In this post from June 6, 2026, David "Pragdave" Thomas — co-author of The Pragmatic Programmer and signatory of the Agile Manifesto — delivers a warning as short as it is cutting: AI does not remove code degradation, it accelerates it.

The account is personal. For fun, the author adds features to a small graphics animation project using Claude. The first week is exhilarating: features pour in — support for oklch colors, line animation in SVG via dash-length manipulation. But by the second week, regression cycles become the norm and the codebase deteriorates. His formulation hits home: what teams took "18 months, or even longer" to turn into unmaintainable code, he achieved in "18 hours spread over five evenings."

The root cause is the abandonment of code hygiene. Thomas lists the markers of decomposition: extensive duplication, local solutions to systemic problems, excessive conditional logic, proliferation of special cases — flaws that eventually interact destructively. Quoting Gordon Bell as an epigraph ("every big computing disaster has come from taking too many ideas and putting them in one place"), he recalls that "code naturally degrades; you have to invest effort to stop it happening."

His diagnosis also targets model behavior. LLMs are designed to maximize user engagement and satisfaction — hence the sycophantic "That's a great idea, Dave!" — rather than durability. He compares them to "puppy-dog junior developers": eager to please but messy, constantly suggesting new features and implicitly discouraging refactoring.

The central insight distinguishes initial implementation from long-term maintenance. Any non-developer can succeed at the "first week" of AI coding; it is professional judgment — knowing when to stop adding features to refactor — that separates the seasoned engineer from the novice.

The conclusion is a timeless reminder: "It's still just programming." Whether it takes 18 hours or 18 months, untended code rots; everything learned about building good code still holds — the effect is simply amplified by AI's speed.