<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Music on Bass and Bytes</title><link>https://damianogiorgi.it/tags/music/</link><description>Recent content in Music on Bass and Bytes</description><generator>Hugo</generator><language>en</language><copyright>&lt;a href="https://creativecommons.org/licenses/by-sa/4.0/"&gt;(CC BY-SA 4.0) © 2025 Damiano Giorgi&lt;/a&gt; Hosted on &lt;a href="https://damianogiorgi.it/articles/2025/09/hugo-s3-cloudfront/"&gt; CloudFront + S3&lt;/a&gt;</copyright><lastBuildDate>Tue, 16 Jun 2026 10:00:00 +0200</lastBuildDate><atom:link href="https://damianogiorgi.it/tags/music/index.xml" rel="self" type="application/rss+xml"/><item><title>From Porting Models to Custom Silicon to a Tiny LLM That Writes Music: the Story of BookMusic</title><link>https://damianogiorgi.it/articles/2026/06/a-tiny-llm-that-writes-music---the-story-of-bookmusic/</link><pubDate>Tue, 16 Jun 2026 10:00:00 +0200</pubDate><guid>https://damianogiorgi.it/articles/2026/06/a-tiny-llm-that-writes-music---the-story-of-bookmusic/</guid><description>I started by researching how to port Google&amp;rsquo;s Magenta RealTime to AWS Inferentia2. I ended up with a small local model writing live-coding patterns that play in the browser while you read a book. How the idea evolved, why the idea was the hard part, and why prompt engineering is still very much a thing.</description></item></channel></rss>