Fable's judgement
Simon Willison’s Weblog
Subscribe
Sponsored by: Sonar — Gartner just named Sonar a Leader in the 2026 Magic Quadrant™ for Technical Debt Management Tools. Read the report and learn how to measure and remediate technical debt across your codebase. Get the report
3rd July 2026
One of the most interesting tips I got from the Fireside Chat I hosted with Cat Wu and Thariq Shihipar from the Claude Code team at AIE on Wednesday was to let Fable (and to a certain extent Opus) use their own judgement rather than dictating how they should work.
The example they gave was testing. You can tell Fable "only use automated testing for larger features, don't update and run tests for small copy or design changes" - but it's better to just tell Fable to use its own judgement when deciding to write tests instead.
Jesse Vincent just gave me a related tip to help avoid burning too many of those valuable Fable tokens in the few days we have left before the prices go up. Tell Fable to use other models for smaller tasks, applying its own judgement about which model to use.
I prompted Claude Code just now with:
For all coding tasks use your judgement to decide an appropriate lower power model and run that in a subagent
Claude saved this memory file in ~/.claude/projects/name-of-project/memory/delegate-coding-to-subagents.md:
name: delegate-coding-to-subagents<br>description: Simon wants coding tasks delegated to subagents running an appropriately lower-power model<br>metadata:<br>node_type: memory<br>type: feedback<br>originSessionId: 30068d78-43a9-4fb1-bb29-9799e18c526a
Stated by Simon on 2026-07-03: "For all coding tasks use your judgement to<br>decide an appropriate lower power model and run that in a subagent."
Why: cost/efficiency — implementation work rarely needs the top-tier<br>model; judgment, review, and synthesis stay with the main loop.
How to apply: when a task in this project is primarily writing/editing<br>code, spawn an Agent with a model override (sonnet for substantive<br>implementation, haiku for trivial/mechanical edits) and a self-contained<br>prompt; review the result in the main loop before committing. Design,<br>auditing, data synthesis, and anything judgment-heavy stays in the main<br>model. See also [[project-goals]].
So far it seems to be working well. I'm getting a ton of work done and my Fable allowance is shrinking less quickly than before.
Posted 3rd July 2026 at 6:51 pm
Recent articles
sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25) - 5th July 2026
Have your agent record video demos of its work with shot-scraper video - 30th June 2026
Porting the Moebius 0.2B image inpainting model to run in the browser with Claude Code - 22nd June 2026
This is a note by Simon Willison, posted on 3rd July 2026.
ai<br>2,103
prompt-engineering<br>191
generative-ai<br>1,860
llms<br>1,827
anthropic<br>305
claude<br>288
coding-agents<br>219
claude-code<br>121
claude-mythos-fable<br>23
Monthly briefing
Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.
Pay me to send you less!
Sponsor & subscribe
Disclosures
Colophon
©
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026