Newsletter Archive

All about AI evals, plus how Braintrust helps companies build better AI apps.

Things you should know as a vibe coder that will make your app actually work / not die.

And why building AI products requires new forms of infrastructure for developers.

How computers learn patterns from data: the foundation for everything from stock price prediction to ChatGPT.

Why AI models hallucinate, why building MCP servers is hard, and the scaling law driving trillion-dollar AI bets.

AI experts all HATE this one law!!!

A brief history of the protocol, why it can be hard to use, and how FastMCP came to be.

AI models inherently make stuff up. What can we do about it?

A beginner’s guide to AI model architectures, why open source licenses aren’t as simple as “free to use,” the evolving role of product documentation, and what Databricks is really building.

Or perhaps more accurately: what does Databricks NOT do?

Why sometimes, you need to tell people how to do things

Unlike an onion, hopefully these neural network layers won't make you cry.

Why GPUs are a great fit for AI, how generative models actually work, and how JavaScript became the most popular programming language in the world.

From humble origins to the most popular programming language in the world.

Why these chips pair perfectly with AI, and how NVIDIA became the most valuable company in the world.