Researcher ships Dehydrate, a tool to strip watermarks from closed-weight LLM text
burkov · x · 2026-10-07
Andriy Burkov criticizes frontier closed-weight LLMs for injecting statistical watermarks (SynthID, textGrain) into paid-for output, warning such text could hurt search rankings or trigger shadowbans. He built Dehydrate for his product ChapterPal: it modifies watermark-embedding word patterns by moving or replacing words, making watermark detection unreliable while preserving sentence and paragraph meaning.
More from Safety
- The AI Doomsday Gap: enterprise clients ask if AI will kill billions, none ask about governance — DavidLinthicum · 2026-10-07
- Common Sense Media calls ChatGPT for Teens an 'unacceptable risk' — The Verge AI · 2026-10-07
- Altman: world should accept some bad things happening for AI's benefits and agency — Duckducklaugh · 2026-10-07
- Commerce Department shut out of new AI task force despite CAISSI's central policy role — ShakeelHashim · 2026-10-07
- Security researcher's old talk predicted ExploitGym — and why it could be problematic — moyix · 2026-10-07
- Researcher slams Anthropic's expanded CVP: 95% of defensive security work still excluded — npinto · 2026-10-07