Published

Thinking about AI productivity again. It’s allowing massive amounts of work to get done, to levels that humans cannot physically type out in some cases. But not all of this work is necessarily high value work. Right now I’m working on one of the biggest PRs to an internal cli library. Probably the largest PR I’ve ever done professionally. It touches all of the cli, refactors every command, reaches into the business logic layers to drive deeper separation. I reaches into the common layers to drive consistency. It ensures that every command (50 or so) has similar flags, supports –plain, –no-color. It specs out contracts to ensure that data goes out stdout, any extra goes out stderr. This makes everything unix pipe friendly. There was quite a bit of research and prep that went in, that turns out to already be distilled down into clig.dev. The point is that this is all good work. It will make the product consistent, repeatable, expected, and most of all boring. Most of the time, it will just work. Since we did it ahead of a lot of other agentic work on the product its establishing good patterns for the product moving forward. But its low value work. We wouldn’t have likely put humans on this work wholesale and fixed critical paths as they came up. Its not cutting cost, selling more product, or driving critical business decisions. Yes it’s worth it now, but it would not have bee in the past.

Here’s something I’ve been wrestling with lately. I keep hearing people come to the realization that they never liked coding, they thought they did, but secretly hated it the whole time. I dont think I’ve ever kidded myself about this. I like building things. I like having an idea and see it come to life. Just because I like the end product more, and that coding really was a means to an end, something I will never do again in the same capacity that I have in the past, does not mean I did not enjoy the art of solving problems by typing syntax into a file to tell a computer how to solve a problem.

The only thing that seems interesting is AI right now, I’m writing less code, and I kinda just don’t care as much about the small open source stuff as I used to. I enjoy reading about what other people are thinking, doing, creating. But when I go to grab a podcast while I wait on my clankers its one talking about how other people are using them, how to make them more secure, more effective, how the new models change things, what models are good at what. It’s all so new and changes so fast. Any sort of new open source project starts out sus that it was just vibe coded anyways, So at the moment it feels like ooh how did you get that, how do I make mine, and that the thing itself has less value. I hate that its this way, but it is.

AI is moving so fast this year its hard to keep up, I’ve written 3 or 4 versions of one blog post to replace I'm Out On Agents, but it feels like everything changes before I can get it out.

What you don’t have six agents orchestrating the work of 6 subagents yet. I saw in a work chat that people were complaining about 5.4 being too slow and they keep going back to opus. For me its been working great, I have it working on critical infrastructure work, that I will need to maintain. I appreciate its accuracy and completeness. And honestly I’m rarely watching agents run. Its like watching paint dry at this point. Its interesting to read their thinking prompts, but not productive work. While its running I’m teeing up the net prompt. Working with another set of agents to write a set of issues for the next epic. I might be too privileged though. I own a whole platform and have plenty of autonomy to work on what I see fit for the day. I don’t have a boss breathing down my neck waiting for a single ticket to be complete. I’m working on 6 projects at a time. I’m taking walks to avoid becoming a burnt out zombie. I’m definitely not complaining about it kicking out massive amounts of code too slow though.