Ai

Published: Apr 8, 2026 After I published Two problems blocking autonomous AI coding assistants, I got some responses. And a pattern emerged. For every problem I raised, someone had the same answer: “We’ll solve that soon.” Verification is manual? Don’t worry, AI-generated tests are getting better. Code review doesn’t scale? Give it six months, the tools will summarize changes for you. The non-determinism problem? Next-gen models will be more consistent. ...

Published: Apr 8, 2026 This is the third post in a series. The first was about two problems blocking autonomous AI coding assistants. The second was about the asymptotic promise of agentic coding. In those posts I talked about non-determinism and the feeling that real autonomous coding stays just out of reach. I think I’ve figured out why. The trade-off nobody talks about If you want an AI coding agent to be really efficient, you have to let it loose. Give it access to your file system. Let it run shell commands. Let it make decisions without asking you first. The more freedom you give, the more it can do for you. ...

This is the fourth post in a series about agentic coding. The first was about two problems blocking autonomous AI coding assistants. The second about the asymptotic promise. The third about the freedom-risk curve. I think I’ve been circling around something in those posts without naming it. When we talk about AI agents, there are actually two very different things going on. Mode 1: The agent writes software. You ask it to implement a feature, write a script, build a component. It produces code. You run the code. The code is deterministic — same input, same output, every time. The problems I wrote about before still apply: you need to verify the code and understand what changed. But once the code works, it works. ...

Published: Mar 30, 2026 So I’ve been using AI coding assistants daily for a while now. Claude Code, GitHub Copilot, Codex - I’ve tried them all. And I keep running into the same wall. Every time I use agentic coding, I end up doing two things manually: First, I verify that the code actually does what I expected - running tests, checking behavior. Second, I read through the changes to understand how the shape of the codebase changed. ...