Crazy Wisdom
Episode #510: Open Source, Open Minds: a Conversation with Dax Raad on the Future of Coding
- open source development
- command line interfaces
- long-tail integration
- coding agents
- terminal UI
- TUI frameworks
- ease of adoption
- universality of the CLI
This video isn't available here. Try YouTube, or listen to the audio below.
Watch on YouTubeAbout this episode
Timestamps
00:00 Stewart Alsop and Dax Raad open with the origins of OpenCode, the value of open source, and the long-tail problem in coding agents.
05:00 They explore why command line interfaces keep winning, the universality of the terminal, and early adoption of agentic workflows.
10:00 Dax explains pushing the terminal with TUI frameworks, rich interactions, and constraints that improve UX.
15:00 They contrast CLI vs. chat UIs, discuss voice-driven reviews, and refining prompt-review workflows.
20:00 Dax lays out fast feedback loops, slow vs. fast models, and why autonomy isn’t the goal.
25:00 Conversation turns to model switching, open-source competitiveness, and real developer behavior.
30:00 They examine inference economics, Chinese open-source labs, and emerging U.S. efforts.
35:00 Dax breaks down incumbents like Google and Microsoft and why scale advantages endure.
40:00 They debate centralization vs. decentralization, choice, and the email analogy.
45:00 Stewart reflects on building products; Dax argues for healthy creative destruction.
50:00 Hardware talk emerges—Raspberry Pi, robotics, and LLMs as learning accelerators.
55:00 Dax shares insights on terminal internals, text-as-canvas rendering, and the elegance of the medium.
Key Insights
- Open source thrives where the long tail matters. Dax explains that OpenCode exists because coding agents must integrate with countless models, environments, and providers. That complexity naturally favors open source, since a small team can’t cover every edge case—but a community can. This creates a collaborative ecosystem where users meaningfully shape the tool.
- The command line is winning because it’s universal, not nostalgic. Many misunderstand the surge of CLI-based AI tools, assuming it’s aesthetic or retro. Dax argues it’s simply the easiest, most flexible, least opinionated surface that works everywhere—from enterprise laptops to personal dev setups—making adoption frictionless.
- Terminal interfaces can be richer than assumed. The team is pushing TUI frameworks far beyond scrolling text, introducing mouse support, dialogs, hover states, and structured interactivity. Despite constraints, the terminal becomes a powerful “text canvas,” capable of UI complexity normally reserved for GUIs.
- Fast feedback loops beat “autonomous” long-running agents. Dax rejects the trend of hour-long AI tasks, viewing it as optimizing around model slowness rather than user needs. He prefers rapid iteration with faster models, reviewing diffs continuously, and reserving slower models only when necessary.
- Open-source LLMs are improving quickly—and economics matter. Many open models now approach the quality of top proprietary systems while being far cheaper and faster to serve. Because inference is capital-intensive, competition pushes prices down, creating real incentives for developers and companies to reconsider model choices.
- Centralization isn’t the enemy—lack of choice is. Dax frames the landscape like email: centralized providers dominate through convenience and scale, but the open protocols underneath protect users’ ability to choose alternatives. The real danger is ecosystems where leaving becomes impossible.
- LLMs dramatically expand what individuals can learn and build. Both Stewart and Dax highlight that AI enables people to tackle domains previously too opaque or slow to learn—from terminal internals to hardware tinkering. This accelerates creativity and lowers barriers, shifting agency back to small teams and individuals.
Episode transcript
Welcome to the Crazy Wisdom Podcast. This podcast is for you. If you have an insane drive to find the truth of things, it's not the good answers that we seek, but the good questions. I interview a range of different guests from many different fields, all with the intention to uncover the simple truths that are hidden in plain sight. Most people don't want to go there. I go there, my guests go there, and you benefit. Please let me know if you enjoy these episodes and as always, subscribe on itunes, Spotify or wherever you listen to the podcasts.
Welcome to the Crazy Wisdom Podcast. I've got Dax Rad here and he is the co founder of opencode, which I've been using along with all the other command line interfaces to learn how to vibe code. And so we're just gonna do something a little bit different here, which is that I'm gonna send out there. Yes. I'm gonna send this link to docs on Twitter and then. So he can retweet it. Okay. So if you go ahead and retweet it, then everybody will be able to see.
So interesting where we are in time right now. I love the fact that you are competitive with all the proprietary ones, which are all closed source and you guys are open source. Can you talk more about what it's like to build an open source command line interface for an agent?
Yeah, I mean, there's two sides. There's the open source side and there's the actual thing. We're building the open source side. We've been doing this for a while. Pretty much every line of code I've written since 2021 has been open source. We've been building open source stuff for quite some time. And the projects we like to pick are we try to look for opportunities where there's a problem and the problem has a long tail, which means there's a wide range of things that the solution needs to integrate with. We looked at the coding agent space, and that long tail manifests as all the different models, all the different providers, et cetera. That's where open source is really great because as a small team, you're not really going to be able to cover something that wide just as the core team. But open source helps you tap into the larger user base and have them polish the experience in some of the places that you don't have time to focus on. Also, it's not just time. It's like the parts of the product that are good are the parts that the people that work on it use themselves. I don't Use. I'm not someone that like a lot of people, their company has an Azure account that has access to an LLC and they're mandated to use that. I am never going to be in that situation. I'm never going to be able to create a polish experience for that, but someone in the community will. So that's what's been fun about doing this work for open code is there's just so many different environments that this thing can work in and having someone representative from the community to represent that environment and push it forward. So we look for opportunities like that. Because otherwise you can make any product open source, that's fine, but when there is this long tail thing, that's when open source is actually an advantage.
Your first full transcript is free. After that, an email opens every transcript in the index — a list of readers we can write to, not a guest book.