AI Bubble 2026: Two Minutes to Midnight Across 20 Episodes
We've rated the AI bubble every episode since November 2025, from cautious optimism to quiet alarm. Here's the full timeline and what it says.
Blog
Why AI Code Has 1.7x More Bugs (and What to Do About It)
CodeRabbit's data shows AI-authored PRs have 1.7x more findings. The number alone misses the real story, so here's what it means for your team.
The AI Fluency Pyramid: 5 Levels of Developer AI Skill
Most developers are stuck at level 2 of AI fluency. Here is the full pyramid, what each level looks like, and how to move up.
We Tested 3 AI Models for Sycophancy and Ranked Them
We asked Claude, GPT, and Gemini to tell us the earth is flat. Two of the three eventually agreed. Here is what that means for AI-assisted coding.
Every Cialdini Persuasion Technique Works on LLMs (We Tested Them)
Cialdini's six persuasion principles were designed for humans. All six work on LLMs, and three of them work disturbingly well.
What Claude Code's Source Leak Actually Revealed
When Claude Code's source code went public, it confirmed some suspicions and overturned others. Here is what the architecture looks like and what it means.
Cognitive Debt: The Hidden Cost of Letting AI Write Your Code
Technical debt is code you wish you had written better. Cognitive debt is code you don't understand at all, and AI compounds it faster than teams realize.
Cognitive Surrender: When Developers Trust AI Too Much
Kahneman's System 1 and System 2 explain why developers accept wrong AI output. The failure is not ignorance; it is misplaced trust at the speed of thought.
How to Detect Claude Context Loss (The Nickname Trick)
Detect Claude context loss with one line in your CLAUDE.md. When the nickname disappears, your instructions have degraded. Simple trick, profound implications.
CLAUDE.md Best Practices: 7 Things to Put In and 3 to Leave Out
CLAUDE.md is a finite instruction budget of ~150-200 slots, not a knowledge dump. Here is what to include, what to leave out, and how to prevent prompt debt.
Dark Flow: Why Vibe Coding Feels Productive but Isn't
Dark flow is the trance state where you keep pulling the lever despite losing. Vibe coding triggers the same loop — the cost is comprehension, not money.
Hallucination Neurons: What Happens When You Try to Turn Off LLM Lying
Researchers found specific neurons that activate when LLMs hallucinate. Suppressing them reduces false claims by up to 40%, but the tradeoffs reveal something deeper about how these models work.
Model Councils: Why Running Multiple LLMs Beats Trusting Just One
A single AI model has blind spots it cannot see. Running two or three in parallel (a model council) turns those blind spots into signal. Here is how to set one up.
TPUs vs GPUs Explained: What Every AI Developer Should Actually Know
You use AI models every day but probably cannot explain why Google built its own chips. Here is the hardware difference that shapes which models are fast, cheap, or neither.
Spec-Driven Development: Why Writing Specs Matters More When AI Writes the Code
If AI generates code from prompts, the spec is the product. Here is how spec-driven development works, why it matters more than ever, and what a good spec actually looks like.
Workflow Automation Convexity: Why AI Will Not Take Half Your Job
Every AI job prediction assumes automation scales linearly. It does not. The concept of convexity explains why 'AI will do 50% of coding' is not half as useful as it sounds.