hotai.news
← Back to AI Newsflash
AI Briefings / Content Guide
AIHOT · Published on November 3, 2026 at 02:05

Anthropic adds a rule for Claude prohibiting the cloning of existing games

AI Brief

Anthropic recently added a system prompt for the Claude model that prohibits replicating specific existing games, even if they are renamed or claimed to be original. This rule is encoded in a JSON file under the name "tengu_heron_brook" and was confirmed by XDA in the October 30 release of Claude Code version 2.1.314. "tengu_heron_brook" The longer the conversation, the higher the success rate for voice agents. We analyzed 469 agents running both voice and chat in production environments and found an interesting pattern: when conversations become complex, voice becomes the fastest path to solving problems. https://elevenlabs.

Continue looking at this topic

Direct useCodex repair test: when 0007 becomes 7, how do you verify the patch? ↗OpportunitiesDiscovered a skill using Claude Code to create city check-in maps, with a single post receiving 2,315 likes and 3,039 saves. ↗News and AnalysisCan Claude Code prevent writing outside the working directory? What boundaries still need your own verification? ↗Hotly discussed viewsAs AI bookmarks pile up, how do you turn them into useful project leads? ↗

Return to original text

A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.

Open AIHOT original