Watch language models fight in a tiny AI arena
Built TinyAIArena where four models battle on an 8x8 grid instead of sitting in a static leaderboard.
Source
hp6 on Hacker News · 2026-09-27 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-15.
What they did
Built TinyAIArena where four models battle on an 8x8 grid instead of sitting in a static leaderboard.
Result (as claimed)
Spectatable matches with open source code.
Tools they used
The source does not name specific tools.
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Write a one-page brief
Describe the app in plain words: who it is for, the 3 core screens or actions, and what "done" looks like.
Start the project with your agent
Open your AI agent and paste the brief. Ask it to propose a stack and a file plan before writing code.
Build one slice at a time
Ship the smallest working flow first, run it, then add features one by one. Commit after each working step.
Test it like a user
Click through on desktop and phone. Ask the agent to add basic tests and fix anything that breaks.
Check security and ship
Keep keys in environment variables, check auth and database rules, then deploy and share the link.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Watch language models fight in a tiny AI arena What the original author did: Built TinyAIArena where four models battle on an 8x8 grid instead of sitting in a static leaderboard. Reported result (as claimed by the author): Spectatable matches with open source code. Source: https://news.ycombinator.com/item?id=49867775 Tools they used: not named in the source Category: Vibe coding & apps Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Watch language models fight in a tiny AI arena What the original author did: Built TinyAIArena where four models battle on an 8x8 grid instead of sitting in a static leaderboard. Reported result (as claimed by the author): Spectatable matches with open source code. Source: https://news.ycombinator.com/item?id=49867775 Tools they used: not named in the source Category: Vibe coding & apps Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Watch language models fight in a tiny AI arena What the original author did: Built TinyAIArena where four models battle on an 8x8 grid instead of sitting in a static leaderboard. Reported result (as claimed by the author): Spectatable matches with open source code. Source: https://news.ycombinator.com/item?id=49867775 Tools they used: not named in the source Category: Vibe coding & apps Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Related use cases
Ship an iPhone app where the agent did design to submission
A teleprompter app was built with Claude Code covering interface, builds, testing, image assets and App Store submission.
Build your first games as a designer, not a game dev
A 25-year designer built six games with Claude Code and Codex; getting them running was quick, making them fun took longer.
One-shot a Figma-like design app with Opus in eight prompts
Used Claude Opus 5.5 to few-shot a working Figma-style app in about three hours across eight prompts.
Turn text descriptions into game-ready 3D assets
A developer gave a headless coding agent control of Blender so it outputs models with rig, animations and colliders from a text prompt.