AI trains AI: RL-training an agent that trains models with RL

Dan Austin built a pipeline where an agent is handed a training task (“teach a model to do X”), writes a complete RL training job (environment, reward, dataset, hyperparameters), and submits it to real GPUs. Then he RL-trained the agent itself, rewarding it when the models it trained got better. Reward climbed from about 0 to 0.63 over 54 steps, and transferred to a held-out task family. Everything is open-sourced, including write-ups of the failed pilots.