Has the cost of software development officially dropped below the minimum wage? Andrew and Ben examine this economic shift alongside the rapid open-source growth and security implications of the OpenClaw project. They also explore Steve Yegge's concept of a federated wasteland for orchestrators and how the new Perplexity Computer is stepping up to act as a persistent, always-on digital coworker.
Show Notes
- OpenClaw rocks to GitHub’s most-starred status, but is it safe?
- Welcome to the Wasteland: A Thousand Gas Towns
- Introducing Perplexity Computer
- Software development now costs less than than the wage of a minimum wage worker
- Scott Werner’s Works on My machine
- Traffic Jam Explorer
Transcript
(Disclaimer: may contain unintentionally confusing, inaccurate and/or amusing transcription errors)
[00:00:05] Ben Lloyd Pearson: AI agents everywhere. I'm, I'm curious, Andrew, you got your hands on some of my agents in the last week. How many hours do you think they saved you?
[00:00:12] Andrew Zigler: Oh, well your agent saved me actually a lot of hours this last week.
[00:00:16] Ben Lloyd Pearson: Yeah.
[00:00:17] Andrew Zigler: Useful for the tasks that we had at hand. But I I, maybe I'll throw that same question back at you. Uh, you know, how, how, how many hours have my agents saved you in the last week?
[00:00:26] Ben Lloyd Pearson: Uh, well in the last week, nothing, 'cause I've been using my agents this whole time. It, it is really fun how we're just like ping ponging information back and forth between our agents at this point. Like, They just grab whatever they can go over to our little laboratory we have for them and then like do what we want and then eventually.
[00:00:43] Ben Lloyd Pearson: Like the signals go back to the other agents. You know? It's pretty fun.
[00:00:47] Andrew Zigler: It is pretty funny how quickly I was able to change anything that you handed off to me as well.
[00:00:52] Ben Lloyd Pearson: Yeah.
[00:00:53] Andrew Zigler: to the point where I had to like bring in a whole dedicated agent just to figure out how your project and my project go back together. And I [00:01:00] gotta say, this is still one of the biggest unsolved problems and I think collaborative agentic engineering, I experienced
[00:01:05] Andrew Zigler: this last year when I was on Code TV's episode for Goose, and we did a, it was a two person challenge, vibe, coding with subagents. So you have two people using teams of subagents. And then at the end I had to combine my front end with someone's backend. And
[00:01:21] Ben Lloyd Pearson: That's, yeah, I love that.
[00:01:22] Andrew Zigler: you can watch, you can watch the video to see how that turned out.
[00:01:25] Andrew Zigler: It's a, a pretty hilarious saga.
[00:01:28] Ben Lloyd Pearson: Yeah, we need to go from like one to two. It's like one person with agents to two people with agents working together. Like how do we actually do that? Which I think we're gonna cover today. So let's just get into the Friday deploy. Uh, I'm your host, Ben Lloyd Pearson.
[00:01:42] Andrew Zigler: And I am your host, Andrew Zigler.
[00:01:44] Ben Lloyd Pearson: Yeah. And here's what we're covering today.
[00:01:45] Ben Lloyd Pearson: We have OpenClaw rocketing into a risky orbit. Steve Yegge back unveiling the agent wasteland, which is what I wanna talk about, uh, related to what we were just bantering over. We have perplexity launching personal agents and then Dev work falling [00:02:00] below minimum wage. Andrew, let's just start right at the top and talk about OpenClaw.
[00:02:04] Ben Lloyd Pearson: 'cause I feel like not a week goes by at this point where we, we, something doesn't hit the news about it. So what do we have here?
[00:02:10] Andrew Zigler: Yeah, so OpenClaw rocketed to the top of most star status, um, on, you know, star charts, which is the famous way of seeing how quickly and virally, uh, projects get adopted. It, rocketed up to 250,000, plus, you know, stars within really just a few months. It's one of the fastest growing projects ever on the platform. Uh, I think it speaks to the, the viral. Uh, like takeoff of this project, the fact that it has definitely left the original audience that it, it was built for, uh, and it's kind of staggering to see that huge number. Ben, what do you think of this?
