When you face a problem and spend days finding a solution, write about your successes – or even failures. This will help others who are stuck on the same issue, and it will help experts find missing information or unclear wording in their docs (which is why documenting failures is useful, too). Blogs, social networks, anything goes, really – even if only your friends see it, some of them may still find it useful.

I am not telling you to run your coding agent’s frontier reasoning on a box in your closet. You can’t, not at parity, not yet. I’m telling you that a huge fraction of the tokens flowing through a mature AI workflow are doing unglamorous work that a good open-weights model on your own hardware does just fine — and every one of those you pull back in-house is a token that no longer shows up on someone else’s invoice with a markup on top.

I realize that among this mix of contrasting feelings, there is one emotion that dominates - one that comes from my direct interactions with LLMs. I don’t like them. They talk to me in this grating LLM-voice, an uncanny valley of talking to a real human. They confidently bullshit me - often giving me useful, helpful answers. But also just making stuff up with the same assurance - and with only a veneer of fake remorse when I call them out on it.