Ideas Weave Every Narrative with AI.
The developers thriving in the AI era aren’t the ones who code faster — they’re the ones who ramble on purpose. Before writing a single line, they explore problems out loud, use AI as a thinking partner, and surface assumptions they didn’t know they had. Rambling isn’t procrastination. It’s the pre-coding phase that most developers skip because it looks like wasting time.
AI coding agents like Codex and Claude Code are burning us out. You ask for a minor tweak, and they hand back a completely rewritten plan. BDFL, an open-source supervisor, solves this plan drift by introducing versioned approvals and isolated execution. The only way to manage AI’s chaos isn’t more collaboration—it’s a benevolent dictatorship.
Martim Chaves recently ‘reinvented’ logistic regression, but the math is exactly the same. The real breakthrough isn’t a new algorithm—it’s using LLMs to build interactive widgets that transform static, painful technical education into a hands-on experience. The future of learning isn’t reading. It’s playing.
AI coding assistants that provide Socratic hints for LeetCode problems promise efficiency, but they often bypass the essential struggle of learning. Users seek hints to escape the discomfort of failure, but in doing so, they spoil the ‘aha’ moment and fail to build genuine problem-solving skills. The pain of learning isn’t an obstacle; it’s the point.
A 600,000-install AI skill with only a few lines of code proves the biggest bottleneck in programming isn’t the AI — it’s your ability to articulate what you want. The grill-me skill forces you to think clearly before a single line of code is written, turning vague ideas into executable blueprints.