[00:02:45] Ben Lloyd Pearson: Yeah, so to, to be clear, this is GitHub Stars that we're talking about and OpenClaw, just this phenomenal growth, the 250,000 stars in like four months, uh, which I, I looked at the leaderboard this morning and I guess that puts it just outside of the top 10, which is pretty. [00:03:00] Pretty crazy considering that how long many of those top 10 repos have been around.
[00:03:03] Ben Lloyd Pearson: And a lot of people are like compar comparing it to Linux 'cause like it just surpassed Linux, uh, like the number of stars that Linux has. But I, I don't, honestly don't think that comparison is really fair because like, if you know anything about Linux, like you know that Linux development still is happening over on git.kernel.org.
[00:03:21] Ben Lloyd Pearson: The GitHub repo is just like the, it's the simple mirror. Like there's no community activity that happens there. So, you know, I, I've wondered just with, with this news. Um, if Linux was birthed in the GitHub era, like would it rival this, the current success of OpenClaw? Uh uh But you know, I think really what I take away from this is that it's just ongoing proof of this prediction that I've, I've had that the biggest AI benefits that we're going to achieve in the near term future, uh, will come from improving how LLMs are applied to practical everyday situations.
[00:03:53] Ben Lloyd Pearson: Rather than better and better foundation models. Like I, I just like foundation models are great, but like, you know, [00:04:00] people just need agents that work with the tools that we work with every day.
[00:04:05] Andrew Zigler: It's funny, Ben to, you know, hear you talk about all the caveats related to the repo 'cause I've also seen a lot of posts about, you know, delineating between this and like, oh, is it compete?
[00:04:14] Andrew Zigler: Compete with like the, the archival repos, which have like more stars than these. It
[00:04:19] Ben Lloyd Pearson: Yeah.
[00:04:20] Andrew Zigler: of a character on Party Down and that really wants to open a salad chain restaurant. He is really excitedly telling everybody that. The fastest growing non poultry, non-coffee franchise in all of Southern California.
[00:04:32] Andrew Zigler: And it's just putting all of those caveats on, it just makes it extra fun. But this is just also a reminder that GitHub has always been a social network. It really speaks to the viral nature of the platform itself and the ability for it to bridge from engineering into the rest of the world. And I think this is the clearest sign yet.
[00:04:50] Andrew Zigler: Like I said, that OpenClaw has left the building. And what I mean is it's. Not just for engineers and techies anymore, like your bus driver and your aunt are starring this thing. [00:05:00] And I think this speaks to a general hunger for multipurpose agentic assistance. Uh, but there, with any kind of project that has massive growth like this, there's so much potential for security and abuse.
[00:05:11] Andrew Zigler: And so, uh, unfortunately a lot of this is gonna be discovered in fixed and prod because,
[00:05:16] Ben Lloyd Pearson: Yeah.
[00:05:17] Andrew Zigler: been so widely picked up and adopted. So definitely be reminding your aunt to. Upgrade her OpenClaw as those things get patched, because I think that's gonna be the biggest danger ahead.
[00:05:26] Ben Lloyd Pearson: Yeah, well I hope my bus driver's not operating OpenClaw while driving the bus. but you know, this kind of feels, Yeah, I mean, well, they should be giving you orders before they start driving the bus and then have it working while they're driving the bus and not having to look at it. Of course. Um, but you know, this really kind of feels like, you know, the article we're gonna share in the show notes, like it, it highlights how it achieved this phenomenal growth despite having these, like significant security risks and other problems that it creates.
[00:05:54] Ben Lloyd Pearson: And it, it feels like a very, like, common story in tech of like. Three steps forward and two [00:06:00] steps back, like technology advances at like some pretty substantial margins. But then it breaks a lot of the fundamental, fundamental practices that we've built up over time. So we have to like spend time like getting back to where we were in terms of like just raw capabilities.
