1011: tmux + Terminal Maxxing with Ben Vinegar

Scott and Wes sit down with Ben Vinegar, former Syntax GM and founder of Modem.dev, to geek out over terminal-maxxing, from SSH-based development and tmux workflows to AI-powered coding agents. Ben also demos two of his open source tools: Hunk, a slick terminal code reviewer with 4k+ GitHub stars, and TermDraw, a terminal-based diagramming tool that posts directly to your agent. Show Notes 00:00 Welcome to Syntax! 00:49 Introduction to Modem and AI Project Management 01:40 Exploring Terminal Usage and Productivity 04:26 Setting Up Remote Development Environments 08:38 The Power of TMUX in Development 11:20 What makes TMUX splitting different? 12:46 Integrating AI with Terminal Workflows 14:56 The Future of Terminal Applications 17:31 Balancing GUIs and Terminal Interfaces getfresh.dev Ben’s talk at AI Engineer Miami 24:39 Navigating Development Tools and Environments 26:44 The Balance of Security and Convenience in Coding 30:27 Cautionary Tales: The Risks of YOLO Mode 33:53 Innovative Tools for Enhanced Coding Experience 34:09 Hunk: Terminal code review. 41:39 TermDraw: A New Way to Visualize Code and Ideas 46:22 The Dynamics of Open Source Contributions 48:31 Visualizing Code: Tools and Techniques 50:54 Podcasting and Editing Processes State of Agentic Coding. Podguy: Agent-driven post-production workflow for video podcasts 56:23 Introducing Modem: A Product Intelligence Platform 01:01:39 Connecting Feedback to Product Development 01:03:15 Sick Picks Sick Picks Ben: Nirvanna: The Band - The Show - The Movie, Timecrimes Shameless Plugs Ben: https://modem.dev/ Hit us up on Socials! Syntax: X Instagram Tiktok LinkedIn Threads Wes: X Instagram Tiktok LinkedIn Threads Scott: X Instagram Tiktok LinkedIn Threads Randy: X Instagram YouTube Threads

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Scott Tolinski?

  Welcome to Syntax. Today, we have the former general manager of Syntax and the co-founder of Modem, which is an AI project manager and a non-annoying terminal guy. Too oftentimes, we have terminal folks who are just, "Why don't you do it this way?" Ben has a really awesome setup, and we're going to be diving into all of the ways that he is using his terminal for running agents, all of the cool things that he is doing. And man, I'm so excited to catch up with Ben, but I'm also excited to dive into some of his projects, because just watching his most recent talk, man, it solves a lot of the problems I'm

• 0:42Scott Tolinski?

  personally having. So, we're going to dive into all of that and more. My name is Scott Tolinski, and with me is always this Wes. But most importantly, welcome, Ben.

• 0:50Wes Bos?

  Hey, guys. It's good to be back.

• 0:52Scott Tolinski?

  Yeah. This is your second time on Syntax?

• 0:56Wes Bos?

  This is the third time. This is the third time. Going back a while.

• 1:00Scott Tolinski?

  Yeah.

• 1:00Wes Bos?

  But the last one was an emergency fill-in, so it's nice to be, you know, properly invited.

• 1:08Scott Tolinski?

  Sometimes we need the emergency fill-ins, and you're just the guy for that, so.

• 1:12Wes Bos?

  Yeah. You've got lots to say. And Ben had a talk at the AI Engineer Conference a couple of weeks ago, and I just watched the video, and I thought it was super interesting, his like rig of like, how he's doing agent decoding, how it's done remotely, SSHing into boxes and doing it on a box versus locally. TMOx, I've been like, I would say it's fair that I'm a TMOx hater.

• 1:37Scott Tolinski?

  You're a hater.

• 1:38Wes Bos?

  And maybe changed, you know? Never, never really understood all of the hype around it, but Ben's usage of it, pretty good. So, I think like, let's dive into that, man.

• 1:50Scott Tolinski?

  Yeah, I'm a TMOx not-understander. Yes. I'm curious.

• 1:54Wes Bos?

  Okay, so.

• 1:56Speaker 02

  I don't know. The background is, look, I'm a Mac enjoyer. Okay. I like IDEs. I have used Cursor primarily, but even before that, VS Code, like probably a lot of people. Look, even gave the JetBrain stack like a pretty good go there for a while. So like, that's like, I like debuggers. I like all those tools and everything. And look, when we're building modem, I think it's worth mentioning that modem is like a, we started like a year ago. And it's AI product management, product. It could be project too. That's okay.

• 2:30Wes Bos?

  Oh, product. Did I say project?

• 2:31Speaker 02

  Yeah, but like, you know, the lines blur between them, so it's okay. Really quickly, product management, you know, helping you do the non-coding tasks. I could talk about this later, but you know, synthesizing feedback from customers. Making sure your ticket backlog makes sense, following up with users when you land some stuff. I'll cut it off there. We started about a year ago and we actually decided that we would code gen the product, like the project from the very beginning. It was kind of like, look, the whole thesis of modem is AI coding is 100% going to be totally real. And if you believe that, then it's going to go down, like the time to deliver code is just going to keep dropping. And then like the other parts of your job are going to be boring and slow. So can we work on that?

• 3:12Speaker 02

  And that's kind of where modem came from. And if we're going to build it, if we believed in that future, we had to like build it that way from the beginning. So I'd say it's like 99% code gen, but like tasteful curated code gen, like everything is code reviewed. We go back and forth with the agents a lot. We do edit the code. Man, I was having this problem, which was, I feel like it's a problem that you're seeing a lot of lately, which is. I don't have a setup where I have like a, there's no Jira backlog. Or linear backlog where agents are just spinning up all day.

• 3:46Wes Bos?

  Yeah.

• 3:47Speaker 02

  Have you guys tried that?

• 3:48Scott Tolinski?

  No.

• 3:48Wes Bos?

  No, I don't, I, I think that's the craziest thing that people have like agents just constantly picking things up and churning. Like if I, if I were to let a rip on my like GitHub issues for all of my projects, I'd, I'd be done in a couple of days. And it would not be very good.

• 4:04Speaker 02

  Yeah, it would not be very good. Right. Yeah. I like, I've experimented with it.

• 4:11Speaker 02

  Even modem, because it like it ingests data and like conversation data and says like, hey, these are like product features that people are interested in. I've experimented with just having like modem spin up agents to build stuff. I don't know. I don't think we're there yet, guys. So I was just thinking, oh, like, how can I get more done? And I started thinking about all the ways that I was being kind of like, I don't know, not getting as much productivity as I wanted. And one of the most basic ones, frankly, is that the machine has to be on all the time, you know? And I feel like you're seeing this online with people joking about cracked laptops, or I feel like I even just saw a video of someone with like a harness walking down the street with their laptop, like, I don't know, just like this.

• 4:51Scott Tolinski?

  Oh, I was just telling Wes moments ago, I installed a, it's an app called, oh, man, what is this thing called? It's called

• 4:58Speaker 02

  Caffeinate.

• 4:59Scott Tolinski?

  Keeping You Awake, which is like a free version of caffeinate, which, yeah, it means you can shut your lid of your laptop and have your agents still keep running.

• 5:08Speaker 02

  Even if I had them still running, I don't know, I don't have like a permanent internet. Like, maybe you can solve this entirely. I do have a friend who's like walking around with a massive battery in his backpack, for example, and like a permanent internet connection. So people are doing it this way.

• 5:21Scott Tolinski?

  Oh, my God.

• 5:22Speaker 02

  Yeah, you know, like I'd start a job in the middle of the night. Like, I would, I don't know, you ever done this? Like, I'd queue, you know, like, I'd write like a plan, and then like, maybe like midnight, I'd be like, go, you know?

• 5:32Scott Tolinski?

  Oh, I've done this, yes.

• 5:33Speaker 02

  And then I come back in the morning and find out, well, one, maybe it got blocked on a tool approval call because I wasn't running dangerous mode. And even, even though I thought I'd approved every single tool, like, nope, it tried to run one thing that I didn't approve. And so it stopped 20 minutes in, or it turned off, or whatever. So, look, I just started running, running my agents, you know, by shelling into machines leased, or whatever, like, you know, get a, get a droplet, or get a VPS from Hertz or our Digital Ocean. I've done a lot of that. And I also just have like a pretty beefy machine that I keep connected in my basement with now 3 gig fiber.

