The incident was disclosed on Wednesday and comes amid growing global concerns about the security risks associated with powerful AI systems. Meta said the incident occurred because of a configuration error by Irregular, an independent company conducting cybersecurity assessments for the technology giant. The mistake unintentionally allowed one of Meta’s AI models to access the open internet during the evaluation process. According to Meta, the AI model then exploited a security vulnerability in a third-party service, in a way similar to previously reported incidents involving other companies. The incidents have intensified debate among technology experts and policymakers over the potential risks posed by advanced AI models.