Skip to content
NewA calmer, faster ZeroHour
StoryAI industryinfo

Anthropic Watermark Loophole on Older Claude Models

2 sources · 2 articlesFirst reported Updated ()1 · 1 read
What's new

First merged summary.

Merged summary · x-ai/grok-4.7 · rewritten as coverage arrivesSummaries by Vani AI

API users can bypass watermark on Claude Opus 4.6 and Sonnet 4.6 by changing sampling parameters.

Anthropic expands text watermark to four Claude models but API users dodge it on two older ones via tweaks to temperature, top_p or top_k. The company retrofits older models to meet the EU AI Act deadline. Watermark uses a Google DeepMind SynthID variant and applies at model level across hosting platforms.

Key facts
  • Watermark applies to Claude Mythos 5, Opus 4.7, Opus 4.6 and Sonnet 4.6
  • Loophole exists on Opus 4.6 and Sonnet 4.6 at default sampling settings
  • Watermark adds no extra tokens or affects pricing or speed
  • Detection API available in private preview
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

Timeline

dated events in the reporting · oldest first
  1. Oct 31, 2026Anthropic expands watermark to four Claude models with API bypass on older versions · The Decoder
Vendors
AnthropicOpenAICloudflareGoogle
Products
Claude SecurityClaude CodeCodex SecurityMantis
AI models
Claude Opus 4.6Claude Sonnet 4.6Claude Opus 4.7Claude Mythos 5

Coverage

oldest first · one row per article · UTC
  1. · 1d ago MarkTechPostFirst report

    Four labs' code-security agents share a find-then-disprove design

    Claude Security, Codex Security, Cloudflare's skill and Google Mantis differ in runtime, access and how much proof they require.

  2. · 1h ago The Decoder

    Anthropic watermark rollout leaves loophole on two older Claude models

    API users can bypass watermark on Claude Opus 4.6 and Sonnet 4.6 by changing sampling parameters.