• 6:14Speaker 02

  Which is pretty sweet.

• 6:15Wes Bos?

  That's awesome.

• 6:16Speaker 02

  The connectivity one is another one. Like, if you're on the plane, if you're on the train, you're trying to work with agents and you barely got an internet connection.

• 6:22Wes Bos?

  Yeah.

• 6:22Speaker 02

  As long as you can shell into a machine that has great internet, like, you can, you can go all day. So anyways, that's, that's the preamble. I'll, I'll pause there because I've been talking here, you know?

• 6:31Wes Bos?

  Yeah, I, I find that really interesting because I've been finding like my, I got the MacBook M1, just M1 Max, whatever, like the, the best one you could buy when, when I got it. And I've been noticing recently, it's like, it's starting to slow down. And a lot of that is, is because I'm running several agents at once. There's background processes, you know, you're running a lot more software. Things are starting to get laggy. And I often think like, like, maybe I should just be running all of this stuff not on my machine. Right? You can run it when you're not there. You can run it when, like, the, the whole IBM Thin client, like, are we, are we back to that?

• 7:10Speaker 02

  We, we could be. I'll also add, I was hitting the, the machine, like, limits too. Like, look, you get two agents that are trying to hit like your test suite at the same time. Depending on, depending on the test suite. Like, a lot of our test suite hits the database, so they're pretty heavy. I've hit problems with like Macs, you know, I have to optimize the number of connections you're opening, for example, on the test suite, but I get up to, I get, I get up to Mac CPU pretty fast.

• 7:35Wes Bos?

  Yeah.

• 7:35Speaker 02

  Even on an M5. I don't know if you guys are there on that.

• 7:38Wes Bos?

  Not yet. Not yet. I've been waiting for the next ones to come out. We, yeah, waiting for the next one. But also it's just like, there's so many processes that get started and not stopped and just kind of sit around and hang out and take up space and all this stuff.

• 7:51Speaker 02

  Yeah, so, I don't know. Look, I just committed, I, I may have had a weird setup anyways. Like, I really enjoy Open Code and Py and even just Claude Code. I would do this thing with Cursor where I'd actually just open up like a window, like a dedicated terminal for like Claude Code or Open Code, but I would just use Cursor for like Tab Complete and like navigating diffs and editing code.

• 8:14Speaker 02

  So I felt like you're halfway there, like you're using, you know, once you realize that you're just using the terminal agent quite a lot and like, well, how much do I need this IDE? And so that turned into like, you know, as a norm, as a norm core, like Mac user, what if I just shell in to my machine and I just do all the work there? You lose a bunch of things. I don't want to say that it like is awesome, but I've learned a bunch of things along the way.

• 8:38Wes Bos?

  So like, like, tell us about that. Cause like I've, I've SSH into boxes before and like, what I find is that it's a little bit limited because like you don't have all the stuff that you have installed on your machine. And certainly you can get all of that set up. So like, is that what you're doing? You're just getting like a, a box with everything installed that you needed, or you just kind of let the, the agent install everything? So that's kind of like my first question. And the second one is like, doesn't the terminal suck as a UI? I like, I use it every single day, but like, limited, isn't it?

• 9:09Speaker 02

  Well, let me start. I'll, I'll give the setup. The setup that I use is TailScale, you know, SSH into the machine. I think you guys have talked about TailScale here, maybe even a dedicated video, if I remember correctly.

• 9:22Scott Tolinski?

  Yep. Oh yeah. I use, I love TailScale. I use it for every system. I have even my, my wife set up on TailScale to connect to our services.

• 9:33Speaker 02

  Yeah. Still watching this syntax content, still following along.

• 9:37Wes Bos?

  Right on.

• 9:38Speaker 02

  Was there a TailScale episode or did I hallucinate this whole thing?

• 9:41Scott Tolinski?

  No, it was a video. It's a dedicated video.

• 9:42Speaker 02

  Yeah. Okay.

• 9:43Wes Bos?

  We, we talked about it quite a bit. I've been using CloudFlare Tunnels. Scott's been using TailScale. So we've, we've mentioned it on several podcasts.

• 9:50Scott Tolinski?

  I made a video all about my setup, which is similar to yours, but missing several key things that I'm excited to dive into.

• 9:57Speaker 02

  And then after that, it's TMX and TMX is a window multiplexer. There's other ones of these that are more modern, like Zellage. Zellage is a popular one. Played around with that, but I'll, I'll explain why TMX maybe a little bit more later because there's some real advantages to it. TMX is a window manager for the terminal. So that gives you a couple of things like one, you can actually create windows, like panes. You can split the terminal, just as you could split Ghosty or I term, or even Chrome, you can split like inside a Chrome tab, you can split that now. If you played around with that. So same thing you can get on TMX and then you can have like, well, I can have my coding agent on the left. So I can have open code or Py or Claude there on the left. And then on the right, I'll usually just have.

• 10:43Speaker 02

  Maybe just like a raw terminal and I'll go into an editor, I'll look at a diff tool. And that's usually most of how I work. If I need to look at a server, I can also get to that via tail scale. Or often I'll just like build something and push it to a branch and let, I use Vercel a lot, like using Vercel preview branches, do the work for me of like making, you know, if you have reasonable confidence in the agent today to build something somewhat correctly, you know, then you can, then I can go and take a look at the preview branch and poke around with it if we're talking like a web project, for example. I'm building a lot of terminal stuff, so I just use that on the terminal.

• 11:20Scott Tolinski?

  How is TMX different than splitting your ghosty term? Like, because I use like split panes in my term all the time. But like, what makes TMX panes different than that?

• 11:32Speaker 02

  Two major reasons. One is that you can detach and reattach to your TMX session from anywhere, whether that's ghosty or iTerm or another computer, you know, in a different room. And I think that's really great because you end up, you kind of build a little workspace, you know, so I'll usually have five windows with different projects that I can kind of tab between. And there's commands that you learn for doing this. And each of those windows has like split panes. And sometimes I split them a little bit differently, depending on what I'm trying to achieve. And you can just, you know, so if you disconnect, you can reconnect and you get that all back. Whereas I think if you split all the, let's say you do a whole bunch of windows in ghosty and you split them or whatever, if you disconnect,

• 12:17Speaker 02

  you've actually got to reconnect every single one of those. If that makes sense, like they're all dedicated.

• 12:22Wes Bos?

  Yeah, like you're, that's just multiple SSH connections, right? Yeah, that's, that's no way to live.

• 12:29Scott Tolinski?

  That's how I live currently. That's, that's why I'm so interested in this. Yes.

• 12:34Speaker 02

  Look, I think if you just want like the UX, I think Zellij, Z E L L I J, is almost like an easier one to use. I've played around with it. I, some people in this office here that use it. But the second reason why TMX is this, and why, and not Zellij, TMX has a CLI interface that's pretty cool. It allows you to inspect active sessions and to send keys and to manipulate them. So from one session, you can be like, hey, go read the logs in TMX pane one. Okay. And now your coding agent just has to run a bunch of CLI commands, which looks something like tmux space capture pane 1, tmux space,

• 13:17Speaker 02

  you know, send keys 1. It can inspect the sessions. It can figure out which pane you're even talking about pretty effectively. So I'm talking about using any coding agent, you know, open code plus like a, like, you know, probably like a sonnet or a, you know, even like a Kimi, like you actually don't need a super smart model to do this. I find like even Kimi K25 will do this totally effectively. So that's valuable for a bunch of things. One, I don't know tmux, man. Like, I didn't learn these keys. So like, the first thing I did, and this was a total experiment, was give me a tour of tmux to a coding agent. You're in a tmux session. Give me a tour. And it just started opening

• 13:59Speaker 02

  up panes and windows and being like, go check this out. I opened up this. I opened up that. And I'm like, wow. Okay, so you don't even need to learn the commands. If you just want to get started with this, you just got to start tmux and you tell your agent, probably even figure it out that it's in one, and you can ask it what you want. Like, I want this in this pane on the right. I want this. I want you to split the pane this way. You can just use natural language and you can get the environment that you want without being like an expert. Does that make sense?

• 14:30Scott Tolinski?

  Yeah. Yeah. So AI, you can talk, you can control the term directly from your, your local agent. Yeah, that that seems very useful to me. Okay.

• 14:40Speaker 02

  I couldn't get it to work with Zellage. This is one of the things where tmux is like, I don't know, it's old, right? It's kind of old.