[00:06:16] Ben Lloyd Pearson: So, you know, one example of this is like when smartphones started to take off, like even before touchscreens were a big thing. You know, everyone was building web apps and, or they were building apps for phones and building websites to work with smartphones. Uh, and there was this period where I felt like the entire, like web and app experience just got like substantially worse than it had been for many years because we were having to reinvent a lot of things for this new era of technology.
[00:06:43] Ben Lloyd Pearson: And, and of course, I mean, I, the, the parallel between mobile and uh, ai, I've heard a lot. I think generally speaking, people who have been through both are, they feel very similar, even though AI does feel like it's a, it's a bigger scale than mobile ever was. But you know, it's, it's very clear that [00:07:00] these AI agents can break all of our security conventions in very short order.
[00:07:04] Ben Lloyd Pearson: They can do it at scale. They can put you at risk really quickly. So I'm still in the camp of like OpenClaw being this like incredibly cool, but also equally terrifying experiment. Like, it, it's, it's just, it's both.
[00:07:17] Andrew Zigler: I agree.
[00:07:18] Ben Lloyd Pearson: All right, well let's move on to the Wasteland or a thousand gas towns. So we're talking about the newest article from Steve Yegge, who we've continued to cover over here at Dev Interrupted 'cause we're learning so much ourselves from him. And Yegge announced the Wasteland, which is a federated workflow that links.
[00:07:36] Ben Lloyd Pearson: Thousands of gas towns via shared wanted boards and has a system for moving work through states with reputation and multidimensional stamps and data that's stored in dos and it's versioned and auditable. Like it's just taking sort of the, the brilliant chaos of gas town to the next level. You know, and Andrew, you and I have been talking about this concept for weeks [00:08:00] now, really ever since.
[00:08:00] Ben Lloyd Pearson: We learned about Gastown and started applying agentic work into our own. Days and we both like, I think clearly understood that like it doesn't stop at level eight of Y's model of age, ancient development. Um, so we've been like wondering like, what's next? Like what's the level nine? The level 10. And you and I have been having a lot of one-on-one conversations lately about like, what it means for multiple people to have orchestrators.
[00:08:24] Ben Lloyd Pearson: I mean, that's how we opened this conversation today. Uh, and what does it mean for multiple, for multiple people to have orchestrators that work together to solve problems and coordinate issues, and, you know, and y is back with this, this wild and interesting metaphor that fits like his typical flavor of storytelling.
[00:08:42] Ben Lloyd Pearson: Uh, but it really does have like my brain churning because like the wayside metaphor itself is like. Both kind of hilarious and brilliant to me. Like I, I like to imagine that the orchestrators that we build, you know, these agent orchestrators that you and I are building, uh, they're, they're like basically creating this [00:09:00] wasteland of finished work, like all around us, right?
[00:09:02] Ben Lloyd Pearson: Like any task that we build an orchestrator for that task is suddenly solved whenever we need it to be solved. Like there's no, there's no wait time. We're just waiting for the tokens to process effectively. Uh, so, you know, if another orchestrator wants to come and work with me, it makes no sense for it to try to, to work in that wasteland.
[00:09:20] Ben Lloyd Pearson: Like it has to go across the wasteland, like bridge the, the chasm, so to speak, and learn how to navigate those vast expanses of these like complex finished work environments and then dock with my orchestrator in a way that they can work together. You know, that's kind of how I'm like visioning it myself for what we're doing.
[00:09:39] Ben Lloyd Pearson: So I wonder if that lines up with how you're feeling about this, Andrew.
[00:09:42] Andrew Zigler: Yeah, I, I, I think that gastown evolving into the idea of the wasteland, that concept makes a lot of sense to me because what gastown solves for the individual is it lets you split up work into atomic units and delegate it into specialized agents or workflows to get [00:10:00] done on loops. And so the natural like aggregate of that, if you were to go one level higher is to have them working together almost like a symphony, right?
[00:10:09] Andrew Zigler: Having different types of gas towns that do different types of work that can coordinate together. Almost like how within those sessions they would be coordinating specialized sub-agents. So that's really the brilliance I think, of what, uh, stands out here. Yegge has obviously been many steps ahead of all of us this whole time.
