Subvolts take Explore self-improving AI agents and their impact on development with Nous Research's CTO. May 21, 2026 - Developers
- Learn about emerging AI agents that blur the line between software and autonomous collaborators, and how they might change development.
- Business
- Understand how evolving AI tools are becoming autonomous collaborators, potentially impacting future business operations and human roles.
This is a solid interview with a leader from an AI research organization discussing advanced agent technology.
Hermes Agent: Agents that grow with you
Audio streams from Daniel Whitenack and Chris Benson. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Practical AI hosts Daniel Whitenack and Chris Benson interview Jeffrey Quesnelle, co-founder and CTO of Nous Research, about Hermes Agent. They explore self-improving AI agents, recursive learning, and evolving AI tools. The discussion also touches on the distinction between models and harnesses, the changing role of developers, and what uniquely human qualities remain as AI advances.
This episode discusses new AI agents that can learn and improve over time, like a digital assistant that gets smarter. It explores how these evolving tools might change software development and what makes humans special as AI gets more capable.
This episode delves into the cutting edge of open-source AI, specifically self-improving agents like Hermes. It's for developers and AI enthusiasts tracking the evolution of AI tools beyond static models. Quesnelle's insights offer a glimpse into how AI is becoming a collaborator, raising questions about human roles in an AI-accelerated future. This aligns with frontier labs' work on agentic systems and autonomous AI.
- HostDaniel Whitenack
- HostChris Benson
- GuestJeffrey Quesnelleco-founder and CTO, Nous Research
- Guest: Jeffrey Quesnelle, Nous Research co-founder and CTO
- Show: Practical AI
- Length: 52 minutes
- Topic: Hermes Agent, self-improving AI Agents, recursive learning systems
Chapters from the publisher ↗ · Transcript ↗ Key moments and transcript search come with a later piece.
Open Source AI is entering a new era, one shaped by self-improving AI Agents, recursive learning systems, and rapidly evolving AI Tools that blur the line between software and autonomous collaborators. In this episode, Daniel and Chris sit down with Nous Research co-founder and CTO Jeffrey Quesnelle to explore Hermes Agent. Along the way, they discuss models vs. harnesses, the changing role of developers, and one of the biggest questions facing the AI Future: what remains uniquely human as AI capabilities continue to accelerate?
Featuring:
- Jeffrey Quesnelle – Website, LinkedIn
- Chris Benson – Website, LinkedIn, Bluesky, GitHub, X
- Daniel Whitenack – Website, GitHub, X
Links:
Sponsors:
- Framer: The enterprise-grade website builder that lets your team ship faster. Get 30% off at framer.com/practicalai
- Prediction Guard: A self-hosted AI control plane for running agents in high impact environments. predictionguard.com/practicalai
Upcoming Events:
- Register for upcoming webinars here!
- Midwest AI Summit 2026
- recursive learning systems
- Jeffrey Quesnelle
- AI systems that can learn from their own learning processes.
- harnesses
- Jeffrey Quesnelle
- Frameworks or systems that use AI models.
44 minNarrative intelligence and the human advantage
WithReed Frerichs
47 minOpen models and the future of Physical AI with NVIDIA
WithMing-Yu Liu
49 minFrom AGENTS.md to Enterprise Deployment
WithNick Kuhn
57 min
46 minHow Cursor Trained Composer on Fireworks: Distributed Infrastructure for High-Performance RL
WithFederico Cassano, Dmytro Dzhulgakov
Questions people ask
- What is Hermes Agent?
- Hermes Agent is an example of a self-improving AI agent that is part of a new era of recursive learning systems and evolving AI tools.
- What is discussed regarding AI and humanity?
- The episode discusses the changing role of developers and one of the biggest questions facing the AI future: what remains uniquely human as AI capabilities accelerate.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Daniel Whitenack and Chris Benson.