Text AI Watermarks Are Trivial to Remove, Argues New Technical Post

pseudolus · hn · 2026-08-13

A technical blog post argues that current watermarking schemes for text-based generative AI are fundamentally flawed and can be easily removed. The article breaks down the technical reasons behind the fragility of these watermarks, questioning their practical efficacy as a security and alignment measure.

Original post →

More from Safety

Safety channel →