NEWS · MODELS · #3083
Anthropic to retrofit text watermark onto four older Claude models; two are bypassable by sampling tweaks
Anthropic emailed API customers saying it will add an imperceptible text watermark to Claude Opus 4.6, Opus 4.5, Sonnet 4.5 and Haiku 4.5 starting Nov. 16, 2026 (Amazon Bedrock rollout may lag). On those older models the watermark only activates when temperature, top_p or top_k are left at their defaults, so changing any one of those sampling parameters can evade the mark; Anthropic also offers a private-preview detection API and cites the EU AI Act deadline.
KEY POINTS
- Anthropic emailed API customers saying it will add an imperceptible text watermark to Claude Opus 4.6, Opus 4.5, Sonnet 4.5 and Haiku 4.5 starting Nov.
- 16, 2026 (Amazon Bedrock rollout may lag).
- On those older models the watermark only activates when temperature, top_p or top_k are left at their defaults, so changing any one of those sampling parameters can evade the mark; Anthropic also offers a private-preview detection API and cites the EU AI Act deadline.
WHY IT MATTERS
This matters because model-level watermarks are being deployed for regulatory compliance and provenance, but the sampling-parameter loophole lets API users evade detection, weakening enforcement and forensic value.