Simon Willison — 2026-07-03#

Highlight#

Simon’s practical prompt engineering tip for Claude Code is a brilliant way to preserve expensive API tokens while maintaining high-quality output. By directing the top-tier Claude Fable model to act as a manager that delegates implementation to smaller models, he showcases a very pragmatic approach to operating AI coding agents locally.

Posts#

Fable’s judgement Following a tip from the Claude Code team at the AI Engineer World’s Fair, Simon explores telling Claude Fable to use its own judgement rather than micro-managing its behavior. He applies this by prompting Claude Code to spawn subagents running lower-power models (like Sonnet or Haiku) for mundane coding tasks, reserving Fable for high-level design and review. The result is a highly effective workflow that saves on valuable tokens ahead of looming price increases.

Simon Willison — 2026-07-04#

Highlight#

The standout post today touches on a fascinating and slightly troubling trend in LLM tool use: state-of-the-art models like Opus 4.8 might actually be worse at interacting with custom developer tools because they are over-optimized for their proprietary, first-party environments. This highlights an emerging friction point for developers building third-party AI agents and coding harnesses.

Posts#

Better Models: Worse Tools · Source Armin Ronacher discovered that newer Anthropic models, specifically Opus 4.8 and Sonnet 5, are failing to correctly use custom tool schemas in his Pi coding harness by hallucinating extra fields, a regression not seen in older models. He theorizes this happens because these newer models are heavily trained via Reinforcement Learning to perfectly use the specific edit tools integrated directly into Claude Code. Simon points out that OpenAI models are similarly optimized on their own apply_patch mechanisms, raising the question of whether open-source and third-party harnesses will now need to maintain entirely separate edit tool implementations optimized for each specific model family.

Simon Willison — Week of 2026-06-25 to 2026-07-03#

Highlight of the Week#

The single most impactful release this week was Simon’s launch of llm-coding-agent 0.1a0, which successfully turns his popular llm library into a full-fledged coding agent capable of file manipulation and command execution. Bootstrapped entirely using Claude Fable 5 via test-driven development, this represents a massive leap forward for his CLI ecosystem and a brilliant showcase of using frontier models to build the very tools that will orchestrate them.