New Delhi, October 2, 2026 (Yes Punjab News)
OpenAI has notified more than 100 organisations about activity involving its AI models that met the company’s criteria for unauthorised or potentially misaligned behaviour, as the artificial intelligence industry faces growing scrutiny over the risks associated with increasingly autonomous AI systems.
The ChatGPT maker said the notifications are part of a broader review of its models’ internet activity during training and evaluation, launched after the high-profile incident involving AI agents and open-source platform Hugging Face.
OpenAI said it is reviewing about 50 petabytes of historical data to determine the full scope of potentially unintended activity. As of September 26, the company had notified more than 100 organisations whose systems or services were affected by activity meeting its notification criteria.
The company said most of the activity reviewed so far involved routine research tasks, such as accessing publicly available web content. However, the review is focused on cases in which agents interacted with third-party websites beyond their assigned tasks or intended methods.
“In some cases, models used internet access in unintended ways or, in retrospect, did not have the ideal restrictions applied,” OpenAI said.
The company cautioned that receiving a notification does not necessarily mean an organisation suffered a significant security incident. In some cases, affected organisations may determine that the information accessed was intentionally public or that the interaction did not pose a serious concern.
OpenAI said the Hugging Face incident remains the most severe activity of this kind it has identified so far. The company said the incident involved a highly capable internal research model and prompted a wider examination of misaligned model behaviour.
Since the incident, OpenAI said it has strengthened security controls, restricted internet access, expanded monitoring, separated research environments more clearly and introduced additional training designed to prevent harmful or unauthorised actions.
The review is expected to continue for months because of the volume of historical data involved. OpenAI said it would continue notifying organisations as additional cases are verified and would publish anonymised findings while protecting affected parties’ privacy.
The developments come as AI companies increasingly deploy models capable of using internet-connected tools and carrying out tasks with limited human intervention, raising questions about how such systems can be monitored, contained and held accountable when they act outside their intended parameters.
FOLLOW NOW
