I’m just back from watching Mastering Claude Code in 30 Minutes, a talk by Boris Cherny, who, I learned, created Claude Code. I was struck by Boris’s reply to one question from the crowd: Hey, why did you build a CLI tool instead of an IDE? Yeah, it’s a good question. There are two reasons. We started this at Anthropic, where people use a broad range of IDEs. Some people use VS code. Other people use Zed, Xcode, Vim, or Emacs. And it was just hard to build something that works for everyone. And so the terminal is just the common denominator. The second thing is that at Anthropic, we see firsthand how quickly the model is improving. I think there’s a good chance that by the end of the year, people won’t use IDEs. And so, we want to prepare for this future and avoid over-investing in UI and other layers on top. Given the way the models are progressing, it may not be practical to work on them soon. ...

Despite what tech CEOs might say, large language models are not smart in any recognizably human sense of the word.

Why Bell Labs Worked is a fascinating, evocative read. We live in a metrics obsessed culture that is obsessed with narrowly defined productivity. There’s too much focus on accountability and too little focus on creativity. The reason why we don’t have Bell Labs is because we’re unwilling to do what it takes to create Bell Labs — giving smart people radical freedom and autonomy. The freedom to waste time. The freedom to waste resources. And the autonomy to decide how. ...

Federico Pereiro’s Being Fat is a Trap is, I think, a great piece of advice. Way more people than I wish who are close to me are struggling with eating disorders of all kinds, so I’m sensible about the topic. This sentence, in particular, rings true in an aching way: Judging people inside the fat trap just intensifies their misery and reduces the odds they can get out of it.

Since yesterday, Claude Code has been included in the Pro subscription we’re signed up for. I’d been wanting to try it for a while, and now nothing was stopping me. Only yesterday (a curious coincidence), I read AI Changes Everything by Armin Ronacher, which gave me a glimpse of the potential and made my hands itch to try it. The initialization of Claude on the repository surprised me; the analysis (reported in CLAUDE.md) is thorough and reveals a good understanding of the project, including both the code and the general functioning, strategies, techniques, technologies and libraries employed. ...

Knowing when to leave might be more important than knowing when to show up. – kupajo in When to Leave

Today’s Armin Ronacher’s AI Changes Everything strongly resonates with me1. I may not be using Claude Code as a daily driver as he now does, but I’ve slowly and steadily introduced large language models (LLMs) into my routine, and I’m reaping the benefits. It wasn’t the purpose of his article, but I wish Armin had gone into the details of how, why, and when he delegates tasks to Claude Code. Update: Armin later a follow-up. ...

In Moving On, Simone Silvestroni recounts how he moved away from the Apple ecosystem. It’s a move I’ve been contemplating for some time. Like Simone, I use Linux at work daily so that the task wouldn’t be too much of a stretch, but I’m probably too lazy (or too old) to execute it.

Run Your Own AI by Anthony Lewis is a concise tutorial on how to run large language models on your laptop from the command line via llm-mlx. It focuses on Macs M-series, but it’s also suitable for other hardware. Saving it here for a friend.

Eve v2.2.1 was just released on PyPI. It is a minor upgrade, but it includes a remarkable performance increase contributed by Alexander Urieles. Also, thanks to Svante Bengtson and Pablo Parada for their help with this release.