Bad evals, my own: five exercises from two LLM judges

<p><a class="article-body-image-wrapper"

<p>Shipshape, the hackathon portal I built for DOGFOOD 2026, gives every team a history panel on its team page and submission page: who joined, who edited the project, when it

<blockquote> <p><strong>Where this fits:</strong> A series aside, not a numbered Part. It is first an apology for a fabricated claim under Part 3; the experiment below is how I

<blockquote> <p><strong>TL;DR.</strong> I built an Anthropic Agent Skill for <code>@ngrx/signals</code> and ran it through the full eval pipeline: capability A/B benchmarks, token