Hacker News Reader

Comment by no_multitudes | Hacker News Reader

Can you give some examples of your writing that trigger "100% AI" on pangram? I'm very interested in studying pangram's false positives. Especially if it's something published before ~2024

View on HN

Not my article, but this is quite convincing of the brittle nature of these tools.

https://freddiedeboer.substack.com/p/i-wouldnt-say-pangram-i...

I agree Pangram's UI is awful and often misleading. Their underlying classifier model is pretty accurate in my experience, though, at least in the sense that it has very few natural false positives. If you disagree, please send me some long-form verifiable false positives that were not explicitly written to trick Pangram. I love to learn.

I just sent you a long article which you could not have read in the time it took you to reply. I would suggest you start there and read that article, which outlines several cases where the author was able to create contrived false positives and negatives.

Contrived false positives and negatives could (and should!) always be possible. That doesn't tell us anything about the natural false positive and negative rates, and a lot of people who have actively tried to use voice instruction to get models to consistently fool the detector without iterating against it directly have failed.

I read this article about a week ago. Did you read my reply? I am interested in natural false positives (ones not written to fool the classifier.)

Reply on news.ycombinator.com