Blog
Notes from building RL environments.
- Why karotte?Building robust RL environments is hard. Let's go through how they break and what karotte can do about it.
- Introducing KarotteWe're open-sourcing Karotte, our tool for building RL environments that hold up against a model trying to reward hack them.
- Building RL Environments for SuperintelligenceAs models move from human-level to superhuman, the qualities that make an RL environment effective change. Here is what we think it takes to build good ones in that regime.
- Slay the SpireWe let nine frontier models play a roguelike deck builder to see how well they strategize over hundreds of decisions in a row.
- Model Submission in RL EnvironmentsA .pt2 file is just a zip. Loading one is not just unzipping. Here are the checks we run before we trust it.