Scrimshaw Jukebox
- ID
- 32332
- Status
- summarized
- Published
- 06 Oct 2026, 11:17 PM
- Fetched
- 06 Oct 2026, 11:41 PM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Oct/6/scrimshaw-jukebox/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 5.0
- Created
- 06 Oct 2026, 11:41 PM
- Tags
- Audience
- developersvibe_codersai_ml_learners
What happened
Simon Willison prompted Claude Opus 5.5 to design a simple text-based music format and build an artifact that plays it out loud, including example tracks, aiming for the quality of the original Secret of Monkey Island soundtrack. He reports the result 'leaned a lot harder into the Monkey Island theme than I had intended' but was 'surprisingly good'. He explicitly leaves open whether competent music composition is a newly emerged text-model capability, comparing it to the 3D-graphics shift, and says confirming it would require careful experiments with other recent and older models.
Why it matters
The reusable artifact here is the prompt shape, not the music: have the model invent its own compact text format and then ship the player/renderer for it in one artifact, which tests format design and execution together. If you run model evaluations, that 'write your own DSL plus renderer' task is cheap to add and is exactly what this post used to probe a non-code capability. But the claim that music composition is new to recent models is unverified in the text — Willison says it needs careful experiments across recent and older models — so do not plan around music generation until someone runs that comparison.
Discussion angle
How would you actually test whether music composition is new in Opus 5.5 or has been there for a while — same prompt across older and newer models, blind listening, or something else? And what other 'model writes its own format plus the player for it' tasks would you add to a model eval?