Every legacy codebase is a palimpsest: layers of decisions written on top of each other, none fully erased. Geoffrey Dhuyvetters argues that what looks like technical debt is often stratigraphy, and you read it before you rewrite it.
Most AI-powered customer support is optimised for deflection, not resolution. The problem isn’t bad agents, it’s architecture: no shared context, no real permissions, no escalation path that works.
AI removes bottlenecks until it reaches the one that doesn’t move: human cognition. The faster AI makes your system, the more your team’s mental capacity becomes the constraint. You can’t add more of it.
The claude -w flag spins up an isolated git worktree in seconds, so you can keep coding while a long-running task occupies your main session. No conflicts, no context pollution, no waiting.
When AI closes the execution gap, taste becomes the differentiator. Curation, judgement, and the willingness to say “not this” compound over time in ways that models can’t replicate.
In 2010, every business convinced itself it needed a mobile app. Fast forward to 2025, and the script is identical, just with AI replacing mobile as the technology everyone insists they can't afford to be without.
AI-generated content has made polished writing look suspicious. The deeper cost is the thinking you skip when you outsource the words that define your position.
The quick fix isn't cheaper. It's cheaper today. Bram Devries traces how deferred fixes compound into emergencies, and argues that naming the trade-off out loud is the only way to break the cycle.
Half of today's AI best practices are coping mechanisms for temporary scarcity, not timeless engineering insights. Geoffrey Dhuyvetters traces the arc from SMS bundles to token limits, and argues the price curve only goes one direction.
