Yuandong Tian on Recursive Self-Improvement

Yuandong Tian discusses his research on computer Go, from DarkForest to OpenGo, and the role of action-space design in applying reinforcement learning. The conversation covers gradient-free optimization, neural architecture search, Coconut’s approach to reasoning in latent space, representation learning and grokking. It then examines AI-assisted research, recursive self-improvement, coding-agent limitations, and whether alternative architectures can outperform transformers. The closing discussion considers data efficiency, robotics, restrictions on self-improving systems, and open-source models.