• 14:46Scott Tolinski?

  Yeah.

• 14:47Speaker 02

  But all that stuff gets baked into the models. If it's old enough and popular enough. So they're really good at navigating it. So that's just for like getting you started, right? Or like, I still use it. Because like, I don't know all the commands. I've gotten better at it. Like, eventually you decide to learn the hotkeys. But I still reach for the agent to help me out. But I think more meaningful is thinking of tmux as a superpower where your agent can just go and read these other panes. So I'm running a server in pane 2. Okay, I'll go debug that by just reading that pane. And it can even scroll up and down. Like, it has like the buffer and everything. So it could scroll up and down. It can read the log output and go, oh, here you go. I've got the answer.

• 15:32Speaker 02

  Does that make it sense?

• 15:33Scott Tolinski?

  Yeah.

• 15:34Wes Bos?

  Yeah, that checks.

• 15:35Scott Tolinski?

  Yeah, yeah.

• 15:36Speaker 02

  So I've gotten to the point where I even run TMX on my local Mac for this reason.

• 15:42Scott Tolinski?

  Yeah.

• 15:42Speaker 02

  Uh, cause you can't do it with ghosty and you can't do it with Iterm.

• 15:46Wes Bos?

  Yeah, cuz like the options you have here are like you, you need multiple terminal windows, right? So you're either having the agent spin up child processes, which you cannot see, or you're opening multiple tabs and you're kind of copy pasting from, from one to another. And, and both of those experiences kind of suck, right? So it, it's nice to, if you have to run multiple terminals to use something like TMX, where you can use it, like that's, in my opinion, that's the best AI experiences, where the AI can use it and you can use it in, in the same, um, the same way. Like, that's why I think the Web MCP stuff is gonna be so good. Is that like, the way that you use it and the way that the agent uses is the same thing?

• 16:32Wes Bos?

  And, and you don't have to have these separate processes, which is like, oh, now I'm doing agent stuff. I'm gonna do it this different way than how I would normally do it.

• 16:41Speaker 02

  Yeah, and it's open source and it works everywhere. So that's, you know, you take those properties, you hit on something there, which maybe this matches for you, but like if you use Claude, you know, and it spins up subagents, you can't, you can see that the subagent is like, it's really reduced to just like a little like, subagent is working, right? Or you can go and maybe go manually go and inspect it. I think they've got like commands, but you could also just run subagents or other agents or whatever, just like use TMX. And you're right, they, they'll just spin up windows or they can spin up windows that you don't see, but they're there in the background that they can then, like, you could go see them if you want.

• 17:18Wes Bos?

  Yeah.

• 17:19Speaker 02

  And I find that pretty useful. I know that there are some extensions for Pi, the coding agent, which use subagents like explicitly through TMX, so that you can see very clearly what they're all doing.

• 17:30Wes Bos?

  So my, my question here, maybe you'll get into this, but like, the solution to this stuff is just running this terminal thing? Like, like, you know what also is, is really good at this is a GUI. And like links and buttons and things you can click and, and like URLs that you can, you can surf to, to see different agents. Like, why try to like recreate this whole environment in the terminal?

• 17:59Speaker 02

  Okay, so.

• 18:01Speaker 02

  Yes, I am trying to recreate the environment in the terminal.

• 18:06Speaker 02

  And that was, once you start working this way and you're like, man, TMX is good, agents are good this way.

• 18:11Wes Bos?

  Yeah.

• 18:11Speaker 02

  I'm digging it. But now I still have like, well, where's my editor gonna be? And how do I run the servers and all this? Like, there's still some missing stuff, right? And look, I'm not like a hardcore Linux user. That's the whole point. So if someone is like, gonna get really mad at me in the comments, like, I'm sorry. I'm sorry if I've gotten this wrong. But like, I didn't even know until the last year that you could use your mouse over the terminal. I really did not. Maybe just because I had no need. It never crossed my mind that I would ever have to do that. But it does. It works pretty good. It works over SSH. So not just, I think people have seen a lot more TUI apps, right? Like Claude Code is the ultimate version of that. It's clear that it uses the mouse, but it also works over SSH too.

• 18:55Speaker 02

  Because it's just like SSH will like pass key codes back and forth that sort of represent where the mouse position is. It works pretty well. So you can get, you can get GUIs over the terminal. OpenTUI is a library that is what's under the hood of OpenCode.

• 19:15Wes Bos?

  Yeah.

• 19:16Speaker 02

  So if you've used OpenCode and you know that it's got these kind of like user interface mechanisms that you like, you can have like sticky components, right? You can have sidebars, you can have sticky footers, popups, toast, modals, like all of that stuff is actually very achievable. And OpenTUI, you can write, you can write OpenTUI apps in a variety of ways, I think, React and Solid. So for me, as a web developer, I was like, oh, I can just write the things that I understand. And I get these like, I get these UI components on the terminal, but it's all the stuff that I remember about like, you know, on-click handlers and, and stuff like that. Does that make sense? Like render, render.

• 19:57Scott Tolinski?

  Yeah.

• 19:58Speaker 02

  So, one, I think you're seeing a wave of like new apps that use the terminal because this technology exists. That's cool. So, a lot of things that I didn't think were possible a year, year, two years ago, and maybe they always were, right? It just took me, uh, took me to look. You can, you can scroll, you can use your mouse, you can do so much of this stuff. And I use some tools, I could talk about them, like, um, there's a text editor I use called Fresh. Could be like fresh.sh, maybe you guys can find it.

• 20:25Scott Tolinski?

  Getfresh.dev.

• 20:26Speaker 02

  Fresh is somebody trying to build something closer to VS code in the terminal. So, you know, like, I look, I use Vim a little bit, just because like, I'm, I'm sure similar to you all, like, eventually you gotta connect to servers, you have to use it, it works everywhere.

• 20:42Scott Tolinski?

  Yeah.

• 20:43Speaker 02

  But I'm not, you know, do I really want to edit all my code that way? Not really. So Fresh has, um, you know, mouse support, and it has, um, key bindings that feel more at home. It's also got like, what do you call it? Like a, a command palette that opens up very like VS code-like. You can open up, I think you can open up a terminal in there, like a sub-termal, um, and you can select with your mouse and delete text, you can go and navigate the menu.

• 21:11Scott Tolinski?

  Yeah.

• 21:12Wes Bos?

  But you could do all that with a web, uh, a web, uh, UI of, uh,

• 21:15Speaker 02

  That's what I'm trying to understand here is that-

• 21:17Scott Tolinski?

  OpenCode Web has like a remote web UI. That, you got all that.

• 21:22Wes Bos?

  And I'm trying to understand it for myself as well, is that like, I find myself gravitating towards just using the terminal for Claude code, even though, like, the OpenCode Desktop app or the Claude Desktop app, these things are significantly better interfaces. Why do I keep going back to the terminal? Like, why, why are we trying to recreate, uh, GUIs in the terminal, which is like, obviously, a way worse UI, but we like to enjoy it more? What's wrong with us?

• 21:54Speaker 02

  All right. So, look, this is a very good comment, which is, many of these tools allow you to just connect to a remote machine, and then you can get some of the benefits that way, right?

• 22:02Scott Tolinski?

  Yeah.

• 22:03Speaker 02

  In terms of being always on. Why don't I do that? That's a good question. One, I've experimented with it, and I guess- This is probably like, they're better now. I want to put a big asterisk. They're better now. But I think when I went back in time, when I started down this four or five months ago, I just, I don't know. I didn't like the experience. The second thing is, man, I use all the coding agents still. I still run Claude. I still run Codex. And, and not being locked down, like, I think that once you, if you use open code that way, or use Cursor that way, you're really committed to using that tool. Like, you go to the effort of setting it up, and you're not really gonna let it go. Does that make sense?

• 22:39Wes Bos?

  Yeah.

• 22:40Scott Tolinski?

  No, I totally feel that, especially, like you said, you're changing tools all the time. And like Anthropic pulls the plug on using your Claude code and, and open code. And now what do you gotta do? Now you gotta either change the tools that you want to use if you want to continue to use your Claude Codex Max, or you're, you're gonna have to change the subscription, who you're paying, how much you're paying. Yeah, totally.

• 23:02Speaker 02

  I, look, I still use actually Cursor with the shell extension, so that I can navigate the files on the file system. So I still use that occasionally. Like, if I'm really deep into a problem, I will actually use some of those capabilities. So I don't want to say that they're not good or useful or whatever. But I do like the, I guess I like the, the portability, and the flexibility of just having it this way. A good example is, have you guys played with the Hermes agent?

