Uploaded March 2026 | Updated November 2026, 4 days ago
AI is making developers dramatically more productive...so why is everyone so exhausted? In this episode, Scott talks with Steve Yegge, legendary blogger and creator of Gas Town, a multi-agent orchestrator he describes as "Kubernetes for coding agents." Steve shares his theory of the "AI Vampire," that working alongside AI drains human energy Colin Robinson-style (What We Do In The Shadows), even as output skyrockets. They dig into what happens when you're managing ten or twenty Claude Code instances at once, who actually captures the value of a 10x productivity boost, and why the most important thing developers can do right now might be to close the laptop and go for a walk.
AI is making developers dramatically more productive...so why is everyone so exhausted? In this episode, Scott talks with Steve Yegge, legendary blogger and creator of Gas Town, a multi-agent orchestrator he describes as "Kubernetes for coding agents." Steve shares his theory of the "AI Vampire," that working alongside AI drains human energy Colin Robinson-style (What We Do In The Shadows), even as output skyrockets. They dig into what happens when you're managing ten or twenty Claude Code instances at once, who actually captures the value of a 10x productivity boost, and why the most important thing developers can do right now might be to close the laptop and go for a walk.

![Trusting Agentic AI with Dr. Dawn Song
In this partnership episode between Hanselminutes and the ACM Bytecast, Scott talks with Dr. Dawn Song, MacArthur Fellow and leading researcher in computer security and AI and co-director at the Berkeley Center for Responsible Decentralized Intelligence about how privacy-preserving computation, fairness, and accountability can help us design intelligent systems we can actually trust.
https://agenticai-learning.org [https://www.youtube.com/redirect?event=video_description&redir_token=QUFFLUhqbTUzSDBhTGg1NjJMTmQtQl8yc1VSaWhVdEJYZ3xBQ3Jtc0ttNmNLSHdrTFJYQUJGOENIaTlyampKaGVha1hqVVdaZHdBNjl0TFpCTGFMTkp0c2g1NHYwOHpfYjZkRlFWQmw4M0tDRDdKbTBfTG9sNGloUjlxY0JfcjlZM3RWMGNQVGRTd2pvUklncWtQYXBEVHFlWQ&q=https%3A%2F%2Fagenticai-learning.org%2F&v=MnKEOy38Ckc]
This episode is sponsored by Mailtrap.
Check out https://l.rw.rw/hanselminutes for modern email delivery that developers love.
00:00 The Mystery and Power of Large Models
00:28 Episode Sponsorship by MailTrap
00:58 Introduction to Dr. Dawn Song
01:25 From Physics to Cybersecurity: Dr. Songs Journey
02:55 Impact of the MacArthur Fellowship on Dr. Songs Research
03:58 Dr. Songs Diverse Research Interests
05:16 How do you find the balance between what academia expects from a people talking in a room perspective and the lets do things, lets ship products, lets make lives better approach?
08:26 Mission of the Berkeley Center for Responsible Decentralized Intelligence
10:08 What does it feel like to hear things youve been working on for six or seven years now start to break out into the mainstream?
14:26 Security Challenges in Agentic AI
20:21 Complexities and Unpredictability of AI Systems
25:19 Dr. Songs MOOC on Agentic AI
29:16 Open Competition for Agent Evaluation
33:34 Practical Applications of Agentic AI in Workflows Trusting Agentic AI with Dr. Dawn Song](https://i.ytimg.com/vi/9hCyolbVm5E/mqdefault.jpg)








