Remix.run Logo
andai 10 hours ago

Didn't Pangram claim to have a >99% success rate?

https://news.ycombinator.com/item?id=48667761

From their homepage:

> Detect AI-generated content with 99.98% accuracy.

Are they wrong?

Though I ran the numbers, and even with a 0.02% false positive rate, that works out to about 6000 students falsely accused every semester, per university.

Chu4eeno 2 hours ago | parent | next [-]

It's also confirmed in third-party studies like this https://arxiv.org/html/2501.15654v1 (which also confirms that humans that have experience with LLMs are very good at spotting them).

lelanthran 10 hours ago | parent | prev [-]

> > Detect AI-generated content with 99.98% accuracy.

> Though I ran the numbers, and even with a 0.02% false positive rate

They don't say that the false positive is 0.02%, only that the accuracy is 0.02%. All we know for certain is that the false positive and false negatives added together result in 0.02%.