<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom"><title>Ju Lin's AI Weblog: Rust</title><subtitle>An independent research notebook on AI engineering, agents, models and the systems around them.</subtitle><id>https://julin.ai/atom/tags/rust/index.xml</id><link rel="self" type="application/atom+xml" href="https://julin.ai/atom/tags/rust/index.xml"/><link rel="alternate" type="text/html" href="https://julin.ai/tags/rust/"/><author><name>Ju Lin</name></author><updated>2026-11-02T00:00:00+13:00</updated><entry><title>Rust vs C for AI Agents</title><id>https://julin.ai/2026/11/02/rust-vs-c-for-agents/</id><link rel="alternate" type="text/html" href="https://julin.ai/2026/11/02/rust-vs-c-for-agents/"/><published>2026-11-02T00:00:00+13:00</published><updated>2026-11-02T00:00:00+13:00</updated><category term="agents"/><category term="rust"/><category term="c11"/><category term="formal-verification"/><category term="small-python"/><content type="html">&lt;p&gt;AI agents are good at producing Rust code, way too good. But I think it&amp;rsquo;s worth evaluating whether agents would do the same using the C language. I wonder if there is a formal investigation on Rust vs C regarding development velocity.&lt;/p&gt;
&lt;p&gt;Rust is known for memory safety, but that doesn&amp;rsquo;t mean a program written in C is memory unsafe, especially with the recent trend of adding formal verification (TLA+, Lean, Blend, etc.) to code. It used to be impractical to ship something like TLA+ specs along with C code, but with AI it&amp;rsquo;s almost zero friction.&lt;/p&gt;
&lt;p&gt;As a result, when I was working on &lt;a href="https://github.com/soasme/small-python/"&gt;Small Python&lt;/a&gt;, in one of the sessions Claude Code kept trying to find ways to segfault the program, yet it failed. After several hours of trying, it gave up and claimed the implementation was rock solid.&lt;/p&gt;</content></entry></feed>