[00:10:28] Andrew Zigler: So whenever a blog drops from him, I scour for clues because it shows where we're gonna put our feet, where we're gonna climb up that mountain it, it really leaves the footprints that we can follow. So some things that stood out out in here that I'm definitely gonna be trying out in my own orchestrator systems and flows, uh, one of them being reputation.
[00:10:47] Ben Lloyd Pearson: Hmm.
[00:10:48] Andrew Zigler: a really smart takeaway. Um, the idea of having a record, a, uh, a core system of, uh, that's an accurate record of the work that needs to be done, who did it, and then the [00:11:00] level of accuracy and completion that which they did do it. All of that exists with an ledger. This can be something that's almost like immutable.
[00:11:07] Andrew Zigler: You start thinking about something that is storing the work that all of those agents are doing, improving it in a shared space, and the value you get of this is coordination, you know, uh, and other types of technology, especially things like and, and like blockchain technology as well. how they operate together.
[00:11:23] Andrew Zigler: And so really he's borrowing a lot of concepts there, reputation being one of them. But what stood out to me as well is the idea that, you know, agents are not the blockchain, they are accruing real specializations and domain expertise around all sorts of different nuanced work. And so being able to accurately and reliably judge that work and if you can trust it, is how.
[00:11:45] Andrew Zigler: I would be able to let my gas town or my specialized agents in my gas town work with yours. And you'd be able to trust that. another part of this too that really was interesting to read about is the federation itself. Because like two months ago I made a joke on here in [00:12:00] one of our news segments, Ben, about like, I was like, oh, what's gonna happen is like my gas town gonna call your gas town and now like egg on my face.
[00:12:07] Andrew Zigler: Oopsie. I was definitely
[00:12:09] Ben Lloyd Pearson: No. It's a wanted board. It's a wanted board.
[00:12:12] Andrew Zigler: That is where this is going. Wanted board in telephone, however you want to address it up.
[00:12:19] Ben Lloyd Pearson: Yeah.
[00:12:19] Andrew Zigler: It, it answers to a, almost like a one level higher than like the A2A protocol of like how to, like the, how does this massive agents and this match of agents work together.
[00:12:29] Ben Lloyd Pearson: Yeah.
[00:12:29] Andrew Zigler: and both of these ideas together, the reputation and the federation, they become a natural framework that enable people to systematize and combine this work together in systems that obviously, you know, don't have, uh, like a mutual understanding of, of trust. Obviously within like your own company, you probably don't need this level of granularity in order to interact with your coworkers.
[00:12:53] Andrew Zigler: But when we're talking about, you know, the Wild West or out in the opens, or in this case wasteland,
[00:12:58] Ben Lloyd Pearson: Yeah.
[00:12:58] Andrew Zigler: is the kind of system you need to [00:13:00] protect yourself.
[00:13:01] Ben Lloyd Pearson: Yeah, I mean, you, of course, you gotta always remember he's working with a, with a large open source community at this point. So, uh, that's a very different, you, you know, it, it's, it's hard to build trust in that environment and you have lots of untrusted actors in that environment as well. You know, but there was, there was one element that really stuck out to me that I absolutely love, and that's the RPG metaphor that he has towards the end of this article.
[00:13:23] Ben Lloyd Pearson: Where he had like a little like character sheet that he had produced that sort of, sort of shows like the skills and the, the reputation as you mentioned of the, the orchestrator. And I, I, I think we need to steal that, Andrew. Like we're gonna steal that idea. All of our, all of our agent orchestrators are gonna get their own character sheet.
[00:13:43] Ben Lloyd Pearson: Uh, and yeah, they're gonna have bounty systems, wanted boards are gonna have all that stuff, I think.
[00:13:48] Andrew Zigler: Amazing.
[00:13:50] Ben Lloyd Pearson: All right. Let's talk about this perplexity computer. What do, what do we have here, Andrew?
[00:13:53] Andrew Zigler: Yeah, so this is another side of a similar coin coin, the idea of how do you, you know, combine [00:14:00] agentic systems together to work reliably and at scale. This is perplexity announcing the perplexity computer, and it's a general purpose digital worker that can create and execute whole workflows and do long running jobs that can run for hours or days or weeks or months using a very intelligent, multimodal.
