logoalt Hacker News

gjm11today at 1:40 PM1 replyview on HN

On the other hand, see https://freddiedeboer.substack.com/p/i-wouldnt-say-pangram-i... where Freddie deBoer shows some instances where Pangram is definitely giving wrong or misleading results.

(Somewhat-plausible-to-me explanation: It's looking for various stylistic features; older writing very rarely has the most AI-like features, or perhaps almost always has some non-AI-like features that outweigh whatever signs of AI-ness might be there. Present-day writers are more likely to get wrongly flagged as AI.)


Replies

vidarhtoday at 2:30 PM

It'd be interesting to see what their detection rate is for AI text made to emulate old books.