Does telling a coding agent to do TDD by itself make a difference? Or is it one of the rare examples where what's good for the human is irrelevant or bad for an agent? Birgitta Böckeler runs experiments and shares her thoughts.
Martin Fowler
@martinfowler
Author on Software Development. Works for Thoughtworks. Also hikes, watches theater, and plays modern board games. He/him.
- Fragments: responsibility for rogue agents, indicators of a bubble bursting, dread of AI, praise for gov.uk, getting data out of closed packages, eyes on Clacton martinfowler.com/fragments/2026…
- NEW POST Giles Edwards-Alexander does an experiment to see if decomposing a large function helps reduce token costs, suggesting that is may now be possible to measure the economic benefit of refactoring
- NEW POST Subagents get justified by time saved and parallel execution, but @techygarg explains that what really matters is protecting the orchestrator's context.
- Fragments: mismatched views of AI between engineering and C-suite, comparing dotcom and AI bubbles, LLMs build it we run it, law professors prefer LLM answers, using DSLs with LLMs, the stench of LLM-speak