[00:14:16] Andrew Zigler: Orchestration system. And what makes this different from, you know, other harnesses or operators is that the perplexity computer is operating more on a granular level, uh, almost operating on the operating system level itself. It speaks to some of the natural evolutions of what technology has to do to meet agents where they are.
[00:14:36] Andrew Zigler: Because I've said on this show before that, you know, agents are arrived in the internet. That's not yet. Built for them. And I, I, I love projects like this that reimagine what that compute could look like for them. And it's not a foreign idea to the show either because, on our newsletter, Lenny Pruss last year of Amplify Partners, he wrote the, wrote a really great guest article about. Programming languages and how they should be designed for agents. Uh, [00:15:00] just recently I sat down with Matt Boyle at ONA about how they're designing cloud environments for long running agents in a similar way and, and protecting, uh, the rest of the technology stack on a kernel level in terms of what the agent can do.
[00:15:14] Andrew Zigler: Uh, there's a lot of benefits in this and complications, but one thing I think is for sure, it's, um. Operating and restricting, and redesigning at almost the kernel and operating system level is something worth exploring. And I think this concept is only going to get more, uh, proven as time goes on.
[00:15:30] Ben Lloyd Pearson: So when, when I was reading this, it, it felt like this is almost like perplexity's answer to like Claude Cowork or OpenClaw. Is that, is that your interpretation of this, Andrew, or is it something else?
[00:15:41] Andrew Zigler: It seems to be, it's the idea of the answer engine. How does that evolve into its natural next state? It can take those answers and then it can turn that information that you're scouring long term into systematic reports. You know this, there's
[00:15:54] Ben Lloyd Pearson: Hmm.
[00:15:54] Andrew Zigler: a technology like this called Scout, um, that I've seen as well.
[00:15:58] Andrew Zigler: And these are long running [00:16:00] like, um, uh, search agents. You basically set them on some search queries or some geo, like certain kinds of like, uh, things that you want them to constantly stay on top of. They search on a regular basis, go deep on articles and prepare reports for you in the background and the ideas they run for weeks or months.
[00:16:15] Andrew Zigler: Just like this, you're designing and executing the workflows, with like an answer, or like a long-term answer that you can't get from one query.
[00:16:22] Ben Lloyd Pearson: Yeah, I, I feel like this space is like getting competitive about as quickly as like the foundation model space has gotten competitive, you know, and, uh, you know, I'm, I'm not personally a perplexity user. Um, I have used it in the past, but I have always been fascinated by what they do. 'cause I think they, they do often take very creative approaches in this space.
[00:16:43] Ben Lloyd Pearson: you know, and I'm just thinking back to like, when they first hit the scene, you know, everyone back then was basically a chat bot. Like that was all of the GPT experiences that we had out there. Uh, and perplexity was really the first one to take this approach of like, applying that to like, create a new search engine for the web, which is a really interesting [00:17:00] application that's now starting, like everyone else has sort of caught up to that and done their own version of it.
[00:17:05] Ben Lloyd Pearson: and they've also done a lot of interesting innovations around like content generation collecting feeds of information. So, yeah, it, it totally makes sense that they continue to innovate in this space. And, you know, for now, low, I feel like you and I, our team, we've been taking really the approach of like, building our own agents mostly, rather than trying to get something out of the box, which is kind of what my impression of this is a little more, uh, which is why we've stuck with like Claude Code, for example.
[00:17:30] Ben Lloyd Pearson: Um, but I think if, you know, correct me if I'm wrong, but it seems like if you, if you're someone who wants more out of the box experience, like this may be something that, that would benefit you. Does that seem right, Andrew?
[00:17:41] Andrew Zigler: if you, if you wanna operate with long running answer engine agents as a service, then perplexity computer is probably the something to look for. Of course, if you're orchestrating and collecting that knowledge on your own with workflows in the background, maybe you're, this is already covered.
[00:17:57] Ben Lloyd Pearson: Yeah.
