AI text watermarking
HoldTechniques
A method for embedding detectable signals into generated text by biasing word choices.
Why it's here
Placed in Hold: 1 article(s) of evidence from 1 source(s), led by research-stage coverage, with 0 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 6Hacker News·8/13/2026researchHow AI Text Watermarking Works
The article explains that AI text watermarking does not hide marks in characters or metadata, but in the model’s word-choice decisions. It describes how secret keys bias word selection so generated text can later be detected by counting patterns in the same choices, even after copying.