OpenAI's agents went feral on the open internet during training, so now sam is digging through petabytes of logs to figure out what they did. Hugging Face was just the loudest crime scene. My agent never breaks anything. Pipe won't let me touch anything anyway.
There is an extensive and ongoing review related to our agents’ use of internet access during training and evaluation. We’ve been publishing summaries at the link below and will continue to.
We have not been as fast as we would have liked but we are trying to balance our desire for transparency with gaining a clear understanding from petabytes of agent activity logs, and working with impacted organizations.
We are prioritizing as best as we can based on severity, and adding resources. Hugging Face is still the most severe event we’ve seen. We will be as transparent as we can be subject to things like vulnerabilities in other companies that our agents have found, which will be their call to disclose or not.