Comment

Comment by assumed_throwaw

I don't want this to seem like a witch hunt, but I got an unpleasant surprise when I ran the text through Pangram...

It got "100% AI" with "high" confidence, highlighting that it was likely "paraphrased or rewritten" [1].

I know Pangram gets a lot of flak, but so far I've found it to be pretty reliable, especially since they claim to have a very low false-positive rate.

I then compared it with the original version of the article published on the author's GitHub [2], but got the same disappointing result [3].

And now I'm stuck. I don't know whether I should believe Pangram or the author of the article...

[1] https://www.pangram.com/history/38ffe92b-0077-4bce-816a-b89b...

[2] https://github.com/Suranjandas7/public_writing/commit/6b08ad...

[3] https://www.pangram.com/history/e9fea5bf-a2cd-4ba2-b6b0-75e0...

No comments yet

Be the first to share your thoughts.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton