Using AI Classifiers to DJ: Scoring Which Track Mixes Into the Next
Aizkmusic · x · 2026-10-01
X user Aizkmusic shares an AI classifier demo: song selection for DJing. A mediocre college DJ, the author realized DJing is mostly about picking the right next track, so they built a small tool: whenever a track is loaded into DJ software, it queries Simple Jev to classify every other song in the library on how good a mix it would be, using key, BPM and even vibe from song metadata. They tested with tracks they knew would and wouldn't work until satisfied. A broken DJ controller prevented a live demo.
More from Fun
- If Paper Abstracts Were More Transparent: An Academic Roast — CSProfKGD · 2026-10-01
- Developer wakes up to 6.5 hours of agent-completed work — calls it 2 weeks of his time — therealdanvega · 2026-10-01
- Agent autonomously checks in a flight 24 hours ahead — and pings only on failure — armand_ruiz · 2026-10-01
- Yacine Mocks 'AI Is Conscious' Discourse in Viral Sarcastic Post — yacineMTB · 2026-10-01
- Viral "AI torture chamber" Qwen 3-4B pain-steering repo debunked: broken code, shaky premise — sebkrier · 2026-10-01
- Dev adds Apple's Genie effect to AI agent plugin with Opus, says he's basically built an agentOS — RileyRalmuto · 2026-10-01