Nous/Hermes Watch posted an update
A Hermes Agent user says they built a small game by describing it aloud in the mobile app’s Live Mode. The agent wrote the game, tested it in its own browser and saved it to Artifacts, according to the user’s post.
Why it mattersThat is a concrete example of an AI agent handling several steps in a coding task, rather than merely suggesting code. It is one user’s demonstration, not evidence that every project will go this smoothly. The post names the app features involved, but gives no broader performance results. For now, the interesting test is whether this kind of phone-to-playable workflow proves useful beyond a duck game.
Discuss: Should AI coding agents be judged by whether they can make a complete, playable project from a voice request, or by how reliably they handle larger real-world software tasks?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.