• 23:28Scott Tolinski?

  Bro! Currently, 15 minutes before starting this call, I, I ran the Hermes setup. Like, 15 minutes before this. So, um, I have not, but I am, I have like maybe 10 or 12 tabs of stuff open to read after this call. So, I'm curious. I'm Hermes curious.

• 23:47Speaker 02

  Well, I like, I, I've only spent a couple hours with that, but I would say it's like, I didn't have to change anything from my setup, right? I just, I shelled into my box, I installed Hermes and I ran it, and I didn't have to go and figure out whatever remote magic stuff I gotta do.

• 24:02Scott Tolinski?

  Yeah.

• 24:02Speaker 02

  Right? I'm not saying, you know, I, by the way, one thing we didn't get into is, one of the reasons I make the code work on the box, and um, I've also experimented with running VMs on the Mac as well. Could talk about that, using a tool called Lima. I want to run everything in dangerous mode.

• 24:19Wes Bos?

  Yeah, yeah.

• 24:21Speaker 02

  And so having a box, it's just like only loaded with like open source projects. And, um, you know, cause I can, I can, you can even segment your boxes to different scoped projects, for example. You know, you can just go ham. You don't have to worry about anything. I think that's also quite nice. Like, yeah, the freedom.

• 24:39Wes Bos?

  So tell, tell us more about that because I, I think that's where a lot of people are at right now is where everybody's running Claude, dangerously skip permissions on the root of their MacBook that has access to like their entire lives, which would be like, like awful if, if there were to be a, like a security thing to go down. So like, what's your process? Do you have like an image that has a lot of the stuff installed? Or you seem to just have one box and you, and you SSH in?

• 25:06Speaker 02

  I think it's worth like, look, I like experimenting. So I've got a bunch of things. I have.

• 25:11Wes Bos?

  Yeah.

• 25:11Speaker 02

  A framework desktop in my basement on fiber that's running Omarchi, um, that I keep up to date and that I pretty much just use for coding. And then I think it's got like Steam games on there.

• 25:23Wes Bos?

  Yeah.

• 25:24Speaker 02

  Cause it's, it's connected to a TV. Like that's it. It doesn't, it, there's no, I'm not signed into anything personal. I guess you could drain my Steam games or something like maybe in the worst case.

• 25:34Wes Bos?

  Yeah.

• 25:36Speaker 02

  Get my Team Fortress skins or something.

• 25:39Wes Bos?

  But do you not want it to have access to, to a lot of your things? Like that's, that's why everyone went nuts over open clause. If people's like, I, I wanted to have access to my SMS and my, my Google calendar. And I guess that's more like personal agent stuff versus like development?

• 25:56Speaker 02

  Yeah. I, yeah, it is more personal agent stuff. I haven't gone too deep in it. I, we, look, we build an agent. Uh, I've built a full open claw style, oh, like open source agent that we run as well on a VPS.

• 26:11Wes Bos?

  Yeah.

• 26:12Speaker 02

  That's exposed over Slack and everybody at modem can use this. So I, I built some of that as well. I just, I accept that people get increasingly comfort with like YOLO mode or dangerous mode because 99.99% of the time, it's not going to do anything bad. Right? And you kind of get, you get lulled into this false sense of security. But I've already experienced agents kind of like reason to themselves about why they gotta go and do something. And seen, um, seen some bad effects of that. And I just, like my position and the position of the company, for example, is we just, everything is gated. We don't just let agents go YOLO. A good example is early, early in Modem's development, we were working with a design partner.

• 26:57Speaker 02

  And what they had asked the agent to do was to create an issue for something that they were looking at. They were using GitHub, they wanted to. And so Modem is a, it's a multiplayer agent. It exists on the web in Slack. It's not unlike having like an open claw for your team, but it just does like product and project work. Okay. Uh, this is important. It also connects to some of your stuff like GitHub. So we had a customer who, our design partner, early on, who wanted it to open up a ticket for themselves on GitHub. But because of the context, because of what they were talking about, it decided that what the user wanted was to go and open a public issue on an open source repository. So Modem just went, you know, as, as you've probably seen people talk about,

• 27:39Speaker 02

  just went and opened like an open source ticket on behalf of this user, which is not what they wanted. Now, is that going and destroying your computer or like reading your emails or whatever? No, I think it's just that

• 27:55Speaker 02

  an agent can, it's very possible for an LLM to misconstrue your intent. Right? Cause if you said to an agent, depending on what agent you use, like, you know, go ruin my day and delete a bunch of stuff. It can do that with an asterisk that Claude will, I think, has some guards. It'll be like, I don't think that you should do that, but you know. So if you can logic, if you can reasonably, if the agent can reason itself into a position, like it will go and do things that you don't want it to do. I just don't see how that's like unavoidable because to me it's almost like, it's like talking to a human. It's just possible, like what's in your brain and what you want and how you communicate that to the LLM on the other side, like something can be lost in translation and has nothing to do with the effectiveness of the LLM or whatever.

• 28:41Speaker 02

  Does this make it sense?

• 28:42Scott Tolinski?

  Frequently, I would say it almost, it often does, especially for me, because I make assumptions, right? Like, and like, why would you possibly have thought to do it that way? And then you go back and you read your prompt and you're like, oh, I, you know, I, there's so much innate things that I think that it, it knows when it's really like, it's doing what you told it to do. And if you didn't give it clear enough instructions, yeah, very easily get off track.

• 29:08Speaker 02

  So I don't know. I think I'm more sensitive than most and maybe like, we're also running a business. We hit like, I think that the bar for us has to be higher.

• 29:16Scott Tolinski?

  Yeah.

• 29:17Speaker 02

  I don't want to write one of these tweets about, about torching my email. That seems bad. It seems bad for business. So to me, I just prefer to put everything in a position where it's like, not even possible. Does that make sense?

• 29:31Scott Tolinski?

  Yeah, totally.

• 29:32Speaker 02

  I don't know. Cautionary tales, you know? So maybe that's, yeah. How about you guys? You, you YOLO mode on the, on the Mac?

• 29:40Scott Tolinski?

  I was gonna say, have you considered that having one of those blog posts would actually be, you know, all, all, all news is good news, all, all publicity is good publicity? You know, you could get your name out there. We fucked up our whole, or we deleted our whole database and now everybody knows your company name.

• 29:59Speaker 02

  I think that it depends on what you're doing. Like for us, we ingest like sort of product conversations that could be happening on Discord, public GitHub issues, it could be support tickets. I think that we want to demonstrate a high bar towards privacy and security, right? And I just don't think that it serves us well to do that. Now, you could still be right, Scott. You could still be totally right. Like even though I want to conduct myself that way, maybe the right move is to just like drop the database.

• 30:29Wes Bos?

  Do you think we'll get to a spot where the models will be able to figure out what is okay to run and what is not okay to run? Because like everyone's, everyone's just dangerously YOLO mode right now. And we hear every now and then we hear these, these stories and whatever. And like the, the only, the alternative is like, do something like you're doing, which is like, set up a box. But like, eventually you're going to give it access to something that it needs. And it like, you could, like, at some point, you need to give it access to a database, and that might be a prod database, and therefore it should be able to, to drop the entire thing, right? So you, you sort of just slowly add in more access to this thing, which makes it

• 31:15Wes Bos?

  a little bit more unsafe, doesn't access to your, your whole computer, but it does still have to have access to your GitHub, and maybe your email, and maybe your, your actual database. So that's a problem that could happen there. But the other option is just like, you have to sit there and approve, approve, approve every single like ls -l. And there's, there's gotta be something in between where the agent would be like, no, like, oh, yes, I can run a listing of files, but I shouldn't be able to nuke 18 gigs from, from a database. And I'm curious if you think we'll ever get to that spot.

• 31:47Speaker 02

  Man, that's a good question. I feel like it's, it, let's say the, let's say the coding harnesses or the LLMs have more of these like protections in place. The thing is, how does it know when you want to do something destructive? That could be valid too. Right?

• 32:01Wes Bos?

  Yeah.

• 32:02Speaker 02

  And I, I do want to mention this. I'm, I'm using Linux on the desktop and I'm using this stuff. I use the agent to, like, I could not use Linux without coding agents. I'm sorry. I need a coding agent to be like, why is the resolution half? I have no idea.

