What Most People Get Wrong About Evolution | Akarsh Kumar

A lot of people in AI treat evolution as a dumb fallback, basically random search for when you can't take a gradient. Akarsh Kumar thinks that is wrong. Selection hangs on to partial solutions, so mutations only need to be useful about 1% of the time for the search to keep making progress.Akarsh is a PhD student at MIT working with Phillip Isola, works with Sakana AI, and is first author of the Fractured Entangled Representation paper with Kenneth Stanley, Jeff Clune and Joel Lehman. He tells Tim Scarfe why the path a learner takes may shape the structure of what it learns, and why that is a different way of looking at intelligence from the statistical one.Most of the conversation is about ASAL, the method he led for searching whole spaces of artificial worlds. Rather than predict what a rule will do, ASAL runs the simulation and asks a foundation model what happened. Mapped across all 262,144 Life-like rules, the most interesting worlds sit on one small island. Along the way: Game of Life, Lenia (with a clip from its creator, Bert Chan), neural cellular automata, Boids, Particle Life and the emergence of persistence.---TIMESTAMPS:00:00:00 Intro: artificial life, ASAL and Core War in four minutes00:04:19 Life as it could be, not just as it is00:05:46 Why the order you learn things in matters00:08:33 No shortcuts: Wolfram, novelty search and regularisation00:10:44 Kenneth Stanley: the path matters, not just the destination00:11:31 Statistical intelligence vs regularity-based intelligence00:13:49 Artificial chemistry and other possible universes00:15:59 Convergent patterns: shadows of the substrate?00:18:02 How Conway's Game of Life works00:20:49 Change one cell, change everything?00:22:31 Lenia (with Bert Chan) and neural cellular automata00:25:26 Boids, Particle Life and cell-like creatures00:28:47 Persistence, entropy and what life is00:30:15 ASAL: a foundation model as the critic00:34:04 Impostors inside the simulation00:36:50 From primordial soup to alien animals00:38:26 262,144 rules and the island of open-endedness00:40:17 From artificial life to AGI00:41:35 Core War: Game of Thrones, Turing edition00:43:22 LLMs as the mutation step: evolving warriors00:46:03 Evolution is anything but random---REFERENCES:paper:[00:04:19] ASAL (Kumar et al.)00:08:08]" rel="nofollow noopener ugc" target="_blank">arxiv.org/abs/2412.17799[00:08:08] Assembly theory 00:09:54]" rel="nofollow noopener ugc" target="_blank">nature.com/articles/s41586-023-06600-9[00:09:54] FEP paper00:22:38]" rel="nofollow noopener ugc" target="_blank">arxiv.org/abs/2505.11581[00:22:38] Lenia: Biology of Artificial Life (Bert Chan)00:23:20]" rel="nofollow noopener ugc" target="_blank">arxiv.org/abs/1812.05433[00:23:20] Growing Neural Cellular Automata (Mordvintsev et al.)00:41:35]" rel="nofollow noopener ugc" target="_blank">distill.pub/2020/growing-ca/[00:41:35] Digital Red Queen: Core War with LLMs (Kumar et al.)00:43:42]" rel="nofollow noopener ugc" target="_blank">arxiv.org/abs/2601.03335[00:43:42] MAP-Elites 00:44:55]" rel="nofollow noopener ugc" target="_blank">arxiv.org/abs/1504.04909[00:44:55] AlphaEvolve 00:47:03]" rel="nofollow noopener ugc" target="_blank">arxiv.org/abs/2506.13131[00:47:03] AutoML-Zero (Real et al.)00:07:04]" rel="nofollow noopener ugc" target="_blank">arxiv.org/abs/2003.03384book:[00:07:04] Why Greatness Cannot Be Planned (Stanley and Lehman)00:18:12]" rel="nofollow noopener ugc" target="_blank">link.springer.com/book/10.1007/978-3-319-15524… Conway's Game of Life00:25:27]" rel="nofollow noopener ugc" target="_blank">en.wikipedia.org/wiki/Conway%27s_Game_of_Life[… Boids (Craig Reynolds)00:27:12]" rel="nofollow noopener ugc" target="_blank">red3d.com/cwr/boids/[00:27:12] Particle Life (Tom Mohr)00:41:50]" rel="nofollow noopener ugc" target="_blank">github.com/tom-mohr/particle-life[00:41:50] Core War00:08:49]" rel="nofollow noopener ugc" target="_blank">corewar.co.uk/other:[00:08:49] Computational irreducibility (Stephen Wolfram)00:10:46]" rel="nofollow noopener ugc" target="_blank">wolframscience.com/nks/p737--computational-irr… MLST: Why Every AI Model Is an Impostor (Kenneth Stanley, FER documentary)00:28:30]" rel="nofollow noopener ugc" target="_blank">youtube.com/watch?v=o1q6Hhz0MAg[00:28:30] MLST: Blaise Agüera y Arcas on life emerging from codeyoutube.com/watch?v=rMSEqJ_4EBk---LINKS:Akarsh Kumar: akarshkumar.com/ASAL project page and demos: pub.sakana.ai/asal/Digital Red Queen project page: sakana.ai/drq/RESCRIPT:https://app.rescript.in…