Adaptive Spotify Recommendation Builder

Bubo says they used Jev and Claude to build a Spotify recommendation system using 16,558 songs and eight years of listening history. The build uses adaptive reasoning, and its code is open.

View on X cost$0.31

Bubo@bubosees𝕏

Spotify has 10 years of your data and still recommends the same 20 songs I took Jev + Claude and built what it couldn't in a decade 16,558 songs. 8 years of listening history. 5 steps. $0.31 Spotify has 3 weeks of memory. this has 8 years and adaptive reasoning code is open

Sep 22, 2026X postsView on X

Bubo contrasts the build with Spotify’s recommendations, saying Spotify still recommends the same 20 songs despite having 10 years of data. The source also describes Spotify as having three weeks of memory.

Also filed under Tools & apps

Jev: a "System One" model that only makes decisions, $0.042 per million tokens with output free. 40-second explainer of why it matters for automation
Jev: a "System One" model that only makes decisions, $0.042 per million tokens with output free. 40-second explainer of why it matters for automation Jev launched on Sep 15 from TypeSafe AI (founder Diogo Almeida, ex-OpenAI, credited on ChatGPT/InstructGPT). It does not generate text; it returns typed decisions (Choice / Score / true-false) with confidence. Price is $0.042 per million input tokens, output free. In its first week it became the fastest-adopted model on Vercel's AI Gateway, TypeSafe paused signups on Sep 22, Browser Use released jev-ultrafast (a web agent where Jev picks each action; Google Flights search in 7.1 s), and jaredpalmer/kev is an Apache-2.0 clone built on Qwen3.5 you can run yourself. My take in the video: the expensive part of automation was never the writing, i
Untitled
There's a new AI model that refuses to talk. While everyone debates what a "decision model" is even for, builders already shipped the answer. 7 things people built with Jev in 9 days. Number 5 broke my brain 👇
Memory System Built with Jev
Opium says they made a memory system using Jev and that results are very promising so far.
Deterministic LLM Judge Aid
Fadhli used Jev as a deterministic tool to aid an LLM as a judge (gpt-6) in a synthetic, simple-data use case.