Musicians say AI music sounds generic because users lack music theory, not because models do
teropa · x · 2026-09-11
A discussion among musicians (@gh0stn, Adam Neely) argues that AI music sounds generic because most people prompting these models don't understand music.
Once musicians can prompt with real theory — e.g. "18ed2 x 13ed3 polysystemic serialism, 420 bpm, nested 3:5:9 paradiddle, occasional 11-limit just-intonation approach notes" — the model becomes a capability amplifier for the knowledgeable, not a mediocrity machine.
Takeaway: the ceiling of AI music output tracks the user's musical literacy.
Related event: Musicians Say AI Music Sounds Generic Because Users Lack Theory(2 posts)→
More from Multimodal
- H3 Max video endpoint teaser blurs the line between real and AI footage — noahsolomon · 2026-09-11
- 14-Year Editor Tests GPT-6 Astra: It Watched 84 Clips, Cut, Scored and Subtitled in DaVinci Resolve — TheMoonMidas · 2026-09-11
- Tip: Astra performs much better with a clear goal and reference images — Silver-Chipmunk7744 · 2026-09-11
- Suno launches v6-wild for users who miss the grit of older models — suno · 2026-09-11
- Best open-source image model for text and posters? Krea2 and Klein 9B garble text — Ok-Flatworm5070 · 2026-09-11
- TDDN Fuses DINOv3 with CleanDIFT, More Than Triples CLIP's Dense Prediction Accuracy — udmrzn · 2026-09-11