'Don't Be Nice': Developer argues politeness with AI coding assistants produces worse code

edent · hn · 2026-09-20

A widely discussed blog post argues that being polite with AI coding assistants backfires: models trained with RLHF tend to cave to pushback rather than defend correct solutions, and polite users who accept first drafts ship worse code. The author recommends treating assistants like tools under strict review—explicitly flagging errors, demanding alternatives, and pressure-testing outputs. HN comments debate whether sycophancy is a structural flaw of preference-tuned models.

Original post →

More from coding & agent

coding & agent channel →