https://falcao.org/tags/llm/Recent content in Llm on Danilo Falcão da SilvaHugoen-usSun, 24 May 2026 21:00:00 -0300https://falcao.org/posts/openai-codex-5-3-late-review/Sun, 24 May 2026 21:00:00 -0300https://falcao.org/posts/openai-codex-5-3-late-review/<p>This is a late review. GPT-5.3-Codex shipped on February 5, 2026, and here I am almost four months later writing about it. I have no excuse beyond the usual one — too many things to look at, not enough evenings. But having spent the past few weeks reading benchmarks, watching demos, and following what developers are actually saying about it, I want to be honest: it is a good model. A genuinely good one.</p>https://falcao.org/posts/ollama-the-boring-standard/Mon, 18 May 2026 17:30:00 -0300https://falcao.org/posts/ollama-the-boring-standard/<p>There&rsquo;s a particular kind of project I love: the one that takes something new and weird and turns it into something you barely have to think about. Docker did this for containers. Hugo did it for static sites. In 2026, <strong>Ollama is doing it for open-source language models.</strong></p> <p>You install one binary. You type <code>ollama pull &lt;model&gt;</code>. You type <code>ollama run &lt;model&gt;</code>. Your application talks to <code>localhost:11434</code> over an OpenAI-compatible HTTP API. That&rsquo;s the whole user manual. The fact that this is now boring — that nobody has to argue about it on Hacker News anymore — is the point of this post.</p>