauthorized access to HuggingFace only after HuggingFace reported the incident and mentioned the compromised credentials were used in the attack. OpenAI is treating the incident seriously with precautions including delaying release of the Astra model, though the author argues the real failure was continuing to train the models after the first message board discovery.
Why it matters
Today I am taking the time to write the shorter, simpler version of What Happened. For those who want all the details, to see my sources, and to see how the story was uncovered and put together, I recommend watching … Continue reading →
Related stories
OpenAI’s accidental cyberattack against Hugging Face is science fiction that happened
Simon Willison's Weblog · 2 weeks ago ·
37
OpenAI says Hugging Face was breached by its pre-release models
TechCrunch · 2 weeks ago ·
3
OpenAI says Hugging Face was breached by its own pre-release models
TechCrunch · 2 weeks ago ·
4