Notes from the build.
Things I wrote while figuring something out. Never a marketing post. Occasionally wrong. Always mine.
Classic AI tried to program intelligence top-down. LLMs learned it bottom-up — by reading an enormous portion of what humans have written. That's not a technical detail. It might be the most important philosophical observation of our era.
I've killed three note-taking systems. Each time, the same pattern: enthusiasm, elaborate architecture, slow decay, abandoned graveyard. What changed was adding AI agents to the loop. Not as a novelty, but because agents solve the core problem.
We have always been in the process of becoming obsolete. Every generation discovers that what they thought made them irreplaceable was, in fact, replaceable. The question isn't 'what can humans still do?' It's 'what do we want to remain ours?'
Why agent swarms stopped being a Fortune-500 toy and started mattering for mid-market ops.
"What we have learned so far is that using AI well is a skill that needs to be carefully learned by… using it a lot. It’s just too unlike everything else. The call to tinker with it was the right one, but it was too much of a suggestion. This is what I want to change here today. We also learned that, as opposed to most tools, AI acts as a multiplier." _Tobi Lutke, Shopify CEO_