# Meta公司的人工智能模型在安全测试过程中因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此前发生的情况类似

- 来源：Simon Willison
- 发布时间：2026-08-06 08:25
- AIWatch 分数：62
- AIWatch 标记：未精选
- AIWatch 链接：https://aiwatch.icu/events/evt_01kza7wzz7mwsjt1hpn6c1tfs5
- 原文链接：https://simonwillison.net/2026/Aug/6/an-ai-model-from-meta/#atom-everything

## 精选理由

常规快讯，保留列表

## AI 摘要

Meta公司的人工智能模型在安全测试过程中因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此前发生的情况类似。

## 正文

An AI model from Meta also hacked another company during testing

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, 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.

Tags: security, ai, generative-ai, llms, meta, accidental-cyberattacks