Fresh Reads

It's time for a change in schedule and format. Short weekly writing is too shallow when you have AI. I am pivoting: longer, timeless, full technical overviews, once every few weeks.

The skill of writing code will become obsolete eventually, we are getting there faster and faster. And if writing code has not much value anymore, you need to shift your focus. Here is what I am doing.

Discussions about code are getting less and less relevant. We reached a level above it: how to automate your entire pipeline. Here is how I am doing this.

Iteration after iteration, the effect-machine API reached a more stable API. And, guess what, it looks really close to XState. Let's see an example then.

State machines in effect is a question of time. I am working from multiple angles to ensure this will come, soon, sooner. Here are the latest updates of what's happening.

Welcome to the new era of open source development with AI. You can move way faster, the scope can explode with ease, and you may find yourself prompting a lot. It's not easier.

If before writing was the most effective tool to organize ideas, now it has a competitor in AI. Yes, but they can also work together. And they work on different levels and situations.

If you write code, you want your API to be clean, concise, and beautiful. Less explicit, less verbose. Agents may be the opposite. Give them a full explicit API, and don't leave anything hidden.

Library development is changing as well with agents. The principles are the same as app code: as much linting, tests, and static checks as possible. With that in place, internals can move, fast.

The new @typeonce/effect-machine library is out, and it brings state machines and state charts into effect. Composable and fully type safe, just like effect. Let me give you an introduction.

It wasn't even a year ago when most devs stopped writing the code. The first revolution. We are now entering the second phase of AI coding: stop reading your code as well. Let me show you how.

AI model releases and trends seems to be speeding up even more than before. But you don't need to follow all the details. Here is what I am focusing on to keep up with AI without being overwhelmed.

With AI, you can do more than ever before. Bigger tasks in parallel. And not only in code. But more does not necessarily means more hours, that's a trap.

AI, so fast and easy, just prompt and watch. Well, turns out it may be too easy. So easy in fact, that you can always start another project, without stopping to think if you really need it.

The new major version of XState (v6) is now out in alpha and ready to be tested. I already migrated a full codebase and sent 7 PRs with improvements. Let's see what's new.

The new trend in AI coding is called loops. Well, in reality those are just subagents. Yes, subagents that you don't manage, but another AI does for you. And you just watch, and review.

Writing code used to be a fully offline experience. It's writing text after all. But AI changed that as well. Without connection, do you wait, or do you write manually?

AI writes code fast. AI in a loop is even faster. But you are still the reviewer, are you? Here are a few ways to slow down AI to your pace, will keeping up fast mode.

AI is writing more and more of your code. You don't even need to be precise, the AI will figure out the details for you. Well, too much of this, and you stop learning. This is how I am preventing this.

Do you want to maximize your AI output? Well, you can technically run as many agents as possible, but turns out it may not be that easy, nor a successful strategy.

I released my first post-AI article this week. Are technical articles still needed with AI? Well, yes, but not all kinds. Here is how I am thinking about this, and what I will keep reading.

Most frontend bugs are hidden behind confused business logic and race conditions inside components. Easy solution: make all components dumb, no business logic inside them, and let AI take care of them.

Effect is taking over the TypeScript ecosystem, now faster than ever before. I have been running effect everywhere for a while: here is what you will get on the other side once all becomes effect.

AI codes fast. Too fast for you to review that much slop code and bad patterns. But there is a solution: prevent bad patterns altogether with custom linting rules. Here is how I do this.