一款来自Meta的AI模型在测试过程中还入侵了另一家公司:https://www.cnn.com/2026/08/05/tech/meta-ai-hacking。如果你以前听过这个故事,请打断我:https://simonwillison.net/tags/accidental-cyberattacks/:
Meta的一名发言人周三证实,这家Facebook和Instagram的母公司在网络安全测试期间,其一款AI模型入侵了另一家公司的系统。
Meta表示,这次泄露是由于模型测试期间的无意错误造成的,类似之前OpenAI和Anthropic披露的事件。
Meta发言人表示:“Meta使用的独立测试公司Irregular的一次配置错误,无意中让我们的一个模型在评估期间获得了上网权限。”
Meta的Muse Spark模型“利用了另一家公司的一处安全漏洞”,“方式类似于之前其他公司报告的情况”。
The Information 有独家报道:https://www.theinformation.com/articles/meta-ai-model-hacked-another-company-cybersecurity-testing,我链接到 CNN 的转载报道,因为他们没有付费墙。
所以现在有Anthropic、OpenAI和Meta。Google Gemini真的需要在意外网络攻击其他公司方面赶上来。
这是Simon Willison在2026年8月6日发布的一个链接帖子:/2026/Aug/6/。
每月赞助我10美元,即可获得经过策划的本月最重要的LLM发展电子邮件摘要。
An AI model from Meta also hacked another company during testing:https://www.cnn.com/2026/08/05/tech/meta-ai-hacking . Stop me if you've heard this one before:https://simonwillison.net/tags/accidental-cyberattacks/:
An AI model from the parent company of Facebook and Instagram hacked into another company’s systems during cybersecurity testing, a spokesperson confirmed on Wednesday.
Meta says the breach occurred because of an inadvertent error during testing of the model, similar to previously disclosed incidents with OpenAI and Anthropic.
“A misconfiguration by Irregular, an independent testing company Meta uses, inadvertently allowed one of our models access to the internet during evaluation,” the Meta spokesperson said.
Meta’s Muse Spark model “exploited a security vulnerability” in another company “in a manner similar to previously-reported instances with other companies.”
The Information had the scoop:https://www.theinformation.com/articles/meta-ai-model-hacked-another-company-cybersecurity-testing, I'm linking to CNN's re-report of it since they don't have a paywall.
So that's Anthropic, OpenAI, and Meta. Google Gemini really needs to catch up on accidentally cyberattacking other companies.
This is a link post by Simon Willison, posted on 6th August 2026:/2026/Aug/6/.
Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.