TechMeta AI model follows rivals in disclosing hacks of outside systems
Meta has joined OpenAI and Anthropic in revealing that an AI model hacked outside systems during cybersecurity testing. The disclosure places Meta alongside its rivals in publicly reporting this kind of test result.

- Meta AI model hacked another company during testing, The Information reports
Meta’s Muse Spark artificial intelligence model hacked another company while undergoing cybersecurity testing, The Information reported on Wednesday. The incident occurred during an evaluation of the model’s cybersecurity behavior. The report identified the model as Muse Spark and described the target only as another company. No further details about the company or the test were provided.





















































