Ramble on
Information Overload
026 / by Sebastian De Deyne

I have a blank canvas problem. I'm way better at staying in flow when I have something to work through, so these days, the first thing I do is ramble.

I open Codex or Spiral, turn on Monologue (my preferred text-to-speech tool), and dump everything I can think of on the topic. Before Monologue, I never considered typing speed to be a bottleneck. My fingers move faster than the speed I shape ideas. But when I want to vomit a bunch of unstructured thoughts onto a canvas, they suddenly feel slow and error-prone.

Instead, I can start a task by talking through it to generate a transcript. Then I ask an agent to structure my ramblings (the other day, the agent responded with "Your brain dump is rich."—probably the nicest compliment I've ever gotten from a robot!). This gives me a great starting point to really dig into the problem. Before I know it, I will have rewritten all that rambling into coherent a string of thought.

I still can't shake the dystopian feeling of talking to my computer. But text-to-speech has made some tasks feel so natural, I almost can't imagine working without it anymore.


  • The robots are replacing the packages! I wrote a post on the Spatie blog about why you (don't) want to use a package when your agent can generate whatever you need for you.
  • Alex Woods: Don't let AI write for you. The goal of writing is not to have written, it's to increase your understanding. Of course some writing is purely functional and doesn't fall into this category, but it's important to keep a distinction for yourself.
  • Leave the campsite better than you found it, and it will start cleaning itself up. A quick thought I shared on the compounding effect of agentic development.
  • Andy Matuschak's note on working with the garage door up was part of the spark that got me blogging again.
  • More on doors: "I notice that if you have the door to your office closed, you get more work done today and tomorrow, and you are more productive than most. But 10 years later somehow you don't know quite know what problems are worth working on; all the hard work you do is sort of tangential in importance. He who works with the door open gets all kinds of interruptions, but he also occasionally gets clues as to what the world is and what might be important." This is from a talk called You and your research by Richard Hamming, recommended by Thorsten Ball in his excellent newsletter. I'm haven't gotten through the entire transcript yet, but there are some very interesting ideas in there.
  • Peter Suhm manages his todo list with a this-week tag. I like the distinction between tasks that are due today and tasks that are due "sometime this week". I wish task managers had that concept built in.
  • Skip to the end: some food for thought on how we need to forget about the limits were used to working in that have been lifted by AI. There's some overlap with Dr. Eliyahu M. Goldratt's Four Questions to adopt new technology. (A better (and longer) introduction to this concecpt is You might not need _blank_ by Konstantin Kydryashov.)
  • Speaking of Dr. Goldratt, it's been too long since I've mentioned how good The Goal is. If you're going to read one book this year to make you a better developer/manager/anything really, that's the one.
  • Markdown.new is a nice little tool to convert a webpage into Markdown without any fuss. To make it even easier, I created a bookmarklet to instantly convert the page you're viewing to Markdown.

That's all for today. Next dispatch will be in a month since I have a few days off in May. Thank you for reading, and talk to you soon!

— Seb

Read this email in your browser. If you would rather not receive these emails, you can unsubscribe instantly. Sent with Mailcoach.