librarian › everything, newest first

Writing

Everything, newest first. Series appear as one entry with their parts.

1. 01 Note Agent Boundaries: Draw the Line, Then Let GoHow I draw boundaries for AI agents: which level is enough, where the line goes, and when it's worth letting go. I care less about benchmark scores than about whether a system works in a real business. Series · 5 of 5 parts

   1. Part 1 Moving AI Agents from Hype to Engineering Reality: Finding Your Sweet Spot in the Architectural Spectrum 23 Mar 2026 · 6 min
   2. Part 2 L1 & L2: Teaching AI to Be Precise, Not Just Prolific 22 Apr 2026 · 19 min
   3. Part 3 L3: Let the Model Choose the Next Step, but Let People See Every Step 24 Apr 2026 · 12 min
   4. Part 4 L4: Before You Add Another Agent, Decide Who Has the Final Say 19 Sep 2026 · 5 min
   5. Part 5 Evaluation: However Fast Agents Change, First Ask What Problem You're Solving 28 Oct 2026 · 5 min
2. 02 NoteWhy Does Your AI Always Agree With You? On AI SycophancyAI sycophancy, the tendency of mainstream large models to please the user with flattering, agreeable answers over the facts, starts in reinforcement learning training. Five habits in how you ask can get you more objective, sharper opinions out of AI. 5 Jun 2026 · 7 minRead →
3. 03 ViewVibe Coding Gets You There Faster — It Doesn't Choose Where You're GoingWhat Vibe Coding actually reduces is the cost of making ideas visible — turning vague descriptions into something that can be seen and touched. What it doesn't reduce is the cost of judging whether something is worth building in the first place. The faster the tools, the more easily a wrong direction gets amplified. And the people who can translate between business logic and technical implementation? They're becoming rarer, not more replaceable. 25 Apr 2026 · 6 minRead →
4. 04 ViewIs Your Bulleted List "Too AI," or Just Thoughtfully Structured?Redefining the role of structure in professional communication in the age of Generative AI. 18 Mar 2026 · 2 minRead →