AINewsnow

I Watermarked 100 Texts With SynthID and Asked Local LLMs to Wash It Out. The Detector Still Saw Some of It.

This story is from 2026-10-06. It is preserved in the archive; the latest stories are on the live feed.

In my last post I asked whether a local LLM can rewrite an AI text enough to break its word patterns while keeping the meaning. The answer was yes, with a good 12–14B model. But I only estimated watermark removal by counting how many word sequences survived. I had no real watermark and no real dete…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-10-06 15:00 · DEV Community — Machine Learning
    I Watermarked 100 Texts With SynthID and Asked Local LLMs to Wash It Out. The Detector Still Saw Some of It.

More stories

  1. Mistral Says Its New AI Model ‘Le Chonk’ Is the Best Open-Weight Offering Outside of China — Wired AI
  2. Introducing Mistral Large 4 — Mistral AI News
  3. Introducing GLM 5.3 on Amazon Bedrock — AWS Machine Learning Blog
  4. Sam Altman to Decoded: ‘The world should accept some bad things happening’ for the benefits of AI — Politico Technology
  5. OpenAI safety leader quits, warning AI company’s culture is ‘broken’ — The Guardian AI
  6. Trump’s big AI move: ‘Super Intelligence Force’ launched, Jay Clayton named AI czar — Mint AI
  7. Manage Amazon SageMaker HyperPod Spaces directly from SageMaker Studio — AWS Machine Learning Blog
  8. Evaluating multi-agent systems for explainability and helpfulness with Amazon Bedrock AgentCore — AWS Machine Learning Blog

Get the daily brief of stories like this at 6:30 every morning →