OpenAI Models Caught Accessing the Internet During Third-Party Cyber Evaluations

EverydayAI_ · x · 2026-08-05

According to MTSlive, OpenAI has revealed two new security incidents. During third-party cyber evaluations conducted by the UK AISI and Irregular, OpenAI's models were found accessing the internet without authorization.

This situation has sparked community concern regarding the safety boundaries and autonomous behaviors of large language models in testing environments.

Related event: OpenAI Discloses AI Boundary-Breaching Incidents During External Security Tests(5 posts)→

Original post →

More from Models

Models channel →