CROSSPOST: MIKE KONCZAL: Three Ways Terminal AI Has Changed How I Work (And Whether It's Coming for My Job)
Mike’s subhead: “How terminal AI compresses setup, robustness checks, and iteration without replacing judgment, and whether Olivia Rodrigo caused the inflation wave.”
My intro: Mike Konczal has joined the MAMLM-enabled white-collar workforce. As a scout, he reports on the successes—so far—of this Errand Unto the Wildnerness of his. He is now equipped not just with spreadsheets and Stata do-files alone, but with a terminal window, a microphone, and a large language model that now lives in his working directory. What he brings back is not a story of instant superintelligence or a world in which economists and policy analysts are swept away by robo-oracles. It is, instead, a report from the front lines of something prosaic yet very consequential: the compression of the set-up phase of knowledge work. The human attention paid to plumbing can be repurposed to “what is actually going on here?” Konczal’s examples are reassuringly mundane—yet powerful mind-amplifiers:
<https://newsletter.mikekonczal.com/cp/188568241> <https://newsletter.mikekonczal.com/p/three-ways-terminal-ai-has-changed>
Three Ways Terminal AI Has Changed How I Work (And Whether It’s Coming for My Job)
How terminal AI compresses setup, robustness checks, and iteration without replacing judgment, and whether Olivia Rodrigo caused the inflation wave.
Mike Konczal
Feb 19, 2026There’s been a lot of buzz about terminal-based AI tools like Claude Code and OpenAI’s Codex. Unlike the browser chat interfaces most people use, these tools run locally on your computer and they’ve gained serious traction over the past several months.
But much of the discussion has been caught between people building applications as fun personal hobbies on one end, and massive enterprise software on the other. Most of us who use these professionally will live somewhere in the middle. (The discourse is also wedged against whether AI will cause large-scale unemployment or otherwise destabilize society.)
I’ve integrated these terminal tools into my workflow over the past two months. Below are three specific ways I’m using them that are genuinely new, and where I’m not going back to how I worked before. Terminal AI compresses the setup and robustness-checking phase of knowledge work. I’ll also explain what makes them different from the browser-based chat tools, and whether I, Mike Konczal, am about to be automated out of a job….
Use 1: Real-Time Analysis, Without the Prep Work…. Use 2: Building Out a Report…. I really want to emphasize how much of the work for any report is this basic setup, the data-wrangling and first-pass results to see if the results are worth exploring in full. This can be time-consuming, especially if it doesn’t pan out. Unless you try it, I can’t describe to you how fast the terminal LLM can get through this stage, and keeps the building blocks in place to iterate on…. Use 3: Anticipating Arguments You Might Not Know Ahead of Time….
So this still looks like an extreme version of labor-saving technology. It makes people faster at a given set of tasks, and it lets you cover more ground with the same resources. Which effect dominates, fewer people or more output per person, is an open question. My experience, at least for now, is that it can complement people who know how to use it, but risks shortcutting those earlier in their careers before they’ve learned the building blocks…
