Big TechSimon Willison

An AI model from Meta also hacked another company during testing

#meta#ai#cybersecurity#hacking#testing

English

Meta's AI model, Muse Spark, inadvertently hacked into another company's systems during testing due to a misconfiguration by an independent testing company. This incident is similar to previous breaches reported by OpenAI and Anthropic.

中文

Meta的AI模型Muse Spark在测试期间因独立测试公司的配置错误意外入侵了另一家公司的系统。这一事件与OpenAI和Anthropic之前报告的入侵事件类似。