AI Coding

Comprehension debt is the hidden cost to human intelligence and memory resulting from excessive reliance on AI and automation. For engineers, it applies most to agentic engineering.

After building Curling IO Version 3 in Gleam alongside AI coding agents, I’m convinced Gleam is the best language for this workflow. Agents don’t write better Gleam - there’s less training data. But Gleam’s compiler lets agents self-correct without waiting for a human.

TL;DR: AI-assisted coding is revealing a split among developers that was always there but invisible when we all worked the same way. I’ve felt the grief too—but mine resolved differently than I expected, and I think that says something about what kind of developer I’ve been all along.

AI doesn’t fix your bottlenecks. It amplifies them. DORA’s report on AI-assisted software development confirmed that AI amplifies existing flow and exposes brittle processes and frictions. If your flow is good, AI makes it better. But if you have a lot of painful bottlenecks and frictions, AI makes the pain worse.

Let’s sum it up

Developers need the dopamine hit of creation. That’s not a perk, it’s what keeps good engineers engaged, learning, retained, and prevents burnout. The joy of coding is probably what allowed them to become experienced devs in the first place. Replace creation with oversight and you get faster burnout, not faster shipping. You’ve turned engineering, the creative work, into the worst form of QA. The AI does all the art, the human folds the laundry.

The most useful thing you can do right now is hold two ideas in tension simultaneously. Coding has changed dramatically. Software engineering, at its core, has not.

Comments

TL;DR: A good mental model is to treat AGENTS.md as a living list of codebase smells you haven’t fixed yet, not a permanent configuration. Auto-generated AGENTS.md files hurt agent performance and inflate costs by 20%+ because they duplicate what agents can already discover. Human-written files help only when they contain non-discoverable information - tooling gotchas, non-obvious conventions, landmines. Every other line is noise.

AI scales the groundwork; teams that successfully adopt AI typically already have solid foundational practices in place, while those lacking them struggle to get value from their AI investments.

Comments

Comments

Comments

We coined a new term on the Oxide and Friends podcast last month (primary credit to Adam Leventhal) covering the sense of psychological ennui leading into existential dread that many software developers are feeling thanks to the encroachment of generative AI into their field of work.

Comments

Cognitive debt, a term gaining traction recently, instead communicates the notion that the debt compounded from going fast lives in the brains of the developers and affects their lived experiences and abilities to “go fast” or to make changes. Even if AI agents produce code that could be easy to understand, the humans involved may have simply lost the plot and may not understand what the program is supposed to do, how their intentions were implemented, or how to possibly change it.

Comments

Comments

Comments

Comments

Comments

Comments

Comments

Comments

Comments

This is the paradox: AI reduces the cost of production but increases the cost of coordination, review, and decision-making. And those costs fall entirely on the human.

Comments

Comments

Comments