The Agent That Created 107 PRs (And Why That Was the Problem)

<p>The agent generates 40 lines of code. You read the diff. You approve the change.</p> <p>What just happened there? You didn't write code. You didn't design a flow. You didn't

<p>A few weeks back I gave a coding agent one instruction: <em>"fix the failing import and ship it."</em></p> <p>CI went green. The agent, which I'd allowed to self-merge when

<p>Is writing code with an agent the same thing as pair programming?</p> <p>That question has been going around lately, and there's a practical consequence sitting inside it that

<p><em>8 dimensions. 38 checks. 5 seconds. 0% industry pass rate.</em></p> <h2> The Problem </h2> <p>DAST exists for web apps. DAST exists for APIs. DAST does not exist for AI

<p>I still remember the exact moment.</p> <p>It was 11pm. My team had been sprinting for 3 weeks building <br /> a new payments feature. Deadline tomorrow. I handed the final <br

<!-- SC_OFF --><div class="md"><pre><code>Built a system where Claude Code writes the code and Codex CLI reviews it independently — the reviewer never sees the builder's

<p>History still matters. I just don't want it to be the default context for agents editing the present system.</p> <p>A coding agent will read whatever you put in front of

<p>On March 31, 2026, Anthropic accidentally shipped the entire source code of Claude Code — its flagship AI coding agent — inside a routine npm update. No hack. No reverse