https://hackerpaper.kaipfister.de/p/2607.27183/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=49591277urn:hackerpapers:mention:2607.27183:49591277Sun, 06 Sep 2026 21:46:26 GMT<p>The false positive rate for Pangram 4 is something like one in 24,000.[0] To put that in perspective, the wrongful-conviction (false positive rate) for death-sentenced defendants in the US is estimated conservatively to be around 4.1%.[1] The FP rate for death-sentence convictions is 1,000 times bigger than Pangram’s FP rate. Now, the US criminal system is not a great yardstick for justice. But it goes to show you Pangram is really good evidence that something was LLM generated. It can be an amazing tool for enforcing AI policies in schools, and there ought to be ways to use it with caveats…</p><p><a href="https://hackerpaper.kaipfister.de/p/2607.27183/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL