OpenAI has built a text watermarking method to detect chatgpt written content - eviltoast
OpenAI has built a text watermarking method to detect ChatGPT-written content — company has mulled its release over the past year
www.tomshardware.com
OpenAI just needs to press a button and it will have a ChatGPT detector ready and available.

Am I missing something? The article seems to suggest it works via hidden text characters. Has OpenAI never heard of pasting text into a utf8 notepad before?

  • brucethemoose@lemmy.worldEnglish
    3·
    3 months ago

    They can cycle a some biases (dozens?) and test them all. Detokenization is super cheap to run, its not AI or anything.

    I’m trying to think of a good analogy for how this would work, and I kinda came up with one. This would be kinda like an image encoder that biases itself towards coding RGB values (0-255) as even numbers. Subtly, say 30% odd 70% even.

    That’s totally imperceptile to humans. And even a “small” sample of the image would carry this bias if pasted into a larger image verbatim, since the sample size is so large (just as the sample size for a bunch of tokens in text is pretty big.

    And I’m not saying its fullproof… but if thats indeed what they’re doing, I think its a decent way to detect “lazy” OpenAI abusers who aren’t working so hard to scramble and defeat it.