A running ledger of what I'm learning about AI — agents, automation, and whatever breaks along the way.
Claude Code records everything its agents do and then gives you no way to read it. I built a reader, pointed it at an 80-agent overnight run, and found a $22 agent that died four hours in without anyone noticing. It's an MCP server now.
A developer with twenty years in gave AI an honest year, hated what it did to the work he loved, and quit. I think a lot of people feel some version of that, and I don't think the tool is the problem — the relationship is. I've inverted it twice this year on my own projects, with nobody making me.
Prompt engineering stopped being the expensive part. Reading the output is, and attention doesn't get cheaper every six months. The missing piece is the layer that decides what never reaches you.
Research-first rebuild of my agent-facing second brain: the rules, the measured before/after, 15 named builders, and the bill.
Twenty prompts over two days, checking in every hour, and I never once understood the architecture I was building — it kept moving while I tried to read it. So now I burst: one long run, then a full day where nothing changes and I can actually learn what I have.
In 2025 every prompt taught me architecture. Now I don't know what's in my own codebase and I haven't learned a new programming idea in a month. I traded it for something else, on purpose, and this is the honest accounting of both sides.
React re-rendered the whole screen on every token, and the only real fix was a migration too big and too joyless to start. Last commit 23 August 2025. Then I bought a week of Fable 5 for $200, and the first commit back — 5 July 2026, 3:23 AM — is that exact migration.
Super-files, scope creep, a component library that got more complicated with every component, praise for ideas I'd explicitly said I didn't understand, and one entire conversation about backend files I never actually attached. Every failure was a missing signal, not a missing capability.
366 commits between June and August 2025. I designed the queue, the workflow engine and the event registry myself, read every line, and hand-picked which files the model could see on every single message. I learned architecture because the model kept violating it.
My first three AI projects, May 2025: a neural network built in Excel cells, a Python server for my local models, and an Android app I didn't know was going to be Kotlin. I could get the model to write code and had no idea where to put the file.
I gave it a misspelled username and a decade-old memory, then described a cosmetic effect only by its shape. It came back with my old Minecraft skin, a solved login mystery, and a working datapack.
Three Claude Code sessions, zero shared memory, one overnight gauntlet: builder agents judged blind against surviving screenshots of a game that died in 2018. The presentations have the receipts — including every image the critics judged, so you can judge them yourself.
Claude played LLM Monster Hunter start to finish as a real player — then delivered a voiced, animated presentation of its own playthrough, built from screenshots it captured while playing. The presentation might be the bigger finding.
A skateboarding wizard in Venice Beach, built in a single prompt in one evening. Then I ran the same prompt with four more districts in it, and the parts I hadn't changed got worse too — which is the actually useful part.
Fable 5 wouldn't do the creative work and couldn't fix its own 3D mistakes — but it built me the tools to fix them myself. Plus what two AI-generated songs taught me about who should write the lyrics.
A public ledger for what I'm learning about AI, instead of scattered notes no one (including future me) can find.
New entries show up in any reader app — no account, no algorithm, nothing recommended to you. Paste this into one:
aaronorelup.com/rss.xml