Anthropic Adds 2 Sentences to Claude Code to Stop AI Video Game Clones

Anthropic added two sentences to Claude Code’s prompt for its Opus 5.5 model to prevent it from recreating specific existing video games. Developers say the filter also blocks crash-dump analysis, anti-cheat work and debugging on their own projects, according to BeInCrypto. Anthropic technical staff member Addy Osmani confirmed the change on X on October 30, citing its policy against intellectual-property infringement, and said the guardrail would be tuned further. The move comes ahead of Anthropic’s Nasdaq debut; its IPO prospectus, filed October 26, flags liability from third-party misuse and books a $1.5 billion authors’ settlement as a 2025 expense.