Anthropic · OpenAI · Claude · GitHub · Wired · Wired
Coders Say They Already Caught Workarounds to Claude’s Invisible Watermarks
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
Within four hours of Anthropic confirming that Claude models would globally embed invisible, machine-readable watermarks into any AI-generated content, developer Guillaume Meyer had published his override.
Key facts
- His code to remove watermarks from Claude-generated text has since gone viral on GitHub, has been bookmarked more than 20,000 times on X, and has drawn more than 100 contributors, with many more
- The technique, called SynthID, was developed by Google, which has been using it to watermark its AI-generated content since 2023
- Of course, this relies on using other large language models which do not insert watermarks—possibly not a safe bet since 190 organizations—providers OpenAI, Microsoft, and Meta among them—have signed
- Within four hours of Anthropic confirming that Claude models would globally embed invisible, machine-readable watermarks into any AI-generated content, developer Guillaume Meyer had published
Summary
His code to remove watermarks from Claude-generated text has since gone viral on GitHub, has been bookmarked more than 20,000 times on X, and has drawn more than 100 contributors, with many more incorporating the technology into their own projects. Meyer and others started investigating how watermarking works after Anthropic announced last week that Claude would adopt it to comply with the European Union’s AI Act. Some are trying to evade the watermarking because they disagree with the idea that all AI-generated content should be labeled as such, Meyer told WIRED, while others, including himself, say they simply relish the technical challenge.