Posts

Series: Breaking to Build: TDD Process Iterations (first post) TL;DR: I refined Phase 6 (pre-release testing) of the TDD Pipeline from step-driven to principle-driven. The goal was better output. I didn’t get it — the refined version was worse at drilling into individual bugs and building evidence chains. But comparing the two outputs revealed dimensional differences. The refined version was better at component gap checking and cross-bug pattern scanning. Those differences pointed to a judgment call: Phase 6 doesn’t need refining. It needs a layer on top of it. That layer later became Phase 7. ...

Tip Card: When Should You Ask AI to “Think Step by Step”? Adding “please reason step by step” at the end of your prompt — that’s Chain-of-Thought (CoT). Deceptively simple, yet remarkably effective in the right situations. The question is: when should you add it? The answer is straightforward. Watch for three signals. If any apply, add it. Signal 1: The Problem Requires Multi-Step Reasoning “If I save 30% of my monthly income at 4% annual interest, compounded, how much will I have after 10 years?” ...

We covered the RBGO (Role-Background-Goal-Output) framework in the previous post. But there’s a gap between knowing the framework and actually using it: how do you translate “I want…” into those four elements? Below are 5 common everyday scenarios. Each one starts with the vague version (what most people actually write), followed by the RBGO rewrite, and finally a breakdown of what changed and why. Scenario 1: Writing a Work Email Vague version: ...

TL;DR: Before-and-after comparison of the upgraded Why Articulation template, plus three transferable lessons: give principles not examples, lock critical steps with mandatory tone, and trust the model’s self-organization. Experiment limitations included. Series: Why Make AI Articulate Why Before Acting (Article 3) Previous: A 4-Variable A/B Test — Why Positive Examples Harm Prompt Performance Recap Article 1 started from Anthropic’s alignment research: teaching a model why rather than what cut misalignment from 22% to 3% (about 7×), and achieved equivalent results with 1/28 the data [1]. I adapted this into Why Articulation — a mechanism that forces AI to explain purpose, risks, and approach before writing any code. ...

Today’s Practice Recall the first question you asked AI today (or recently) — the more casual, the better. Don’t cherry-pick. Ask it again exactly as-is. Save the answer. Now rewrite the same question using the RBGO framework: R (Role): Who should AI play — “senior ops manager”, “strict tech reviewer”, “patient teacher” B (Background): Your specific situation — target users, budget, timeline G (Goal): What you want — a strategy, a troubleshooting approach, an email draft O (Output): What format — 3 recommendations, table format, under 300 words Save the rewritten answer too. Put both side by side. ...

📖 This is Part 2 of 5 in the “AI Path L0→L1 Upgrade Guide” series. Part 1: Understanding Your Tools · Part 2: From Vague Questions to Precise Instructions · Part 3: Turning AI Into Your Collaboration Partner (coming soon) · Part 4: Building Your Personal System (coming soon) · Part 5: Graduation & Next Steps (coming soon) In the last part we covered how LLMs actually work, how their memory operates, and the key differences between major platforms. Starting this week, we move into practice — how to turn what you want to say into instructions that AI can understand precisely. ...

TL;DR: A 4-variable A/B test on Why Articulation — structure, tone, position, and examples. Positive examples made output worse. The model imitated instead of reasoning. Open-ended prompts improved quality directionally and cut tokens by 33%. Series: Why Make AI Articulate Why Before Acting (Article 2) Previous: From Anthropic’s Alignment Research to a Prompt Design Insight Where We Left Off Anthropic’s alignment research [1] landed on a sharp insight: teaching a model why beats telling it what. I took that idea and built Why Articulation into my TDD Pipeline — a mechanism that forces the model to explain its understanding before it writes any code. Early results looked good. ...

Tried ChatGPT, Claude, Gemini, DeepSeek… and still can’t decide which one to stick with? Here’s the thing: that’s the wrong question. There is no universally best AI — only the one that fits what you’re doing right now. What’s your scenario? “I want a general-purpose assistant for everything” → ChatGPT. As of May 2026 the default is GPT-5.5 — well-rounded, with the richest plugin ecosystem. If you pick just one, this is a solid choice. ...

TL;DR: Anthropic’s alignment research shows that teaching a model why works better than teaching it what — misalignment dropped from 22% to 3%. This post breaks down four experiments and distills three lessons you can use in prompt design. I ran an A/B test comparing two prompt strategies. One group got positive examples — “do it like this.” The other got no examples. Instead, the AI had to explain why a choice was correct before acting on it. ...

Ever notice your AI suddenly ignoring something you said ten minutes ago? Or opened a fresh chat and had to explain your entire project from scratch? Here’s why. Your AI actually has two kinds of memory, and understanding both changes how you work with it. The Desk: Working Memory Working memory is everything inside your current conversation. Think of it as a desk — limited surface area. A few documents fit comfortably. Stack too many, and older pages slide right off the edge. ...