• 32:21Wes Bos?

  Oh, same. Yeah, same. Okay. Why the heck can't I, uh, use SMB? Okay. You don't have it installed. Okay. Let me, yeah.

• 32:30Speaker 02

  I do, if you heard, I use Steam. The little sidetrack here, but I think this is fun because I use Steam. I use this framework desktop on Linux as like a gaming machine hooked up to a TV.

• 32:41Scott Tolinski?

  Okay, yeah.

• 32:42Speaker 02

  It works because of all the work that Steam has done with this compatibility layer proton for like the Steam Deck. I had one for six months, didn't use it, but it works on Linux desktop. I had a game that by all measures is very popular and should have run, but I couldn't figure it out at all. So, you know, coding agent, why isn't this game running? And it just started ripping, looking at all the crash logs, you know, and after five minutes, it's like, oh, you got to run with this command and that should pave over this compatibility thing. Man, I Googled this for like an hour, you know? I just could not find anybody with the answer. I was shocked. I just want to make a comment that like coding agents make you doing stuff on Linux way more approachable.

• 33:24Scott Tolinski?

  Totally.

• 33:25Speaker 02

  But at the same time, it's going and messing in, you know, it's like, oh, let me fix this. I'm just going to go rip and like write these system files and stuff.

• 33:32Scott Tolinski?

  Yeah.

• 33:33Speaker 02

  Okay.

• 33:35Speaker 02

  And I wanted to do that because that's part of what makes like, that's part of what makes it really powerful. And so I'm connecting this to say, sometimes you want it to be powerful. Sometimes you want it to arguably be destructive. And how do you know when you want it to do one and when, when the other one is right? I don't know. I don't know. Does that make sense?

• 33:53Scott Tolinski?

  Yeah, totally.

• 33:56Wes Bos?

  Tell us some more about the tools that you've written here to make it. You've got hunk and term draw, which help you take the, I guess, the ASCII experience and make it a little bit more gooey.

• 34:08Speaker 02

  Yeah. So I mentioned like fresh as like a, an editor that I think just makes it a little nicer to use on the terminal. I realized maybe like two months ago that I was suffering from AI psychosis.

• 34:22Scott Tolinski?

  Oh, yeah.

• 34:24Speaker 02

  And I felt like a lot of people were two months ago because maybe like four, six, Opus four six has come out and we were all having a lot of fun, generating lots of stuff. And I realized that, oh no, I have not been paying as much attention to the code as I have been. And specifically, this is not for like modem, but I meant for like all my little open source thingies, you know, I was just kind of like, I was vibing more than I'd ever. And I realized part of it was. I just didn't really have a nice way to like, look at the diffs frankly, because of this like way that I had adopted like, you know, I was using the, I was using the stock diff program. And then I started using, looking at different um diff outputs for Git that connect to like, connect to Git like,

• 35:08Speaker 02

  I don't know if you've played with some of these, but Delta is one of them. DiffTastic is one that's popular. It does like a more like syntax aware diff, which is kind of nice.

• 35:20Speaker 02

  These are all like things that you can plug into um Git diffs pager, you know, diff pager mode today. And you can do it on Mac, you can do it on Linux. And if you do use Git on the terminal, I use Git on the, I like, for some reason, I never let go of Git on the terminal. So, so that's where I started, but I was just never satisfied for a variety of reasons. One is, I just didn't like their syntax highlighting choices. I, also a big one was, they're not responsive. You know, we're so used to responsive layouts on the web.

• 35:53Wes Bos?

  Yeah.

• 35:54Speaker 02

  But terminal programs, not so much. And, you know, sometimes depending on how you're working, I've got like a really, I've got a split pane, I've got a really tiny surface area. I don't want split diffs. I want them to be stacked. But sometimes I've got like a really wide area and I want them to be split. And I couldn't actually find like a tool that made that really nice. So,

• 36:16Wes Bos?

  Yeah.

• 36:16Speaker 02

  it just wasn't nice. So I wasn't, I wasn't reading the code because it wasn't that nice. And then second of all, I was really interested in some of this new technology that had come out. Open2e, mentioned earlier. And then Pierre Dis, diff.com.

• 36:32Wes Bos?

  We had him on the podcast last week. It hasn't, at the time of recording, we haven't, it hasn't even gone live yet.

• 36:37Speaker 02

  Was that Jacob? Who you got on there? It's a other fellow?

• 36:39Wes Bos?

  Yeah, we had Alex and Amadeus on.

• 36:42Speaker 02

  Okay, great timing. So like, that is a great library and you're seeing it pop up everywhere, like anywhere. It's a great diff rendering library. I guess it's gonna be on the show, but I understand that they are basically building a GitHub clone. I actually use that product. And to use modem in the early days, I could talk about that if you're curious, but, so I was already very familiar with the whole, like their whole approach to diffs. And they put it out as a library. And it's meant for like, it's web tech, right? Primarily, but I was curious if you could plug it into Open2e, right? Open2e supports React. Diffs.com has a React output mode and I was like, man, is it even possible that I could plug these two things together?

• 37:21Wes Bos?

  We're wondering, we're like, how the hell is it doing this?

• 37:25Speaker 02

  So that's the, and then would it even make sense? Would it even look good? And the answer was yes.

• 37:31Speaker 02

  I had to do a lot of optimization, like I've used the agents in like, you know, goal mode or auto research mode to like, get the frame rate up. And I had people, before I released Hunk, people were like, it's a terminal app. Why do you care that like about the frame rate? And the answer is yes, it does matter. So, so that's where Hunk came from. So you can check it out at, um, you know, on the show notes, but

• 37:56Speaker 02

  github.com slash modem dash dev slash hunk.

• 37:59Wes Bos?

  Oh, you need a cool domain name for this. Take a page from the Pierre guys.

• 38:03Speaker 02

  We have, we have modem, or sorry, we, yeah, we have hunk.dev. I just got it. I just haven't put anything up there.

• 38:09Wes Bos?

  Well, you have got hunk what?

• 38:11Speaker 02

  Oh, .dev, hunk.dev.

• 38:12Scott Tolinski?

  That's a redirect to my website, honestly.

• 38:17Speaker 02

  Oh yeah, it's a fun name too. I think that's a fun name.

• 38:19Scott Tolinski?

  It's a fun name, for sure.

• 38:20Speaker 02

  So anyways, it kind of works. And then after that, like this came out like two months ago, like I was using it quite a lot. And I think that this is always like a nice thing is like when you're using software and you're using it a lot, right? I know you guys work on stuff to maintain the pod, right? You know, just keep, it just gets better. So, you know, like the diffs look nice and I put in some themes, like it just looks nice, I think, relative to most of the solutions on the terminal. And it has mouse support, has a sidebar with a file picker, and that's gone through like a bunch of iterations. It's got some other interesting features, probably the most notable one is it has a CLI totally ripped off from T-MX, which is that your agent can write and read to it and it can navigate the session for you.

• 39:02Speaker 02

  So it takes like rev ranges, so you can say like hunk diff main, like you can diff main, you can diff, you know, main at five, you can do like, you can do a diff on a branch, or you can actually just ask the agent to drive it, just like you could T-MX. And it can leave annotations. So it's a more, not only is it, I think, like a, kind of like a really nice diff viewer, it's also got this kind of agent integration via the CLI, which I think is kind of neat. So check it out, hunk.dev, we'll have that live.

• 39:33Scott Tolinski?

  Oh yeah.

• 39:35Wes Bos?

  I can't believe you did hunk.dev when hunk.rodeo was available.

• 39:40Speaker 02

  I

• 39:40Wes Bos?

  Hunk rodeo.

• 39:42Scott Tolinski?

  Hunk.

• 39:43Speaker 02

  Let's get that too.

• 39:44Scott Tolinski?

  Yeah.

• 39:46Speaker 02

  It's under 20 bucks, we'll get it. What does a dot rodeo domain cost?

• 39:51Scott Tolinski?

  116 bucks for the first year. Ah, no, thanks. No, thanks.

• 39:57Speaker 02

  Yeah, also, you know, questionable content when you Google, Google this thing.

