A McCartney-Style Music Generator Built Without AI Learning
The author used Claude Fable 5 to analyze Paul McCartney's composition techniques-repeated notes over shifting chords, irregular phrase lengths-and built a generator that produces chord progressions and melodies using those rules.
1 source Jul 14
Reporting from 1 source: GameBusiness.jp.
Why it matters
The experiment demonstrates that a rule-based generator can replicate stylistic hallmarks of a specific artist without using any training data, offering a different path from AI music generation.
The algorithm does not use any song learning data, offering a rule-based alternative to AI music tools like Suno.
Claude Fable 5 identified several hallmarks of Paul McCartney's songwriting, including repeated notes over shifting chords and irregular phrase lengths. The author then coded a generator that applies these rules to create new chord progressions and melodies. Unlike AI music tools that learn from large datasets, this generator uses no song data at all. The result is a composition tool based entirely on explicit musical analysis rather than statistical patterns.
Written with AI by Yomimono from the 1 cited source below, including Japanese-language reporting where cited. See our editorial policy.
Add Yomimono as a preferred source on Google