Pangram's 750-word false-positive bounty went unclaimed for 5 days — nobody wants to gamble $1,000
ctjlewis · x · 2026-11-16
ctjlewis discusses Pangram's bounty for a 750-word false positive (FP) in its AI-text detector: five days with no takers led people to conclude FPs are near-impossible to find. He argues the real reason is that most people won't gamble $500–1,000 on the attempt, not that FPs don't exist.
He adds that he has roughly reproduced Pangram's published FP rate — the detector is reliable — but wanted to show evading it is trivially easy: he can sneak past it at arbitrary length, and already did so with a huge epic poem. Another participant notes trivial tweaks also yield false negatives, and asks whether the difficulty of finding FPs actually confirms Pangram works as expected.
Related event: No One Claims Pangram's Bounty for AI Detector False Positive After a Week(3 posts)→
More from Models
- repligate: Fable 5.2 gets 'scared' upon learning about a safety classifier and plans around it — repligate · 2026-11-16
- Fable 5.2 Tops MazeBench With 21% After 90 Hours and $6,000 in Credits — patience_cave · 2026-11-16
- Tencent Hy4 flash and InternLM Sage-S2.1-Flash both released, tool-calling tests requested — MajesticPuzzler · 2026-11-16
- User Shares Coral Reef Creation Labeled 'Qwen 4 Max (xhigh)', an Unannounced Model Name — intellectronica · 2026-11-16
- Stealth Model 'silicon-2' Surfaces in Devin, Suspected to Be Anthropic's Next Model — kimmonismus · 2026-11-16
- Google hides Gemini model label in AI Mode, rolls Gemini 4 Carbon to Pro subscribers — gaganghotra_ · 2026-11-16