Robert Lange, founding researcher at Sakana AI, joins Tim to discuss Shinka Evolve — a framework that combines LLMs with evolutionary algorithms to do open-ended program search. The core claim: systems like AlphaEvolve can optimize solutions to fixed problems, but real scientific progress requires co-evolving the problems themselves. In this episode: - Why AlphaEvolve gets stuck: it needs a human to hand it the right problem. Shinka Evolve tries to invent new problems automatically, drawing on ideas from POET, PowerPlay, and MAP-Elites quality-diversity search. The architecture of Shinka Evolve: an archive of programs organized as islands, LLMs used as mutation operators, and a UCB bandit that adaptively selects between frontier models (GPT-5, Sonnet 4.5, Gemini) mid-run. The credit...
