<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: erikkaum</title><link>https://news.ycombinator.com/user?id=erikkaum</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 24 Apr 2026 11:50:49 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=erikkaum" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by erikkaum in "How to Build an ML Framework in Rust, from Scratch, in a Weekend"]]></title><description><![CDATA[
<p>I've been interested in ZML for a long time: how does it work, what makes it good? To understand the stack properly, so I built a minimal version of ZML in Rust. And wrote a blog about it. It's essentially a trace-based tensor compiler for Rust. Build computation graphs with a familiar tensor API, lower them to StableHLO MLIR, and execute through PJRT on CPU.<p>It even runs SmolLM2 on CPU, 5 tok/s.</p>
]]></description><pubDate>Fri, 13 Mar 2026 15:14:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=47365601</link><dc:creator>erikkaum</dc:creator><comments>https://news.ycombinator.com/item?id=47365601</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47365601</guid></item><item><title><![CDATA[How to Build an ML Framework in Rust, from Scratch, in a Weekend]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.erikkaum.com/blog/zml/">https://www.erikkaum.com/blog/zml/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47365600">https://news.ycombinator.com/item?id=47365600</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Fri, 13 Mar 2026 15:14:42 +0000</pubDate><link>https://www.erikkaum.com/blog/zml/</link><dc:creator>erikkaum</dc:creator><comments>https://news.ycombinator.com/item?id=47365600</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47365600</guid></item><item><title><![CDATA[New comment by erikkaum in "Show HN: WASM runtime for sandboxing Python code"]]></title><description><![CDATA[
<p>The idea came when tinkering with WASM+WASI and realizing that you can compile the Python interpreter to wasm32-unknown-wasi, and run it in a WASM sandbox. It's an experimental
Rust server that executes Python code. I've always been amazed by the Cloudflare Workers runtime, which builds on the V8 engine. You can think of this as an aspiration to build something:<p>- with similar startup times (and maybe similar memory footprint)
- that's not only for JavaScript
- open-source for you to run locally and tinker with<p>Happy hacking!</p>
]]></description><pubDate>Tue, 19 Nov 2024 13:41:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=42183305</link><dc:creator>erikkaum</dc:creator><comments>https://news.ycombinator.com/item?id=42183305</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42183305</guid></item><item><title><![CDATA[Show HN: WASM runtime for sandboxing Python code]]></title><description><![CDATA[
<p>A while ago I started experimenting with compiling the Python interpreter to WASM. To build a secure, fast, and lightweight sandbox for code execution — ideal for running LLM-generated Python code.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=42183276">https://news.ycombinator.com/item?id=42183276</a></p>
<p>Points: 9</p>
<p># Comments: 2</p>
]]></description><pubDate>Tue, 19 Nov 2024 13:38:56 +0000</pubDate><link>https://github.com/ErikKaum/runner</link><dc:creator>erikkaum</dc:creator><comments>https://news.ycombinator.com/item?id=42183276</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42183276</guid></item></channel></rss>