A new study mined 3,553 coding-agent sessions and found that requirements which only become visible once code exists get an agent’s prior work deleted or replaced at nearly twice the rate of any other edit. In a controlled follow-up with Aider, telling the agent in advance that a change was coming bought back about a sixth of one line — not the rework itself.
We walk through the study’s numbers, its own hedges about what a syntactic proxy can and can’t prove, and why the finding narrows the case for spec-driven development rather than undermining it — the paper tested a chat warning, not a written spec.