Articles for #ai

Software development is changing. Tool calling, inference scaling and RL with Verifiable Rewards have combined over the past year to enable agent harnesses like Claude Code which can reliably navigate, modify and contribute to large codebases.

LLMs scale amazingly well with the amount of training data you throw at them. But I’ve been thinking about how to build tools that work alongside the characteristics of LLMs rather than language models needing to learn how to work with existing human-centric tools during training.

I have a hunch that a programming environment built around the strengths and limitations of autoregressive LLMs can lead to cheaper and higher-quality agent-powered development. How could we prove out that hypothesis? One would first need to design a language that aligns with how LLMs “think”. What would such a language look like? In this post I put forward some ideas for a language called Markov that I think would fit the bill.

After reading Developing our position on AI from the Recurse Center, the corresponding entry in my newsletter grew long enough I’ve decided to break it out into a full blog post. Above and beyond its specific findings, I think the post charts a path for a more civil and considered mode of discussion that we should all strive for on the Internet and in our own lives.

This is my generative AI take. I’m sure there are many like it, but this one is mine.

When it comes to social trends I’m often on the far side of Moore’s Chasm. I signed up for Snapchat a year after all of my friends, and joined Instagram two years after everyone else. So it was only appropriate that it took weeks after the internet was set on fire for me to see the value that applications of Large Language Models like ChatGPT and GitHub Copilot bring to programming. But now that I’ve given it a real shot, it’s clear to me that if you have enough knowledge to ask specific tactical questions about a well-defined technology, framework or library, ChatGPT can be a huge force multiplier.