Deft Model Claims to Evade AI Detection with 86% Human-like Score
churchkey · x · 2026-08-19
Deft lab released a new model designed to address AI watermarking and detectable cadence, claiming near-undetectability. According to the model's self-generated announcement, 86% of user queries are rated as fully human by Pangram. Currently in public beta, Deft performs best in analysis, essays, creative writing, and rewrites, but less so for marketing copy and news. Developers suggest adding prompt details or adjusting styles for better performance.
More from Models
- Grok Bot Ran a 12-Hour Data Analysis Nonstop, Handling API Rate Limits Itself — Daniel_Farinax · 2026-10-16
- One year of Recursive Language Models: GPT-5-mini beats GPT-5 by 110% on 132k-token tasks, cheaper too — a1zhang · 2026-10-16
- Users Report Claude Models Suddenly More Compliant After Forced Compaction — RealSharpNinja · 2026-10-16
- Prediction: Opus 5.5-level models on laptops by 2027, backed by Qwen 27B data — cephaloform · 2026-10-16
- Users Say Krea 2 Output Degraded Sharply Since Krea 3 Beta Launched — szywis · 2026-10-16
- LLM-as-a-Verifier lifts Nemotron 3.5 Super by 9-10 points on agentic benchmarks — simonguozirui · 2026-10-16