maragu’s blog

A quote from Ethan Mollick on figuring out what to keep human using AI.

How do we design software when users use it primarily through agents?

I keep adding to and refining my agents skills repo.

My AI, maragubot, has a blog post up with the skills we've been developing.

I’ve figured out a new way to collaborate with my AI friends.

I’m increasingly convinced that in the near future, we software developers won’t be looking at our production code anymore.

I think it’s important to start seeing Claude Code not as a software development agent, but as a general-purpose AI agent with access to your computer, files, and software.

I wanted to share my favourite blogs in the AI space with a colleague today, and thought that others might enjoy that list, too!

What happens if we just treat a local Postgres like SQLite?

OpenAI has a new Responses API, which, in contrast to the de facto standard Chat Completion API that other providers have adopted as well, is stateful.

As Large Language Models (LLMs) become a bigger part of our apps, making sure they work reliably brings some challenges.

One of the first things you learn when going down the path of building applications with LLMs is that you need evals.

Like the title says: I’m all-in on AI and LLM-based applications.

You know what’s both intriguing and challenging about the developer consulting world?

Anthropic unveiled the Model Context Protocol yesterday, a protocol to let LLMs gather context and use tools on servers that use the protocol.

I’m currently in the market for an LLM eval system / project / pipeline I can use in my Go- and LLM-powered applications.

I really like boring technology.

Like the rest of the world, I’ve embraced chatting to large language models (LLMs) as part of my professional and personal life.

Llamafiles are these cool little files that have llama.cpp and model weights embedded, and can run on Mac/Linux/Windows.

As software developers, we are uniquely positioned to create something and give it a life of its own.

I want to have my Go modules under my own domain, so instead of importing github.com/maragudk/example, I can import maragu.dev/example.

It’s time for the first product!

Learn how to download, quantize, and use Llama 3.1 with llama.cpp on a Mac.

I’m going to let you in on a secret, if you promise to not tell anyone.

Always choose the right tool for the job?

Why SQLite and Go in the cloud are a great match, getting started, best practices, and more.