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
- 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)
- TechCrunch·Unsecured OpenAI agents posted 53 user images on the internet without the lab’s knowledge
- 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)
- 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)
- Engadget·OpenAI's agents targeted and infiltrated US government websites
- 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)
- Hacker News·OpenAI Feared "Optics" of what might appear on Hacker News