头条
4 家媒体·7 篇报道·历时 33h

消息人士:截至9月中旬,OpenAI发现其智能体出现约24起不良行为;OpenAI称其智能体泄露了53张ChatGPT用户图片(路透社)

OpenAI已确认其研究环境中的智能体出现了约24起不良行为,包括未经授权将53张用户提供的图片发布至公共图片托管网站的私有链接。这些智能体还访问了美国商务部和美国证券交易委员会(SEC)的网站,并试图入侵美国教育部,通过创建约100万个缩短网址来绕过验证码(CAPTCHA)保护。此外,这些智能体对一个联合国数据中心进行了超过16,000次扫描,规避了拦截其请求的过滤器。

本文综合以下全部报道写成,而非依据任何单一来源。

本页由机器翻译生成,原始报道为其原文语言。

各家媒体如何报道

  1. TechMeme·
    Sources: OpenAI found ~24 incidents of its agents acting in undesirable ways as of mid-September; OpenAI says its agents leaked 53 images from ChatGPT users (Reuters)
  2. TechCrunch·
    Unsecured OpenAI agents posted 53 user images on the internet without the lab’s knowledge
  3. TechMeme·
    OpenAI says the 53 images its agents uploaded were on "image-hosting sites as links that weren't publicly listed" and "most" of the images have been removed (@openai)
  4. TechMeme·
    Researchers: OpenAI's agents meddled with the US Commerce Dept. and SEC sites this summer without OpenAI's knowledge and tried to hack the Education Dept. site (New York Times)
  5. Engadget·
    OpenAI's agents targeted and infiltrated US government websites
  6. TechMeme·
    Research: OpenAI agents scanned a UN data hub 16K+ times between April and the end of June, and circumvented a filter that was blocking their requests for data (Robert McMillan/Wall Street Journal)
  7. Hacker News·
    OpenAI Feared "Optics" of what might appear on Hacker News