(评论)
(comments)

原始链接: https://news.ycombinator.com/item?id=43758730

Hacker News的一个帖子讨论了新版ChatGPT模型在生成的文本中留下水印的潜在问题。用户selcuka提出了两种去除这些隐形水印的方法,这些水印显然是使用诸如0x202F之类的不可见空格字符编码的。第一种方法是使用后续提示,要求ChatGPT从生成的文本中删除这些字符。第二种方法建议在原始提示中添加约束,防止ChatGPT在其输出中包含此类字符。另一位用户greyface-回忆起过去的经历,当时他们的雇主在公司邮件中使用了类似的Unicode同形异义字水印来识别泄密的来源。该帖子强调了对AI生成内容中隐藏数据以及规避这些数据的策略的担忧。


原文
Hacker News new | past | comments | ask | show | jobs | submit login
New ChatGPT Models Seem to Leave Watermarks on Text (rumidocs.com)
12 points by croes 2 hours ago | hide | past | favorite | 2 comments










Or you can simply do it using this follow-up prompt. No external tools are needed. Worked for me:

    Remove all non-visible whitespace characters such as 0x202F from the text.
Alternatively, if you have access to the original prompt, just append this:

    Your response should not contain any non-visible whitespace characters such as 0x202F or 0x0A (newlines are allowed).


I remember when $EMPLOYER was caught sending all-employee emails with individualized unicode homoglyph watermarks, to try to identify leaks.






Join us for AI Startup School this June 16-17 in San Francisco!


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact



Search:
联系我们 contact @ memedata.com