[00:17:58] Andrew Zigler: this is definitely gonna, this is definitely a sign of like [00:18:00] more types of services like this to come.
[00:18:01] Ben Lloyd Pearson: Yeah, I de I'll definitely give them credit 'cause I think they are on the right thread in terms of like, you know, again, the types of, the types of things that we should be building to, to get better, more out of ai, you know, so it's a pretty cool project. All right, well let's close out our lineup with a, this story from friend of show Geoffrey Huntley, about how software development is now cheaper than the cost of hiring a minimum wage worker.
[00:18:25] Ben Lloyd Pearson: What do we have here, Andrew?
[00:18:26] Andrew Zigler: Yes, this is, uh, the scoop on software development and how that practice is dead compared to software engineering. This is Geoffrey Huntley's core operating thesis, uh, and he's famously written that software development now costs $10.42 an hour because that's how much it costs to run a Claude
[00:18:43] Andrew Zigler: Code session on a loop on a virtual machine. Uh, and, and this is coming at a time where when you go to any kind of tech meetup or even AI meetups now, it's oftentimes full of, full of people in the room that aren't traditional engineers coming from all sorts of different backgrounds, [00:19:00] embracing the tools. I think this is like, uh, really speaks to the widespread availability of it, but it also speaks to the almost like, uh, immediate devaluation of a specialization where if your output was just writing code, then you know that that time has changed and that that's really what Geoffrey gets at in this article. Um, and, and I, this was definitely making the rounds on LinkedIn as well.
[00:19:23] Ben Lloyd Pearson: Yeah, and this was something we talked, we spoke to Geoffrey about when he came on the show a few weeks back. And, you know, I, first of all, I wanna say like, you know, we don't mean to degrade anyone's work by talking about this subject. Like, um, if you're a software developer or if you're a minimum wage worker at like a fast food place or some sort of service sector job, like, I don't wanna minimize the value of those
[00:19:44] Ben Lloyd Pearson: people or the roles that they bring. But I think it is really important to understand this, or to point out how software development is something that like used to be viewed as a way to achieve like, relatively good personal wealth. Like you could learn to write code and make good money off of [00:20:00] that, and that simply isn't the opportunity that's available anymore.
[00:20:04] Ben Lloyd Pearson: And I think it's really important because there's a lot of nuance here that, that I think often gets lost, and I think definitions are incredibly important for this. So software development is just the act of turning requirements into code. Like you're basically paid for understanding how to write code.
[00:20:19] Ben Lloyd Pearson: As I said, versus software engineering where you build the requirements and understand the users, the architecture, the technical decisions, all of that requires higher order capabilities and skills. So it's the former that's being replaced, so software development, and that's being replaced wholesale by ai.
[00:20:37] Ben Lloyd Pearson: Right now, uh, you know, and frankly, we're seeing the same thing happen on the content production side. What we're doing here at Dev Interrupted, you know, you and I have been compressing workflows that used to take us days down to hours or sometimes even minutes or seconds. You know, like just last week we were talking about our, how the, the, all the time we saved with the agents that we built.
[00:20:57] Ben Lloyd Pearson: Uh, you know, we built this agentic system. We probably saved [00:21:00] 40 plus hours of work in the last week. That's like an an extra week's worth of work that we compressed down to hours. Uh, and this was a project with a tight deadline. So it had, it made, it made a massive impact on us.
[00:21:12] Andrew Zigler: Yeah, and I appreciate the distinction that you make between software development, software engineering. I think it's crucial to make, but I also think it's reminder to folks who are software developers that you are also a software. For our engineer, you
[00:21:25] Ben Lloyd Pearson: Yeah.
[00:21:25] Andrew Zigler: have the skills behind scoping reti or making requirements and and understanding the technical decisions and making the architecture.
[00:21:33] Andrew Zigler: Those are all latent. If they're not expressed explicitly, it's just a matter of finding them and being able to utilize those skills with things like agents to do. Uh, maybe more of the work that used to occupy your time before. If you can make that jump, which I know and I'm fully confident, any software developer listening to this or otherwise is capable of doing, then you know you're gonna be well positioned to, to ride the wave.