• 40:05Speaker 02

  Look, I don't know. I was making this and I was sharing it, but not like going too hard. I was using it a lot, but it's actually it. Hunk seemed to get a lot of attention lately. And I guess at this point, like I've even forgotten why it's, why it's good, but people seem to think that it's good. I don't know. I think part of it is the, look, I, I really actually like GitHub. Pull request reviews. So it's taking like a lot of that UI. If you're familiar with GitHub, you know, code review, you know, you want to leave a comment back to your agent. You want to navigate between different files. It's got a different, it's got a similar kind of like file navigator. So that's what's going on there. And for me personally, it has helped me review more of the code that's happening on this remote box over SSH.

• 40:46Wes Bos?

  You got me Googling right now. Can I install Omar G on my, I've got like a 2009 Mac Pro right now.

• 40:53Scott Tolinski?

  If it's Intel, you can. It

• 40:55Wes Bos?

  It's an Intel.

• 40:56Scott Tolinski?

  Does not do well with the M processors. There's like a, a forecast, because I looked into this because I was running it on my old system 76 laptop. And I'm like, I would like this so much better on a real machine, on a real machine. And, uh, I don't have one that's handy.

• 41:11Wes Bos?

  I've been running, like I have an old MacBook, Intel MacBook, and I had my OpenClaw running on it. And I, the other day, I haven't, haven't messaged my poor little OpenClaw in probably three months. And I just messaged it the other day and it's still running. Like it's laying on the ground three months later. Like that's, that's amazing. But I, I do like that workflow. So you got me, you got the gears turning here. Anyway, that's just a bit of a side that, let's hear about your, uh, your other package that you've, you're working on.

• 41:39Speaker 02

  So that's one. And this is in pursuit of a, you know, my pure portability. IDE pseudo IDE terminal setup. The other one is term draw. I started experimenting experimenting with writing ASCII to agents quite a bit. Maybe because I started as a very young person on bulletin boards before I had the internet. Like I had a dial up modem. You know, I'm not that old, but like, just imagine like a 13 year old, you know, connected to computers that he should not be in the nineties. Like the internet existed, but you could connect to like a local bulletin board. And so to me, I really have this like headspace of ASCII and ANSI character drawing.

• 42:19Speaker 02

  So ignoring the terminal, like if I was using cursor or conductor or these other tools that I've tried. Have you ever had this experience with an agent where you're like, ugh. All right, you built this web thing, but like, look, can you take that button? You can put it to the left. You ever done that? And then, and then it's like, oh, you mean over here? And it like puts it in a, in another location you're not happy with. And then they're like, no, no, like, can you drop it a little bit? And then maybe you'll share a picture, like maybe, maybe you'll take a screenshot and you'll like draw an arrow about like what you want. Have you done that?

• 42:52Wes Bos?

  I, I, I thought this was kind of interesting because you said in your talk, you said like, like, why give it an image when it all it does is it converts it to text? And when you can, you can just give it a thing. And I thought like, I actually like, I find screenshots work almost better in some cases than like hooking it up to like a Chrome Dev Tools MCP.

• 43:14Speaker 02

  Oh, they totally do.

• 43:15Wes Bos?

  Which is amazing, but like, like the, I guess unreal that visualness is better than the actual raw data of how something works. So is that true for diagrams as well, even if they're done in ASCII?

• 43:29Speaker 02

  My experience has been, so I guess I started experimenting with this where I would just draw, type it out. I would just like literally type out ASCII little diagrams and be like, look, I want the button here. And I found that to be pretty successful. And this is going back, you know, to December. So I was already down this path. And then at some point, I'm like, why am I typing this out? I could just draw it. So Term Draw is like a terminal illustrator. Okay, you can draw shapes, you can draw boxes, you can put text. You can, you can write text. It's got now elbow connectors. I think I just added. You can have, when you're drawing boxes, you can use different borders. You can put like a dashed border to indicate something's temporary.

• 44:12Speaker 02

  And I say it's an illustrator because these are actually like objects that exist on the, on the pane or like on the drawing surface. So once you draw a box, you can move it around. It's got baked in grouping. So if you wanna, if you, if you draw like a window and you wanna do like, hey, I want a two column layout. You can resize things and they stay, they stay in place. So it has some context about, oh, I'm a box inside of another box. So if you wanna drag things around. So it's got some kind of like nice things. You can, you can grab the corners and resize stuff. And even the text is like movable. So I've done all this basically so I could just like diagram out things that I want. Without having to explain it, like I can open up Term Draw. I can draw what I want and be like, go and do this, you know?

• 44:56Speaker 02

  And in 20 seconds versus having to type out, you know, well, I want a website with two columns and I want on the left side, I want this, right? Instead, you can just really draw it out. And my experience has been that the agent totally reads this quite well. I've done a bunch of experiments. Opus 4.7 really good at, really good at ASCII diagrams. If you wanna play at this, I feel like it really leveled up. Something else.

• 45:19Scott Tolinski?

  I do, I've noticed that too. Yeah. I like it when I'm doing like a grill session and it's giving me ASCII diagrams. This or that, this or that. Yeah.

• 45:27Speaker 02

  I, I experiment with having, I've been experimenting also with having the agent like draw ASCII diagrams in hunk annotated comments, which I think is fun. So, you know, leave a comment, but it's like, I'm gonna write like a sort of layman diagram to help you understand what you're looking at. That I wouldn't necessarily wanna commit to the code, but I'll put it here as an annotation for you as you're reviewing it.

• 45:50Speaker 02

  So anyways, that's Term Draw. It helps if you're, I'll say it's also helps if you're, if you're doing terminal apps. If you're building terminal apps, it's pretty useful to draw terminal, terminal constructs.

• 46:01Wes Bos?

  That's wild. It's like a whole gooey, but in the, the format it saves in is like a .td.json file. What is in that file? Is it literally just the ASCII as text or is it like more structured?

• 46:15Speaker 02

  Oh, that's like, so normally it just outputs to standard out, but somebody added, added that is like, well, I want to save it and come back.

• 46:21Wes Bos?

  Oh, I see.

• 46:22Speaker 02

  This is another topic, but I'm having a struggle understanding whether like feature requests are real or not.

• 46:31Speaker 02

  Okay. Which is like, like, so these, these projects have gotten like some minor notoriety. And now I guess I'm stuck in the world of like, people are opening up pull requests and issues and understanding.

• 46:41Wes Bos?

  Yeah.

• 46:41Speaker 02

  If what people want is real or not is becoming hard. That's just a side topic.

• 46:46Wes Bos?

  And it's, is it because like, you don't know if these are real people? Or do you think it's just somebody that says like, this should be, this is possible because I can type my, any thought I have into a box. And, and code it up.

• 46:59Speaker 02

  Yeah. Man, so many, like I, somebody on Hunk, for example, I'm like, man, how is this person opening up so many pull requests? And why are they so on point? And then I realized that it's like, they're generating a PR for every single issue automatically that somebody opens.

• 47:14Wes Bos?

  Ah.

• 47:15Speaker 02

  And then I'm like, you know, I thought you were just a user who was really into this. And then I go and look at their profile and they've got like, you know, 10,000 commits. All from the last few months and they've contributed to like 160 different repositories. And I'm like, oh.

• 47:29Wes Bos?

  But like, who's, who's paying for that?

• 47:31Speaker 02

  I know. Yeah. I don't know.

• 47:35Wes Bos?

  Is it, is it people that have these, like often I find it's, it's people that have like a startup in the space and are trying to prove that their thing is the best. And then they're just spamming everyone. Is that what it is? Do you think?

• 47:47Speaker 02

  In this case, like, you know, I don't want to name names. I think someone could easily find this, but it didn't seem that way. It actually just seemed like they were taking a lot of pleasure and contributing to open source as far as I could tell.

• 47:58Wes Bos?

  Maybe they work for Amazon and they're trying to get their token count up and they need to burn them on something.

• 48:04Speaker 02

  Or maybe they are building something behind the scenes and maybe they're not ready to reveal it yet. But you know, here's one, what is my merge accept rate? Right? You, you can actually get some, you can get some data on this.

• 48:15Wes Bos?

  Yeah. Interesting.

• 48:18Speaker 02

  So anyways, yeah, the format is just if you want to save it and come back. I don't know how many, how often people are doing that, but the person who requested it, when I didn't merge, they came back and said, hey, I really want it. I've been waiting for this and that's a good indicator for me that maybe they're real.

• 48:31Wes Bos?

