<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Vagner Bessa — Blog</title><description>Articles on AI engineering, LLM agents, and building production software.</description><link>https://bessavagner.com/</link><item><title>A fast molecular-dynamics simulator in pure NumPy</title><link>https://bessavagner.com/blog/fast-molecular-dynamics-in-numpy/</link><guid isPermaLink="true">https://bessavagner.com/blog/fast-molecular-dynamics-in-numpy/</guid><description>A naive molecular-dynamics loop is O(N²) and dies past a few hundred particles. With cell lists, a cutoff Lennard-Jones potential, velocity-Verlet integration, and reduced units, you can simulate thousands of particles in pure NumPy and watch a gas equilibrate.</description><pubDate>Thu, 25 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Running LLM-Generated Code Without Getting Burned</title><link>https://bessavagner.com/blog/running-llm-generated-code-safely/</link><guid isPermaLink="true">https://bessavagner.com/blog/running-llm-generated-code-safely/</guid><description>A practical look at sandboxing the code a language model writes — the threat model, the isolation options, and a minimal Docker setup you can build on.</description><pubDate>Tue, 23 Jun 2026 00:00:00 GMT</pubDate></item></channel></rss>