A Reader Asked Whether a Hotter Rewriter Washes Out SynthID Faster. I Ran the Sweep.
In my SynthID post I rewrote 100 watermarked texts with three local models, and the detector still saw a trace in most of them. Every rewriter ran at one sampling setting: temperature 0.7, with Ollama's defaults of top-p 0.9 and top-k 40. I never varied it. A reader asked the obvious question. Synt…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-10-14 16:10 · DEV Community — Machine Learning
A Reader Asked Whether a Hotter Rewriter Washes Out SynthID Faster. I Ran the Sweep.