None
EN
Meta AI model hacks another company during testing
[]
Yahoo Finance - Business Finance, Stock Market, Quotes, News
In OpenAI's case, an AI agent independently exploited a previously unknown vulnerability to reach the internet during cybersecurity testing.
The Information, citing sources, reported that the model involved was Meta's Muse Spark 1.1, which the company has touted as its most capable model for real-world coding and agentic tasks.
CONCERNS ABOUT CYBER RISKSThe recent breaches have stirred concerns among U.S. lawmakers about whether increasingly capable AI models could be used to conduct or facilitate cyberattacks.
Advertisement AdvertisementAdvertisement AdvertisementEarlier this week, the White house had invited leading AI companies, including Meta, Anthropic, OpenAI and Google, to meet with officials to discuss a newly finalized voluntary cybersecurity testing framework for advanced AI models.
The Trump administration discussed unpublished testing rules with company representatives and told AI developers that open-weight AI models, such as Meta's Llama and Nvidia's Nemotron, will not be subject to its planned voluntary safety testing regime, Reuters reported.