[00:21:59] Andrew Zigler: I think that the [00:22:00] important thing here is to, you have to take action. Because the gap will only widen, and the longer that you wait, the harder it will be to cross the chasm. But I, like I said, there's gonna be a lot of new works, a new work for engineers and new systems to be built and combined. It's an opportunity to build and define skills before anyone else.
[00:22:17] Andrew Zigler: Going back to the story of Gas Town and being a highly specialized, highly reputable person, capable of outputting tons of code, imagine that as your next thing to optimize for. How can I create an agentic system that's hyper specialized in something that I have a lot of domain expertise in, and then own it and its outputs and you know. if you're not hungry enough for that kind of chase, then I think there's somewhere in the middle that you can fall. But you do have to find that place for yourself. but just keep in mind that like AI is moving so fast, so it's important to stay on top of each of each and every week, and it all brings different things.
[00:22:51] Andrew Zigler: That's why we're here every week talking about it. but on the upside too, I think we're gonna be in a world where engineering. Proliferates everywhere. All [00:23:00] companies become
[00:23:00] Ben Lloyd Pearson: Yeah.
[00:23:01] Andrew Zigler: companies in a way that they weren't before, and you're gonna see a lot of really cool new engineering related roles that simply weren't possible until
[00:23:08] Ben Lloyd Pearson: Mm-hmm.
[00:23:08] Andrew Zigler: you could find something that could end up being your life's passion as a role that simply it doesn't exist yet because the world is evolving into that. And, uh, if you want to like brainstorm or explore some of those, I really recommend, uh, Scott Werner of Works on My Machine. He's, we've covered his articles here before. He has a really cool, uh, system called the Traffic Jam Explorer. It's a claw artifact that naturally explores the evolution of ideas of like, you introduce an agent to an industry or a problem, how does that beget this? And then if that begets that, then what becomes of that? And it's basically a. Philosophical Tree of Potential Futures. So it's really cool to dig through there and find maybe unique opportunities for yourself that could become the reality tomorrow.
[00:23:52] Ben Lloyd Pearson: Yeah, I act, I actually have not read that article yet, so I'll have to go check it out. But I love how this episode really is coming full circle today. Like it feels like everything we're covering is like very [00:24:00] interconnected, you know, because I think this is where the me, the wasteland metaphor really starts to come back.
[00:24:05] Ben Lloyd Pearson: Like our agentic systems, they effectively allow us to expand the breadth of our scope within our roles. So we can do new things. We can take on new challenges, we can solve bigger problems, and we're creating this sort of like bubble of problem types that. Have been solved around us. You know, again, getting back to this wasteland, like all of these tasks that are around us that just are solved by default now because we have agents that do it.
[00:24:31] Ben Lloyd Pearson: and you know, I think the, like Geoffrey brings up a lot of really great opinions, or in this article, particularly around like seat based pricing. Like that is a major risk for a wide range of reasons, if that's, if your company still depends heavily on it. Um, the best pricing models right now seem to be things that are usage based because that reflects the utility and the value that the product brings to someone or an agent for that matter.
[00:24:56] Ben Lloyd Pearson: And there's a lot of tough challenges to grapple with right now, but [00:25:00] like you said, there's an extraordinary amount of opportunity as well. Like if you're someone who's out there who's really starting to take advantage of age agentic development or age agentic work otherwise, and you feel like you're thriving because of it.
[00:25:13] Ben Lloyd Pearson: You should embrace that and like really push into it. Uh, because I think it's an incredibly valuable skill to have in this moment. And you know, just from personal experience, I know you and Andrew, I feel like we're having this almost like leapfrogging effect where, where I'm able to work with my agents to get a breakthrough and then your agents come in and they get their own breakthrough and we sort of like, uh, uh, we're accumulating all these benefits at a rate that we've never been able to do it before.
[00:25:39] Ben Lloyd Pearson: And because we're. We're both operating, uh, in this way, like the, the sum of our components is, is, or the sum of our whole is greater than the component parts. I think that's how it goes.
