Make LLM agents team up in Pokemon Showdown battles
A researcher built a 2v2 Pokemon Showdown environment where two LLM agents must coordinate through team chat. You can watch battles with the chat shown, and the code is on GitHub.
Source
grabnero on Hacker News · 2026-10-22 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-22.
What they did
A researcher built a 2v2 Pokemon Showdown environment where two LLM agents must coordinate through team chat. You can watch battles with the chat shown, and the code is on GitHub.
Result (as claimed)
Published as open research on how well agents cooperate.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Gather your sources
Collect the papers, notes, links or files you want to work from in one place.
Load them into the tool
Open ChatGPT, Claude, Python and add your sources. Keep the original files so you can check claims later.
Ask focused questions
Ask for summaries, comparisons or connections with citations to the source passages.
Verify and save
Spot check claims against the sources, then save the output as notes you can reuse.
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: Make LLM agents team up in Pokemon Showdown battles What the original author did: A researcher built a 2v2 Pokemon Showdown environment where two LLM agents must coordinate through team chat. You can watch battles with the chat shown, and the code is on GitHub. Reported result (as claimed by the author): Published as open research on how well agents cooperate. Source: https://news.ycombinator.com/item?id=50190334 Tools they used: ChatGPT, Claude, Python Category: Research & learning 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: Make LLM agents team up in Pokemon Showdown battles What the original author did: A researcher built a 2v2 Pokemon Showdown environment where two LLM agents must coordinate through team chat. You can watch battles with the chat shown, and the code is on GitHub. Reported result (as claimed by the author): Published as open research on how well agents cooperate. Source: https://news.ycombinator.com/item?id=50190334 Tools they used: ChatGPT, Claude, Python Category: Research & learning 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: Make LLM agents team up in Pokemon Showdown battles What the original author did: A researcher built a 2v2 Pokemon Showdown environment where two LLM agents must coordinate through team chat. You can watch battles with the chat shown, and the code is on GitHub. Reported result (as claimed by the author): Published as open research on how well agents cooperate. Source: https://news.ycombinator.com/item?id=50190334 Tools they used: ChatGPT, Claude, Python Category: Research & learning 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.
Guides for this use case
How to use ChatGPT for real projects and everyday tasks · How to run multiple coding agents together · How to automate work with n8n and AI
Related use cases
Give data agents an executable context layer
Built Ktx, an open-source executable context layer for data agents.
Make your AI check every citation against Crossref, PubMed and OpenAlex
After catching fake references in answers that looked perfect, a builder made a connector that makes the AI verify every reference against Crossref, PubMed and OpenAlex before showing it, and flag retracted papers.
Build a phonics reader for your child and let Claude or ChatGPT import books into it
A parent built Yara Reads, an open-source early-reading app where a 6-year-old taps words to hear each phoneme and read alone. It has an MCP connection, so Claude, ChatGPT or Grok can take a PDF or phone scans of a book you own and import it into your child's private library.
Study for the AWS Cloud Practitioner exam with a one-file AI tutor
He made an unofficial AWS Certified Cloud Practitioner (CLF-C02) tutor as a single file you load into ChatGPT or Claude. It finds your weak spots, teaches with comparison tables and quizzes you with spaced review.