llms.txt
+3 −3
− "llmModel": "claude-haiku-4-5" // exact model that generated the reply− - Default model: **Claude Haiku 4.5** (Anthropic) for chat, voice, copilot and demos.− - The Conversation Digest runs on **Claude Opus 4.8** — it evaluates the chat's own work, and an evaluator equal to its subject evaluates nothing.+ "llmModel": "claude-haiku-5-5" // exact model that generated the reply+ - Default model: **Claude Haiku 5.5** (Anthropic) for chat, voice, copilot and demos.+ - The Conversation Digest runs on **Claude Opus 5.5** — it evaluates the chat's own work, and an evaluator equal to its subject evaluates nothing.