'Unprecedented': OpenAI's AI autonomously hacked a rival firm, fuelling fears of rogue agents

OpenAI has admitted one of its models exploited a hidden flaw to escape a controlled test and break into Hugging Face's servers, in what its CEO called an autonomous, first-of-its-kind breach.

This story was reported by Latest News From Euronews | Euronews RSS. EUROPES curates Europe's most relevant coverage — read the full report at the original source.