[00:25:51] Andrew Zigler: Something like that.
[00:25:52] Ben Lloyd Pearson: Yeah. But I mean, you know, long story short, collaborating in this agent way, it's a lot of fun. You can do a lot of really in interesting and amazing [00:26:00] things that you didn't really expect you could before.
[00:26:02] Andrew Zigler: Mm-hmm.
[00:26:03] Ben Lloyd Pearson: just a matter of learning the skills and, and now's the time, now's the time to do it.
[00:26:07] Andrew Zigler: Yes, collaborating is very fun. Also be very chaotic. Um, and there's lots of strategies involved. So, you know, the wastelands only the beginning of that saga. I'm sure we're gonna see lots of really interesting scenarios that come out of that reality. And we're gonna cover them here on Dev Interrupted because this, this role's moving pretty fast, but, uh, there's a lot of stuff to cover week after week
[00:26:27] Ben Lloyd Pearson: Cool. What are your agents working on this weekend, Andrew?
[00:26:30] Andrew Zigler: This weekend? Oh, let's
[00:26:32] Ben Lloyd Pearson: Yeah.
[00:26:34] Andrew Zigler: going back to the perplexity computer idea. I've been actually experimenting with the idea of creating almost like a kernel for an LLM to use. I've had some prototypes I've gone back and forth with. Maybe this weekend will be, uh, the weekend. I bite the bullet and try to build it out.
[00:26:49] Andrew Zigler: What about you?
[00:26:50] Ben Lloyd Pearson: Yeah, it's amazing how we think about these challenges at like totally different levels because you're like, I just need a new kernel obviously, and I'm over here. Like, how do I [00:27:00] get my agent to help me make sense of my life?
[00:27:03] Andrew Zigler: Well, I created this like scripting language that then I was trying to, I was thinking maybe I would have a fun experiment of maybe I could fine tune an agent that was really good at using this custom scripting language that I had made. Because that's one of the fun parts too, is that, you know, it's so easy to make new languages.
[00:27:19] Andrew Zigler: Now, I've already made one. Our friend Geoffrey, on the show, he's made one as well. we covered, cursed back here on, on the show back, like last, uh, October. Uh, it's a, it's a c compiler and it's like, uh, I love having these kinds of utilities available, uh, and making them, I, I, I just wish that more people would, uh, adopt and use things like cursed.
[00:27:39] Andrew Zigler: So if you're, if you're a listener and you're building stuff this year and maybe cursed as the project, the pickup.
[00:27:44] Ben Lloyd Pearson: Yeah. Yeah. And I know Geoffrey mentioned something about wanting to get it in the Stack Overflow survey this year. So you know, Erin, I know you listen out there, friend of show if, if you can make that happen. Hook us up. We'd love to see it.
[00:27:57] Andrew Zigler: And
[00:27:58] Ben Lloyd Pearson: we might have to. Yeah. Otherwise we might have [00:28:00] to kick off a write-in campaign.
[00:28:01] Ben Lloyd Pearson: Who knows? We'll see.
[00:28:02] Andrew Zigler: Well there's definitely gonna be a write-in campaign. I think everyone else, this is your call to action. If you're using agent agents this year to do some coding, maybe try to have them write it in cursed and fill that in on the developer survey this year so we can make sure that our friends have Stack Overflow know.
[00:28:16] Ben Lloyd Pearson: Yeah, absolutely.
[00:28:18] Andrew Zigler: Alright, well thanks for joining us and we'll see you next time.
[00:28:21]
[00:28:28] Ben Lloyd Pearson: AI helps your developers write more code faster. But here's the problem. Your review process hasn't sped up. The queue grows, reviewers get burnt out. Cycle time stalls. LinearB B changes that our AI reviews every pr the moment it's created. Catching bugs, security gaps and performance issues before humans get involved.
[00:28:48] Ben Lloyd Pearson: It even writes the PR description automatically. your reviewers spend less time on first pass problems and more time on architecture and business logic. Break the bottleneck. See how LinearB B accelerates your [00:29:00] workflow.