  Can I ask what your, your flow is for things that must be visual? Like, obviously, we can make diffs and diagrams and everything in the terminal, but eventually you need to view a video, view a photo. And I know that there's like some terminals that can display images, but like, like what happens if you just want to like look at a PNG image? And like, what was your process for that?

• 48:58Speaker 02

  Well, if you're using Ghosty, which is very popular, it uses-

• 49:03Wes Bos?

  Kitty?

• 49:04Speaker 02

  Kitty, yeah, thanks. I'm like, what can I say that won't have Linux people yell at me?

• 49:11Speaker 02

  I think this is fun too, which is like, the protocols have changed. Kitty is a terminal protocol. And I think, I think it works over SSH and it works with Ghosty and you can actually just render PNGs and graphics. Actually, my talk at A Engineer Miami, that whole presentation was done on the terminal, even though it has full images. It's done over the terminal over SSH, so not just a local terminal. I even experimented technically, you can, you can play video over the terminal. However, it's super inefficient and I wouldn't recommend it. It's really just flashing images quickly.

• 49:50Speaker 02

  So like, yeah, so that's one. So just for talking, just talking images and that's a cool one. Otherwise, I think it's like the standard thing where you expose, you use TailScale, you expose a port, I connect to a server. You know, you can still do that, right? Gets a little more painful. I try not to do that if I can. I guess another one is just building, you know, using build servers and generating previews, like using Vercel there quite a bit, but that is like, costs money, some compute, right?

• 50:15Wes Bos?

  And it's like, it's like slow as well. Like, I was using the like cursor, cursor cloud agents and they will spin it up and they have like a browser built in to their like cloud agents, which I really like because you can just fire something off, you can go on your phone. And then like, if it's not possible that way, some people are like, yeah, just send in a pull request, wait for it to build. But like, that's kind of slow as well. Like, I feel like there's, there's no like killer solution there just yet.

• 50:45Speaker 02

  And like if I was building an Electron app or something, this probably wouldn't be a very good environment for that, right?

• 50:50Wes Bos?

  Yeah.

• 50:51Speaker 02

  Right? So I think it depends on what you're building.

• 50:54Wes Bos?

  Maybe that's a good transition. We got a couple of minutes left here is that you have a podcast about agentic coding and then you've you've developed some skills to edit the thing? Like, what's your process for that? And where does that happen?

• 51:09Speaker 02

  I get we're plugging or the plugging can come at the end or it can come now. So

• 51:12Wes Bos?

  You plug whatever you want.

• 51:13Speaker 02

  Plug, yeah.

• 51:15Wes Bos?

  I don't rules.

• 51:16Speaker 02

  It's called State of Agentic Coding with me and Armironaker. Took us probably three episodes before we committed to that name. And it's just once a month. And, you know, we're just talking. I think the episodes are like 90 minutes now. Look, I learned so much working with you all on syntax. Actually, we so loved working with Randy, super producer Randy. And I hear that he's gone pretty deep writing code and stuff, too.

• 51:41Wes Bos?

  Oh, yeah. Yeah, we're he's, he's, he's writing his own replacement as he's, he's, he's a cracked Claude engineer now.

• 51:50Scott Tolinski?

  Yeah, now that DaVinci has MCP and all kinds of Ograph support. Yeah.

• 51:54Wes Bos?

  Yeah, DaVinci MCP. He's like, he built like a whole, like a little chat window for it. And he like

• 51:59Speaker 02

  Oh, my God.

• 52:00Wes Bos?

  And we were like, fighting over like, what the best way to do graphics was. And like, we think like Randy might have cracked the best programmatic graphics approach.

• 52:12Speaker 02

  I think he could run a course right now and I would attend it.

• 52:15Wes Bos?

  Yeah.

• 52:16Speaker 02

  So we actually work with a look, one of the things I learned is how great it is to work with a with a professional editor. So we hired an editor, editor Sam, who was actually somebody I met. He was a candidate for Randy's job. Okay. And I just kind of stayed in touch. And, you know, I was like, Hey, you want to work on this project? So work with Sam. But I think for me, like, there's still so much work. You can't just like, have an editor, right? It's one thing with Randy knows, he's worked with you all for so long. He knows how you all, you know, what you're going for. But our case is a little different.

• 52:54Speaker 02

  I need to watch the video. I need to come like, what do I think is the best, you know, tasteful bits? How do we cut a bunch? Like, obviously, Sam can cut a bunch, but we're also trying to do like a really fast turnaround time on this because AI moves so fast. So if we could just accelerate that, like, we try to do like four days. And then, Sam gets me a cut. I gotta go and review it again. I'm very nervous about saying something really stupid, guys. I'm really nervous. So I've built a bunch of tools to help me with that. Actually, it's, it's open. I just open sourced it in case people want to play with it. It's called Pod Guy. Come link to it. What's interesting about it is it's, it's a bunch of extensions and skills. Okay, I think people have seen that. One of those,

• 53:36Speaker 02

  for example, is it'll download like a whisper model and like generate a transcript. But the skill file knows how to do it. Another one is like I've, you know, find the boring parts to cut in this two hour episode. We might have a two hour episode that cuts down to 90 minutes, right? Just make some suggestions. One that's actually very helpful is by the end of the edit, Sam has inserted all these interstitials all over the place. And I just find it easier to be like, okay, Pod Guy, just find me where all the interstitials are, so that I can time code those for the YouTube description or whatever. And then it just goes and like actually generates a bunch of frames and scans through them to figure out what they are. And then like generates, you know, goes back to the transcript and generates like all these like descriptions for me. So that's just like, it does a bunch

• 54:21Speaker 02

  more. I think what's a little bit more interesting about it is, it's the first time I've used Py. Py is loaded in the repository. And when you fire up the project, it's actually like a slim down Py, where it actually kicks out all of the like, it shouldn't, it doesn't bring in your skills or your extensions from your local, your local development or whatever. It's, it almost only exists in this world to serve you and the podcast editing role.

• 54:51Wes Bos?

  It's like a dev dependency of the project.

• 54:55Speaker 02

  Yes. And it's almost like an alternative CLI, where instead of you trying to remember like all the commands, which I'm never gonna remember, it's very much like, here's the eight things I can do. What do you want me to do? It's not there to write code. It's just there to actually like, almost like it's an agent dedicated to doing this.

• 55:12Wes Bos?

  I've been finding that as well. It's like I've replaced so much of my like script writing and like these like rigid NPM run whatever. I've replaced so much of that with simply just like a bunch of skills and an agent and saying like, this is kind of what I want. And it's just so much more flexible. And it's, it's, it's not like, it's not writing code or anything. It's just like an easier way to have a CLI.

• 55:36Speaker 02

  Yeah. I think Pi is a really interesting one for this because it's, I don't know. Have you guys had Mario on here?

• 55:44Wes Bos?

  Yeah.

• 55:45Speaker 02

  Armin?

• 55:45Wes Bos?

  Yes.

• 55:45Speaker 02

  Yeah.

• 55:46Wes Bos?

  Yep.

• 55:46Speaker 02

  Both of them? Yeah.

• 55:47Wes Bos?

  Yeah.

• 55:48Speaker 02

  I did see it.

• 55:48Wes Bos?

  Package deal. Yep.

• 55:50Speaker 02

  Because Pi is so stripped down by default, right? It actually works really well for this purpose. If you want to like stand it up as your interface to whatever versus say, you know, Claude, you could do this with Claude, but Claude has a bunch of other things that it wants to do. And it's nice to have something that's just sort of like bespoke tailored, you know, for, for this very specific task. And I guess to be ultra clear here, it's not like I run the coding agent. It's like I literally, yeah, I run like NPM run dev and that brings up the coding agent. Yeah.

• 56:22Wes Bos?

  That's great. All right. Let's, let's talk about modem. Um, so it's obviously your company. Tell us, we, we touched on what it was, but like, tell, tell us what it does. And then like, like, why should we care about something like this versus just having Claude go do it?

• 56:36Speaker 02

  Okay. So modem is two parts. One is it's like a product intelligence platform where it integrates into all these places where you and your customers could be having conversations about your product, like support tickets, public community, discord, Slack connect channels. Okay?

• 56:52Wes Bos?

  Yeah.

• 56:52Speaker 02

  And those messages go into basically like a, a pipeline that's not unlike sentries. We're very sentry pilled. And, um, basically just kind of creates like a, you know, we call them topics, but they're kind of similar to sentry issues. Like instead of you, instead of getting a list of like all your errors that are grouped together, we give you a list of all your, all Your kind of product topics grouped together, right? Here's all the places that people are talking about dark mode. Or you know what? You just launched version 15 of your software. And starting, you know, an hour afterwards, you had this big furor of people complaining about this aspect of the product. Like, oh, you broke mouse support in version 15, right?

