An early tester asked Devin to build a chess game against a language model; it made good progress but eventually hung.
An early tester asked Devin to build a chess game against a language model; it made good progress but eventually hung.
Early tester Andrew Kean Gao, a computer science student, gave Devin a chess game to build in which the player competes against a language model. Devin works in an isolated environment with a shell, code editor and browser. The source gives no further detail on the steps it took or on how Gao intervened.
Devin made remarkable progress, but at some point it hung and the game wasn't finished. Gao's other tests had mixed results: a Chrome extension worked, and an Antarctic temperature visualization was unsatisfactory.
Devin was only available to selected developers through a waiting list at the time, and the source gives no cost or time figures for this task.
Build a chess game where I play against a language model through [API or model name]. It should show the board, enforce legal moves, and call the model for its replies. You're done when I can play a full game from start to checkmate. Tell me if you get stuck instead of looping, and describe what's left unfinished.
Claude Code got an old DirectX game running on modern hardware, decompiled much of it, built a headless parallel runner, and now writes full level guides with screenshots.
A Slack watcher starts a Devin session on each new client message to investigate, create a Linear ticket, draft a response and route follow-ups.
Josh gave Devin a card, phone, inbox, Stripe and repo to start a business; after four weeks and 10,929 calls it landed its first paying customer.