/tags/opinion/Recent content in Opinion on Mad BlogHugo -- gohugo.ioen-gbmadking.direct@gmail.com (Mad King)madking.direct@gmail.com (Mad King)Mon, 04 May 2026 00:00:00 +0000/posts/token-maxing-productivity/Mon, 04 May 2026 00:00:00 +0000madking.direct@gmail.com (Mad King)/posts/token-maxing-productivity/<p>There&rsquo;s a new metric creeping into some engineering orgs, dressed up in fancy AI vocabulary: <em>token count</em>. The idea sounds seductive at first glance — if developers are using AI coding assistants, why not measure how many tokens they generate? More tokens = more output. It&rsquo;s just basic numbers, right?</p> <p>Wrong. It&rsquo;s one of the worst productivity metrics you can imagine, and it has a long, embarrassing lineage.</p> <h2 id="the-ghost-of-lines-of-code-past">The Ghost of Lines of Code Past</h2> <p>Let&rsquo;s be clear — this isn&rsquo;t new. &ldquo;Lines of code&rdquo; (LOC) has been the go-to misguided productivity metric for decades. And every senior engineer will tell you the same thing: <strong>it&rsquo;s garbage.</strong></p>