I’ve been using AI to generate some repetitive frontend (guilty), and while most outputs felt vibe-coded, some results were surprisingly good. So I cleaned it up and made a ranking game out of it with friends, and you can check it out here: https://www.designarena.ai/vote
/vote: Your prompt will be answered by four random, anonymous models. You pick the one you prefer and crown the winner, tournament-style.
/leaderboard: See the current winning models, as dictated by voter preferences.
/play: Iterate quickly by seeing four models respond to the same input and pressing space to regenerate the results you don’t lock-in.
We were especially impressed with the quality of DeepSeek and Grok, and variance between categories (To judge by the results so far, OpenAI is very good for game dev, but seems to suck everywhere else).
We’ve learned a lot, and are curious to hear your comments and questions. Excited to make this better!
Comments URL: https://news.ycombinator.com/item?id=44542578
Points: 36
# Comments: 11
Войдите, чтобы добавить комментарий
Другие сообщения в этой группе
I built this out of frustration as I lead the development of AI features at Yola.com.
Prompt testing should be simple and straightforward. All I wanted was a simple way to test prompts with vari
Article URL: https://kristoff.it/blog/zig-new-async-io/
Comments URL: https:
Article URL: https://www.technologyreview.com/2025/03/12/1113130/green-steel-boston-metal/
Commen
Article URL: https://www.nytimes.com/2025/07/09/travel/rental-car-ai-scanner-hertz.html
Comments URL
