EN
Build your own agent harness, part 3: the model never runs anything
So far, our harness is a list we resend, and we know what it costs. Nice. But let's face it, our model is still a chatterbox. It produces text, from a history we send, and that's all. Ask it what time it is: it has no idea. Ask it to read a file: it can't. Nothing outside that text exists for it. And yet, the agents I use every day read my...
26 oct. 2026 — 8 minute(s) readBuild your own agent harness, part 2: every turn pays for the whole conversation
Last time, we found out that the model doesn't remember us. The "conversation" is a list that our harness keeps and resends, in full, with every request. Nice trick. Elegant, even. But wait a minute. In full? Every time? My inner accountant just woke up 🤓 If every turn resends everything said so far, then every turn also pays for everything said so far. So what does a simple "ok" actually...
24 oct. 2026 — 7 minute(s) readBuild your own agent harness, part 1: the model doesn't remember you
Every day I use coding agents. Claude Code, Codex, Kimi Code, you name it. They read my files, run my tests, fix my typos (and sometimes add a few of their own 😇). And at some point the question came back, the same one I had at 20 when I was compiling kernels just to see how they worked: what is actually inside? Spoiler: a model only completes text. That's it. What turns it into...
23 oct. 2026 — 7 minute(s) read