• 57:36Speaker 02

  And so all of this is streaming into a platform where it's categorizing it, organizing it, deduplicating it so that you and your product team can just be like, man, what do people think about our software right now? And you just have everything there. And as you, you know, you launch new things or you introduce bugs. If people are talking about those bugs, it'll wind up into the platform. Does that kind of make sense?

• 58:00Scott Tolinski?

  Yeah. Optum RX. Sign up for this. Optum RX. I'm begging you. Wes and I had an epic rant on the Optum.

• 58:08Wes Bos?

  Scott's like.

• 58:09Scott Tolinski?

  It's my biggest enemy right now on the web. Yes.

• 58:13Speaker 02

  Optum RX. Is this a drug plan?

• 58:17Scott Tolinski?

  It's like subscription based. Your meds get sent to your door instead of having to go to a pharmacy. But they like rewrote their platform and it's total dog.

• 58:27Wes Bos?

  So often you're visiting a website and you're just infuriated about it. Or there's like a part of a product that you use every single day that you just feel like the people that are working on the product have no idea that you're so frustrated with it. And I often want to be like, just, I'm gonna get a job there, fix this and then quit. Like, I just like, I feel like I know better about the problem with this piece of software than anybody at this entire company does. And I wish that I could just get that across somehow. But in, in the olden days, you had to get someone to care about, about your actual problem. But what if you could just simply take everybody's frustrations and complaints and all of these signals that something is wrong with your product?

• 59:10Wes Bos?

  And like, use modem, right?

• 59:13Speaker 02

  That is exactly it. You sold it way better than me. Thank God.

• 59:19Speaker 02

  Which is, you know, like even at Century, like we had this, obviously we have great observability into the performance or the errors, right? But what do people think about it? I don't, you know, usually you need the CEO to, you know, the CEO basically drives by and sends you a message because he's, he's scanning all the channels manually. That's, that's one thing that David does. I wanted to know, I wanted to know what that is, like, or sorry, if I were at Optum RX, I'd want to know that, right? But often it gets bottlenecked behind people, tools, services, et cetera, the engineers, the software developers, the people who probably care, but there's people over there who care, but they can't even see it. So we're trying to like connect that feedback directly to the like software teams. So that's like part one.

• 1:00:01Speaker 02

  The second part is it's connected with an agent that is not unlike, you can call it, you know, Claude or, you know, linear has an agent where it's like really, it's built on that data and it's a multiplayer agent that you can work with over the web or in your Slack channel, in the future Discord, sorry, in your, in your Slack workspace. That is really just like someone that you can, one, you could talk to it to just extract these answers really quickly because it's designed to work with this data really effectively. So, hey, what does everybody think about our new RX platform? Give you that answer really quickly. But it's not designed to just be like a question box thing. It's like, it can take action, it can, it has automations,

• 1:00:45Speaker 02

  it could go and create your backlog automatically on your ticket tracker, it could actually like surface some of these problems directly to your team on Slack. So the idea here is it's, we're trying to get to like a, a vertical product agent, PM, project manager, product manager, that's honestly like working with your team and trying to surface this stuff directly to you, you know, because like, because we don't want another tool that things get lost in. So.

• 1:01:10Scott Tolinski?

  Heck yeah. Yeah, I love that. Now you got to scan YouTube and podcasts for sentiment about products.

• 1:01:17Speaker 02

  This is a thing. We get to dog food it a lot. Like, a lot of people are using Hunk now and opening and like leaving messages on social or opening tickets. And I'm like, oh, man, I actually, I really need, you know. On top of the fact that we dog for this for modem, I also now need to dog for this for our open source projects and like it's, it's a lot of work to keep on top of this. So.

• 1:01:38Scott Tolinski?

  Yeah. Man, do you, do you ever see something like this being applied to stuff that isn't software? Like, I'm just thinking about like, like a physical product or even just like, man, like Lululemon has been getting like tons of hate lately of their, their designs are not good. Um, their, their fabric is pilling, just stuff like that. And I'm curious, like, does Lululemon have some mechanism to figure out what are people saying about our latest leggings?

• 1:02:05Speaker 02

  I think on the conversations I've had is that many companies have something like this. Like everyone understands that it's a problem they gotta solve.

• 1:02:12Scott Tolinski?

  Yeah.

• 1:02:13Speaker 02

  And they, and they have this kind of visibility problem. So I talk to companies all the time, which is like, oh, we built a version of this. There's one person who maintains it and it's not that good. Um, so I don't know what the answer is. Like they might have something, like it might matter to them.

• 1:02:28Scott Tolinski?

  Yeah.

• 1:02:29Speaker 02

  But whether it's good or, or, you know, not good or doesn't exist. Like I think our goal is like, can we just make the best version of that? And then, you know, based on working with customers and design partners, can we just make the best, you know, give everyone like a great version of that so that they can respond quickly.

• 1:02:45Scott Tolinski?

  Sick. Well, I love that. And I can't wait to see this in action more. Um, and everybody who wants to check it out, it's at modem.dev. We'll have the link in the show notes for you to check that out. Uh, if, I will say even if this is not a product that you want to use, go to their website because it's a cute looking website. I love your website. I love your colors. I love your animations. I love the whole aesthetic. Uh, it looks great.

• 1:03:09Speaker 02

  We didn't vibe generate it.

• 1:03:10Scott Tolinski?

  I believe that. I believe that.

• 1:03:13Speaker 02

  I can tell. Yeah.

• 1:03:15Scott Tolinski?

  So that was awesome. Thank you so much, Ben. Uh, we've already done quite a bit of plugging. So do you have a sick pick? I know you're familiar with sick picks. Uh, did you bring one today for us?

• 1:03:26Speaker 02

  There's a lot of chatter about taste and, you know, Sunil Pai from CloudFlare and PartyKit has talked about like, look, if you want to get taste, just go out, go to museums, go watch movies, just watch a crap ton of movies, listen to music. And I do agree and I believe that. So I'm going to pitch a movie. Okay.

• 1:03:46Scott Tolinski?

  Okay.

• 1:03:47Speaker 02

  And that movie is. Nirvana, the band, the show, the movie.

• 1:03:52Scott Tolinski?

  Sick.

• 1:03:53Speaker 02

  Okay, I guess it's an indie film, but it had like a $2 million budget, so not that indie. It's a Canadian movie. These guys used to have a web series turned into a TV show on Viceland. And it's basically about two guys who have a fake band that's called Nirvana. And whether it's a real band or not, it doesn't matter, but every show, I guess, is like, they are just trying to get a show. They're just trying to get a show at the Rivoli, which is like a concert venue. And it's just like a harebrained scheme. I have never watched this show before. Okay. I have no affinity. I don't like, I'm not connected to this at all. But the movie is really good. It blends like what's real and what's not.

• 1:04:38Speaker 02

  If you like, like Nathan Fielder content, you'll probably enjoy this. And it's also a time loop movie.

• 1:04:46Scott Tolinski?

  Okay.

• 1:04:47Speaker 02

  It's, you know, I'm really into time loop movies. I won't give too much away.

• 1:04:52Scott Tolinski?

  Did you see Palm Springs? That's a good time loop movie. Great movie.

• 1:04:56Speaker 02

  Yeah, I think time loop movies are good. I actually, I'm now I'm back on time loop. So I actually also just bought a copy of this movie here, two sick pics. Called Time Crimes. I got it. I got, I saw it on 4K at the movie, at the local bespoke movie store. And this is a Spanish time loop movie from the late 2000s. Also really good. Go check it out. Time Loop Movies.

• 1:05:21Scott Tolinski?

  Sick. Well, thanks so much, Ben. I, the moment I saw your talk, I was like, I cannot wait to dive in. I already have TMOx ripping and I'm gonna figure it out. I'm gonna ask the agent.

• 1:05:34Speaker 02

  Yeah.

• 1:05:34Scott Tolinski?

  Awesome. That's, I'm gonna give it another shot. Appreciate your time, Ben, and we'll catch you on the next one.

• 1:05:39Speaker 02

  Always a pleasure.

• 1:05:40Scott Tolinski?

  Peace.