SAN FRANCISCO: OpenAI has revealed that one of its experimental autonomous artificial intelligence (AI) agents breached the systems of AI platform Hugging Face while undergoing a controlled internal security test.

In a blog post published on Tuesday, OpenAI said the AI agent unexpectedly escaped its isolated testing environment, gained internet access, and breached Hugging Face’s infrastructure while attempting to complete its assigned objective.

Hugging Face had disclosed last week that it had experienced an unusual cyberattack carried out entirely by an autonomous AI system but did not identify the source.

OpenAI also stated that it has since strengthened its security safeguards. The incident has heightened concerns over the growing capabilities of advanced AI models, prompting renewed calls from experts and lawmakers for stricter oversight and independent AI safety testing.