Harvard's field data on coding agents: +30% code, +49% review time, flat output
This story is from 2026-10-17. It is preserved in the archive; the latest stories are on the live feed.
A 78-page job market paper landed last week that puts field numbers on the argument everyone has been having from vibes. Fiona Chen and James Stratton at Harvard wrote it using a proprietary dataset from the engineering analytics platform Jellyfish, and the abstract states the finding flatly: both…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-10-17 00:15 · DEV Community — AI
Harvard's field data on coding agents: +30% code, +49% review time, flat output