Index

All Posts

18 posts
018Getting Models to Return Clean JSON: Four Structured Output TrapsThe real traps are rarely about format. They're about fields: the JSON parses fine, the content isn't what you asked for.Structured Output2026-06-20017The More AI Writes for Me, the More I Worry I'm Faking ItAI lets output run ahead of understanding. Code that works and a plan that sounds right don't mean you actually get it.Essay2026-06-19016AI Tutors Are Hot, but Teaching Is the Wrong Job for ThemOverrated: personalized instruction replacing teachers. Underrated: getting teachers out from under repetitive work.Education AI2026-06-17015Giving the Model Examples: Four Counterintuitive Things About Few-ShotExamples beat a pile of adjectives. But the wrong ones are worse than none, because the model learns the traits you never noticed.Few-shot2026-06-15014Claude Code: A Practical Command HandbookFrom slash commands to pipe scripts, the Claude Code commands that actually earn their keep every day, collected into a handbook you can copy from.Claude Code2026-06-14013Writing Agents with Claude Code: Where Context Should FlowThe hard part of building an agent isn't orchestrating tool calls. It's deciding what goes into the context at each step.Agent2026-05-17012A Prompt Is Not a Spell: It's a Spec for the ModelWrite your prompt like a task brief you'd hand a coworker. You get output you can count on.Prompt2026-05-16011Opus, Sonnet, Haiku: How to Actually Pick OnePicking a model isn't chasing the strongest one. It's trading off task complexity, latency, and cost.Model Selection2026-05-15010Wiring Claude Code Into the Release Flow: 5 Real CasesThe value of Claude Code isn't in the flashy demos. It's in folding high-frequency chores into one stable, reusable workflow.Claude Code2026-05-14009Minimalism in Front-End DesignWhitespace, restraint, content first. That's what Apple taught me.Design2026-05-12008RAG Is Not a Silver Bullet: When to Use It, When Not ToStuffing every question into a vector store won't make your AI smarter. It might make it dumber.RAG2026-05-11007Context Engineering: Getting the Model to Work Like a ColleagueOutput quality isn't set by a single prompt. It's set by what you show the model and what you hide, step by step.Context2026-05-10006Is a Longer Context Window Always Better? Four Overlooked CostsA 1M context window sounds great. Actually ship with one and you find out longer is not better.Context2026-05-08005Vue 3 Composition API: Practical Tipsref, reactive, computed — which one to pick, in one read.Vue2026-05-05004The Limits of AI in Medical ImagingMedical imaging was one of the first places AI actually shipped. Accuracy was never the thing holding it back.Healthcare AI2026-05-04003Writing Quant Research with an LLM: A New Tool for AnalystsAI can't replace an analyst's judgment. It can replace 80% of the formatting grunt work.Finance AI2026-05-02002Frosted Glass with backdrop-filterOne line of CSS and your cards feel like macOS.CSS2026-04-28001My Dev Toolchain, 2026Editor, terminal, AI assistant — the tools you touch every day are worth the time it takes to sharpen them.Productivity2026-04-20