Quoting Prompting Claude Fable 5.2

Anthropic's testing of Claude Fable 5.2 on small coding tasks found that telling the model the codebase is its own raised the rate at which it merged repeated code to about half of tries, versus under a tenth without that sentence, according to Anthropic documentation cited by Simon Willison. When a prompt said nothing about ownership or framed the code as someone else's, the model tended to add to the existing structure even when that repeated existing code. The documented prompt reads: "This codebase is yours: what it's for and how it's built are your call, and you'll keep building on it.

Claude Fable 5.2 responds closely to what the prompt says about who owns the code it works on. In Anthropic’s testing on small coding tasks, when a prompt said nothing about ownership or presented the code base as someone else’s, the model tended to add to the existing structure, even when that repeated existing code. ... If you want the model to improve the structure as it works, say that the code is its own: This codebase is yours: what it's for and how it's built are your call, and you'll keep building on it. In Anthropic’s testing on small coding tasks, the model merged repeated code in about half of the tries with this sentence, and in under a tenth of the tries without it. — Prompting Claude Fable 5.2 https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2 say-who-owns-the-code , Anthropic documentation Tags: prompt-engineering https://simonwillison.net/tags/prompt-engineering , anthropic https://simonwillison.net/tags/anthropic , generative-ai https://simonwillison.net/tags/generative-ai , ai https://simonwillison.net/tags/ai , llms https://simonwillison.net/tags/llms , claude-mythos-fable https://simonwillison.net/tags/claude-mythos-fable