Why AlphaEvolve Is Already Obsolete: When AI Discovers The Next Transformer | Machine Learning Street Talk Podcast

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-assignment problem across models turns out to be genuinely hard.

• Concrete results: state-of-the-art circle packing with dramatically fewer evaluations, second place in an AtCoder competitive programming challenge, evolved load-balancing loss functions for mixture-of-experts models, and agent scaffolds for AIME math benchmarks.

• Are these systems actually thinking outside the box, or are they parasitic on their starting conditions?: When LLMs run autonomously, "nothing interesting happens." Robert pushes back with the stepping-stone argument — evolution doesn't need to extrapolate, just recombine usefully.

• The AI Scientist question: can automated research pipelines produce real science, or just workshop-level slop that passes surface-level review? Robert is honest that the current version is more co-pilot than autonomous researcher.

• Where this lands in 5-20 years: Robert's prediction that scientific research will be fundamentally transformed, and Tim's thought experiment about alien mathematical artifacts that no human could have conceived.

Link to the Full Episode: https://www.youtube.com/watch?v=EInEmGaMRLc

Spotify

Apple Podcasts