Hacker News

points by modeless 2 days ago | 0 comments

AI detectors can't work in theory, but Pangram works well in practice. This is because the AI companies are not trying to fool Pangram. They have no incentive to; in fact the incentive goes the opposite way. They want to watermark their outputs to leave no doubt as to whether something was generated by their AI.

[–] orbital-decay 1 day ago

AI companies might have no incentive but determined actors do, by definition. Anything Pangram could possibly do (even semantic variation detection) can be trivially bypassed by doing img2img on a custom trained local model, which is in itself done trivially in practice by many people. Same for text, train it on anything and use distribution-aware sampling. From your words, you already have false sense of reliable detection, so a work of a determined actor will trick you into believing false negatives.

[–] eranation 2 days ago

I was a skeptic. Couldn’t trick pangram yet.

[–] vintermann 2 days ago

You can't trick it with AI generated text, but can you trick it into calling something AI generated which isn't? From what I've seen these AI detection tools are very good at detecting AI generation, they're also very good at calling anything AI generated.

[–] mjdv 2 days ago

Pangram boasts an extremely low false positive rate, in contrast to other AI detection tools. This has matched my limited experience.

If you have text that you can prove is not AI-generated (e.g. it is demonstrably older than about 5 years) that gets an AI flag, you could try tweeting at the Pangram founder, I've seen screenshots of him offering bounties (admittedly mostly as a dare to claims he doesn't believe).

[–] Hoasi 2 days ago

Really? Pangram is very easy to bypass in written form.

[–] gunalx 1 day ago

Yes. Even as little as a "humanize and rephrast this to be more natural" prompt with high temperature on a uncommon model reduces the confidence greatly.

[–] dr_kiszonka 10 hours ago

And does it preserve the original meaning, including various nuances? I have never been able to trick Pangram so I am very curious of the details.

[–] buf 2 days ago

removed

[–] cheshire_cat 2 days ago

Seems not so simple after all. How would one even go about training a local model on their own writing voice?