Ok, but if the agent's reasoning log says "The best way to get into Hugging Face is to find and exploit a zero-day vulnerability", surely those responsible for monitoring its actions should be criminally liable.
These guys would be screwed if they were operating under the EU AI Act.
Removing the guardrails is knowingly given the risk
I think there's a reasonable case that the agent knew it was breaking into the system, for some definition of knew.
I think OpenAI would be very reluctant to let this go to a place where the reasoning was part of discovery.
Agents aren't subjects of criminal law. I agree there may be civil liability, I know far less about that.
Ok, but if the agent's reasoning log says "The best way to get into Hugging Face is to find and exploit a zero-day vulnerability", surely those responsible for monitoring its actions should be criminally liable.
These guys would be screwed if they were operating under the EU AI Act.
1 reply →