AI detector debate: economist argues Pangram is the only reliable tool, cites 0 FPR finding
paulnovosad · x · 2026-09-24
Economist Paul Novosad argues that among AI text detectors, "Pangram is the Ferrari" and the only one whose results matter. Responding to a paper skeptical of AI detectors, he notes the paper is unclearly written but did find Pangram achieves a 0% false positive rate on pre-AI text. He acknowledges genuine confusion in the debate but also sees intentional obtuseness among detector opponents.
More from Models
- NVIDIA open-sources Nemotron 3 Diarization, a fast speaker-labeling model for up to 8 speakers — iamrobotbear · 2026-09-24
- Generalist-first beats from-scratch specialized models, argues Boris M. Power — soumitrashukla9 · 2026-09-24
- Why GPT-6's rumored recurrent-depth architecture could change inference economics — panic_in_the_galaxy · 2026-09-24
- Jev, a No-Text Model Claiming 200x Faster Decisions, Sparks 'Is a Well-Formatted Wrong Answer Still a Hallucination?' — jamesbrooksco · 2026-09-24
- Hands-on: Jev Beats Gemini Flash on Accuracy, Latency, and Cost — cantrell · 2026-09-24
- User cancels switch to Codex after Opus 5.5's 40% price cut wins him back — ayushtweetshere · 2026-09-24