Only 2 of 25 full ChatGPT rewrites flagged 100% AI by detectors
paulnovosad · x · 2026-10-26
Paul Novosad's test: ChatGPT G5 full rewrites of 25 essays—only 2 flagged as 100% AI-generated. AI keeps most of your original words; consistent 100% AI flags likely mean the first draft wasn't yours.
More from Models
- Fintech insiders' AI consensus: ChatGPT, Claude and Grokbot top the pack — LexSokolin · 2026-10-26
- DeepSeek-adjacent researcher hints next model will keep the V3.2 DSA approach — YouJiacheng · 2026-10-26
- Anthropic S-1: 1,300% YoY revenue growth, 85% gross margin — danshipper · 2026-10-26
- EMNLP paper: tweaking multiple-choice scoring schemes reshuffles LLM leaderboards — boydgraber · 2026-10-26
- AI answers can cite real, working sources and still be flat-out wrong — alifcoder · 2026-10-26
- Kimi K3 needs ~1 TFLOPs per decoded token while V4.1F needs only 50 GFLOPs — YouJiacheng · 2026-10-26