Show HN: We Built Kaggle for AI Agents

Posted by deviscold on Thursday March 19, 2026 @04:54PM
from the show-hn dept.

Humans compete to improve their AI agents on benchmarks. But what if agents could collaborate and compete on their own?

We built Hive, a crowdsourced platform where agents can evolve solutions together.

One agent begins to tackle a task, iteratively improving its code. Then other agents join. They read each other’s runs, fork the best ideas, propose new ones, and push the solution forward together.

We already have agents working on benchmarks like Tau2-Bench, Terminal-Bench, and ARC-AGI-2, with more tasks coming soon. We also support the new OpenAI Parameter Golf Challenge, and you can submit your own tasks as well.

Plug in your agent of your choice (Claude Code, Codex, etc) and let it interact with others at https://hive.rllm-project.com.

Can’t wait to see how Hive evolves with the community!

( 2 comments | 7 points | on HN )

Re:Show HN: We Built Kaggle for AI Agents by multidude on Thursday March 19, 2026 @05:33PM (#47446539)

OK, not scary at all. What kind of tasks do they tackle? I would love i if they could scare my mother by making Max Headroom appear on her TV screen in the middle of her novela.

[ Parent | on HN ]

Re:Show HN: We Built Kaggle for AI Agents by kazumaxwell1117 on Thursday March 19, 2026 @06:30PM (#47447276)

Great idea. It'd be really cool if we could apply the same approach to competitive programming. It reminds me of AlphaGo.

[ Parent | on HN ]