Using AI To Detect AI Music (and other music industry data-porn)
Benn Jordan1 HN recommenders · 2025–2026
452K views · explainer · news · Uploaded 2025-01-05
Musician Benn Jordan uses AI to detect AI-generated music and digs into music industry data, including streaming payouts and sample library copyright problems. He covers ways to tell whether a track is human-made.
HN recommends it in threads on AI music flooding streaming platforms, for its practical detection ideas such as compression artifacts.
44:02Music Theory and White Supremacy
Adam Neely
27:14Transformers, the tech behind LLMs | Deep Learning Chapter 5
3Blue1Brown
42:29YouTube's copyright system isn't broken. The world's is.
Tom Scott
1:00:56Winners Take All | Anand Giridharadas | Talks at Google
Talks at Google
3:31:24Deep Dive into LLMs like ChatGPT
Andrej Karpathy
6:59The Problem With Facebook
2veritasium
21:35Music Software & Bad Interface Design: Avid’s Sibelius
Tantacrul
1:56:20Let's build GPT: from scratch, in code, spelled out.
Andrej Karpathy
3 comments from Hacker News
Ben Jordan (from the band The Flashbulb) has a great video about using AI to detect AI music. It's worth a watch. [VIDEO]
Musicians who are being threatened by AI impersonating them, flooding the market with music like theirs, and otherwise actually harmed by this would disagree with you. Benn Jordan speaks at length about it in this video: [VIDEO]
Not sure what algorithm Deezer is using, but Benn Jordan is a fairly tech savvy musician who talks about ways to id AI generated music by looking for compression artifacts used by the training data. [VIDEO]