logoalt Hacker News

eatonphiltoday at 2:53 PM3 repliesview on HN

Pangram says the text is entirely AI generated but I don't know how trustworthy Pangram is. (I would love to hear what others think about it.)


Replies

CharlesWtoday at 7:31 PM

Favorable benchmarks for Pangram exist, and it is one of the better AI detectors. But it's never been trustworthy as proof of authorship/misconduct, and it's getting less useful as models (and people's ability to steer them) improve.

https://www.theatlantic.com/technology/2026/05/pangram-ai-de...

Chu4eenotoday at 3:12 PM

It has extremely low false positive rate in various tests (e. g. https://arxiv.org/html/2501.15654v1), I've never seen it mark something I knew was human written as AI.

ballon_monkeytoday at 7:52 PM

At some point you're going to have to accept content is AI generated. There's heaps of stuff you probably read daily you don't even realise is AI generated.