Kartones Blog

Pseudo-off-topic post today.

Introduction I firmly believe in tool composition.

Review Title: CLI: A Practical Guide to Creating Modern Command-Line Interfaces Author(s): Derick Schaefer Presentation quality is a bit subpar: In general, formatting is what you would expect from a technical book: titles, notes/remarks, code blocks,...

The scenario From time to time, my blog gets fully crawled.

I recently had to explain to a friend what "evals" are.

Review Title: Tidy First?

I am slowly nerd sniping myself into learning more about how Large Language Models work.

I have a few scripts that I run daily, mostly focused around processing stats and recreating my dashboards (static HTMLs with a chart viewer).

After having played for +130 hours the videogame Vampire Survivors, when the follow up, Vampire Crawlers was recently released, I had to play it.

Instead of just saying "LLMs work way better now", I thought that it would be interesting for once to show something more "applied".

Intro I'm heavily leaning towards agentic-driven development, although done "my way": Focused changes, continuous iteration (including on rules, instructions, subagents, etcetera), and unless it is a simple local script, everything done via TDD.

Review Title: AI Engineering: Building Applications with Foundation Models Author(s): Chip Huyen This book provides a broad and structured overview of how modern AI systems built on top of large language models actually work.

I now prefer almost exclusively digital books, but occasionally, they are available only in paper.

Disclaimer: The following reflects personal opinions based on experimentation outside of work.

Things evolve so quickly in the Generative AI space that, if you're not frequently reading about it, you might miss a significant number of changes.