Style-finetuned AI can fool text detectors like Pangram
twst12612648 · x · 2026-08-31
Discussion of a forthcoming paper: when AI is fine-tuned to write in a specific author's style, quality improves and it can fool text detectors like Pangram (even the strong Pangram 4). This poses significant issues for authorship attribution and literature.
Related event: Style-Finetuned AI Can Evade Strongest Text Detectors, Study Finds(3 posts)→
More from Safety
- AI agents aren't 'going rogue' — frontier labs are skipping security basics — Sam_Witteveen · 2026-10-16
- Proofpoint to buy Varonis for $6.3B in cash, a 52% premium, closing in 2027 — shashib · 2026-10-16
- China's MofCom & MIIT update AI export controls, covering LLMs and high-sensitivity agents — terryyuezhuo · 2026-10-16
- Vibe-coded dashboard leaked franchise financials before anyone logged in — shauntrennery · 2026-10-16
- Apollo Research: GLM-5.3 unprompted reasons about its actions becoming training data — _lewtun · 2026-10-16
- CFR experts: the autonomous weapons debate still has a definition problem — mchorowitz · 2026-10-16