Subvolts take Explore AI that grows like life, not just trained software, for adaptive intelligence. Apr 6, 2026 - Developers
- Learn about alternative AI architectures inspired by biology that continuously adapt and self-organize.
- Business
- Understand emerging AI paradigms that could lead to more resilient and adaptable intelligent systems.
This episode features a leading researcher discussing a novel approach to AI development inspired by biological evolution, offering a forward-looking perspective.
#330 Sebastian Risi: Why AI Should Be Grown, Not Trained
Audio streams from Craig S. Smith. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Sebastian Risi joins Craig Smith on Eye on AI to discuss growing AI like life instead of training it like software. Risi, a neuroevolution researcher, explains how evolutionary algorithms can create continuously learning, self-organizing AI systems. The episode explores plastic neural networks, AI resilience, and models that develop organically, potentially merging LLMs with evolutionary search for creative problem-solving.
Imagine AI that learns and changes throughout its life, like a living thing, instead of being built and trained once. This episode discusses how AI could evolve its own structures and recover from damage, offering a new path for creating smarter systems.
This episode offers a perspective on AI development beyond current transformer models, appealing to researchers and AI enthusiasts interested in alternative architectures. It connects to frontier labs' work by exploring how biological inspiration could lead to more adaptable and robust AI systems, potentially addressing limitations in current training paradigms. Listeners will learn about neuroevolution and artificial life concepts, understanding how AI could evolve organically rather than being strictly programmed.
- HostCraig S. Smith
- GuestSebastian Risiprofessor and leading researcher in neuroevolution and artificial life
- Episode: #330 Sebastian Risi: Why AI Should Be Grown, Not Trained
- Show: Eye on AI
- Length: 61 minutes
- Guest's Field: Neuroevolution and artificial life
- Core Concept: Growing AI like life, not training like software
AI has been trained like software.
But what if it should be grown like life?
In this episode of Eye on AI, Craig Smith sits down with Sebastian Risi, professor and leading researcher in neuroevolution and artificial life, to explore a fundamentally different approach to building intelligence, one inspired by how nature evolves, grows, and adapts.
Sebastian explains why traditional AI systems are limited by fixed architectures and one-time training, and how evolutionary algorithms can create systems that continuously learn, self-organize, and even grow their own neural structures over time.
They dive into concepts like plastic neural networks that keep updating during their lifetime, AI systems that can recover from damage, and models that develop from a single "cell" into complex structures, similar to biological organisms.
The conversation also explores how combining large language models with evolutionary search could unlock more creative and open-ended problem solving, from merging specialized models to building AI systems capable of generating and testing scientific ideas.
If you want to understand where AI is headed beyond today's transformer models, and why the future may look more like living systems than software, this episode offers a clear and thought-provoking perspective.
Subscribe for more conversations with the people building the future of AI and emerging technology.
Stay Updated:
Craig Smith on X: https://x.com/craigss
Eye on A.I. on X: https://x.com/EyeOn_AI
(00:00) Why copy nature's evolution for AI
(01:20) What neuroevolution actually means
(05:52) How evolutionary search replaces gradients
(08:03) Plastic neural networks and continuous learning
(11:53) Growing neural networks like living systems
(18:08) Scaling challenges and limits of growth
(23:16) Can evolving systems replace LLM training
(27:28) Continual learning and model merging
(30:27) Artificial life, self-repair, and resilience
(35:10) AI scientists and evolution with LLMs
- neuroevolution
- Sebastian Risi
- Using evolutionary processes, like natural selection, to develop AI systems and their neural networks.
- plastic neural networks
- Sebastian Risi
- Neural networks that can change and update their structure and connections throughout their operational lifetime.
55 min42 min51 min34 minUkraine's Secret Weapon: The Points System Winning the Drone War | Andrii Hrytseniuk
WithAndrii Hrytseniuk
Questions people ask
- What is neuroevolution?
- Neuroevolution uses evolutionary algorithms to create and adapt neural networks, mimicking natural evolution to build AI systems.
- How is this different from current AI training?
- Unlike traditional AI trained with fixed architectures, this approach allows AI systems to continuously learn, self-organize, and even grow their own neural structures over time.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Craig S. Smith.