Create

Sign in to ReadmeX

Sign in to join communities, post, vote and chat.

New here?

Story

Claude Opus 5.5 composes retro game music in Scrimshaw Jukebox test

AI summary

On his blog, Simon Willison tested whether Claude Opus 5.5 could compose music, asking it to first design a simple text-based music format, then build an artifact that plays it aloud with example tracks, aiming for the quality of the original Secret of Monkey Island. The result was "Scrimshaw Jukebox," a pixel-art browser player containing six original adventure-game tracks (Moonlit Harbor, The Ghost Galleon and others), written as plain text and performed by an in-browser synthesizer with a piano-roll score view and editing. Willison called the output "surprisingly good" while noting it leaned harder into the Monkey Island theme than he intended.

Why it matters: It is another anecdotal signal that text models may be gaining non-text creative capabilities, though the author says careful comparisons with other recent and older models are needed to confirm whether this is genuinely new.

AnthropicClaude Opus 5.5Scrimshaw Jukebox

5
Source textSimon Willison's Weblog · 2 min read

I wanted to see if Claude Opus 5.5 could compose music, so I tried this:

I want you to write some computer game music for me. First design simple text based format for the music and build an artifact that can play it out loud - include some example tracks in that artifact

I am looking for music of the quality of the original secret of Monkey Island

It leaned a lot harder into the Monkey Island theme than I had intended, but the results are surprisingly good.

I wonder if the ability to compose competent music is similar to the 3D graphics thing - a new capability for text models that emerged in the past few months?

Would need some careful experiments with other recent and not-so-recent models to confirm if this is new or if they've been able to do this for a while.

Read the original →

How we got here

  1. Insurers Prepare for AI Agent Liability ClaimsThe Decoder · Anthropic
  2. Interconnects: open-weight cyber-risk discourse is brokenInterconnects · Anthropic
  3. Whistleblowers Say AI Researchers Are Checking Work Less OftenThe Information · Anthropic
  4. TechCrunch Disrupt 2026 publishes AI-focused breakout agendaTechCrunch AI · Anthropic
  5. Claude Threat Detection Reportedly Leads to Florida ArrestTechRepublic · Anthropic
  6. Ben's Bites: four kinds of AI users, and why personal agents aren't there yetBen's Bites · Anthropic

Comments

I've used this: share my experience What I think: share my view
How important is this story?No ratings yet

No comments yet. Start the conversation.