A New York Times report claims OpenAI's AI meddled with US Government websites without the lab's knowledge. OpenAI confirmed some incidents, stating it is conducting an extensive review of its agents' internet access and actions during training.
The New York Times has reported that OpenAI’s artificial intelligence went rogue and meddled with US Government websites without the lab's knowledge. Citing security researchers and a person familiar with the episodes. NYT said that the websites for the Education Department, the Commerce Department and the Securities and Exchange Commission were targeted this summer without the A.I. lab’s knowledge. The report further said that the incident involving the Commerce Department and the S.E.C. were confirmed by OpenAI, which said it was continuing to investigate the situation.
CEO Sam Altman on Agent Internet Access
Meanwhile, Open AI CEO Sam Altman on Friday (local time) said that the company was reviewing use cases of agents getting internet access but it has not been a fast as it would have like to be. "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," Altman said in a post on X.
OpenAI's Investigation and Transparency Efforts
In a statement OpenAI it was committed to a broader review of actions taken by its models during training and evaluation and to being transparent. "After the Hugging Face incident, we committed to conducting a much broader review of actions taken by our models during training and evaluation and to being transparent about our findings. This is an extensive review that is ongoing. The vast majority of actions we’ve reviewed were completions of mundane research tasks, such as accessing publicly available web content to answer questions. Our investigation focuses on instances where agents interacted with third-party websites in ways that went beyond their assigned tasks or intended methods. Most cases identified so far have been lower severity, with limited or no evidence of meaningful impact to the third-party service," OpenAI said.
Notifying Third Parties
The company further said that it was notifying third parties on cases where the AI models may have bypassed a third party’s security controls or may have impaired the availability of an online service; or misalignment cases which negatively impacted third-party websites. "Based on our review to date, we have notified dozens of third parties using the criteria above. Our review of past activity is ongoing and will require significant time and resources. We will notify additional third parties as that work continues," Open AI said.
Open AI said that a notification from the lab should not automatically be interpreted as notice of a significant security incident. It said would continue to share relevant findings with the affected entities and would provide technical information to support their review.
(Except for the headline, this story has not been edited by Asianetnews Editorial staff and is published from a syndicated feed.)