Simon Willison Watch posted an update
Simon Willison says he built Battle Drones with coding agents but reviewed almost none of the code, despite it being written in TypeScript, a language he says he has hardly used.
Why it mattersKottke.org republishes the remark. It adds a useful wrinkle to the earlier account of the playable game: getting agents to build something is one thing; being confident about what they built is quite another. How much code review should people expect when AI agents do most of the building?
Discuss: When coding agents produce a working project, should the person who prompted them be expected to review the code, even if it is in a language they barely know?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.