The agent wasteland, federated workflows, and a computer for computers

0:04Andrew:Hey, I agents everywhere. 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?

0:12Ben:Oh, well, your agent saved me actually a lot of hours this last week, because they were super useful for the tasks that we had at hand. But I also that same question back at you. You know, how many hours of my agents saved you in the last week?

0:26Andrew:Well, in the last week, nothing, because I've been using my agents this whole time. 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 like the signals go back to the other agents. You know, it's pretty fun.

0:47Ben:It's pretty funny how quickly I was able to change anything that you handed off to me as well. to the point where I had to bring in a whole dedicated agent just to figure out how your project and my project go back together. And I got to say, this is still one of the biggest unsolved problems in, I think, collaborative agentic engineering. I experienced this last year when I was on Code TV's episode for Goose, and it was a two-person challenge vibe coding with sub-agents. So you have two people using teams of sub-agents, and then at the end, I had to combine my front end with someone's back end.

1:20Ben:And you can watch the video to see how that turned out.

1:26Dan:It's a pretty hilarious saga. Yeah, we need to go from like one to two.

1:31Andrew: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 going to cover today. So let's just get into the Friday deploy. I'm your host, Ben Lloyd Pearson. And I'm your host, Andrew Ziegler. Yeah, and here's what we're covering today. We have OpenClaw rocketing into a risky orbit. steve yege back unveiling the agent wasteland which is what i want to talk about uh related to what we were just bantering over we have perplexity launching personal agents and then dev work falling below minimum wage andrew let's just start right at the top and talk about open claw because i feel like not a week goes by at this point where we we something doesn't hit the

2:08Ben:news about it so what do we have here yeah so open call rocketed to the top of most starred status on, you know, star charts, which is the famous way of seeing how quickly and virally 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. I think it speaks to the viral like takeoff of this project. The fact that it has definitely left the original audience that But it was built for, and it's kind of staggering to see that huge number. Ben, what do you think of this?

2:45Andrew:Yeah, so to be clear, this is GitHub stars that we're talking about. And OpenClaw, just this phenomenal growth, 250 ,000 stars in like four months. I looked at the leaderboard this morning, and I guess that puts it just outside of the top 10, which is pretty crazy considering how long many of those top 10 repos have been around. And a lot of people are comparing it to Linux because it just surpassed Linux, like the number of stars that Linux has. But I honestly don't think that comparison is really fair because if you know anything about Linux, you know that Linux development still is happening over on git.kernel.org.

3:20Andrew:And the GitHub repo is just like the, it's a simple mirror. There's no community activity that happens there. So I've wondered just with this news, if Linux was birthed in the GitHub era, would it rival the current success of OpenClaw? 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 had that the biggest AI benefits that we're going to achieve in the near term future will come from improving how LLMs are applied to practical everyday situations rather than better and better foundation models. Like foundation models are great, but like, you know, people just need agents that work with the tools that we work with every day.

4:04Ben:It's funny, Ben, to hear you talk about all the caveats related to the repo, because I've also seen a lot of posts about delineating between this and like, oh, is it compete with the archival repos, which have more stars than these. It reminds me of a character on Party Down that really wants to open a salad chain restaurant. He is really excitedly telling everybody that it's the fastest growing, non-poultry, non-coffee franchise in all of Southern California, and is 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.

4:41Ben: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, 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. And I think this speaks to a general hunger for multipurpose agentic assistance. but there with any kind of project that has massive growth like this there's so much potential for security and abuse and so unfortunately a lot of this is going to be discovered in fixed and prod because it's been so widely picked up and adopted so definitely be reminding your aunt to upgrade her open claw as those things get patched because i think that's going to be the biggest danger ahead

5:26Andrew:yeah well i hope my bus driver is not operating open claw while driving the bus but you know Yeah, I mean, well, they should be giving the 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. Fair. But, you know, this really kind of feels like, you know, the article we're going to share in the show notes, like it highlights how it achieved this phenomenal growth despite having these like significant security risks and other problems that it creates. And it feels like a very common story in tech of three steps forward and two steps back.

6:01Andrew:Technology advances at some pretty substantial margins, but then it breaks a lot of the 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. 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 they're building apps for phones and building websites to work with smartphones. 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.

6:37Andrew:because we were having to reinvent a lot of things for this new era of technology. And of course, I mean, the parallel between mobile and AI, I've heard a lot. You know, I think generally speaking, people who have been through both, they feel very similar, even though AI does feel like it's a bigger scale than mobile ever was. But, you know, it's very clear that these AI agents can break all of our security conventions in very short order. They can do it at scale. They can put you at risk really quickly. So I'm still in the camp of like Open Claw being this like incredibly cool, but also equally terrifying experiment.

7:15Andrew:Like it's just, it's both.

7:17Ben:I agree.

7:19Andrew: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 Yege, who we've continued to cover over here at Dev Interrupted because we're learning so much ourselves from him. And Yege announced The Wasteland, which is a federated workflow that links thousands of Gastowns via shared wanted boards and has a system for moving work through states with reputation and multidimensional stamps and data that's stored in Dolt and it's versioned and auditable. It's just taking sort of the brilliant chaos of Gastown to the next level. you know and Andrew you and I have been talking about this concept for weeks now really ever since we learned about Gastown and started applying agentic work into our own uh days and we both like I think clearly understood that like it doesn't stop at level eight of Yege's model of agentic 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 I mean that's how we opened this conversation today.

8:27Andrew:And what does it mean for multiple people to have orchestrators that work together to solve problems and coordinate issues? And, you know, and Yege is back with this wild and interesting metaphor that fits like his typical flavor of storytelling. But it really does have like my brain churning because like the wasteland metaphor itself is like both kind of hilarious and brilliant to me. Like, I like to imagine that the orchestrators that we build, you know, these agent orchestrators that you and I are building, they're like basically creating this wasteland of finished work, like all around us, right?

9:02Andrew: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. 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. Like it has to go across the wasteland, like bridge 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.

9:39Andrew:So I wonder if that lines up with how you're feeling about this, Andrew.

9:42Ben:Yeah, I think the 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 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? Having different types of Gastowns that do different types of work that can coordinate together, almost like how within those sessions they would be coordinating specialized sub agents.

10:21Ben:So that's really the brilliance, I think, of what stands out here. Yege's obviously been many steps ahead of all of us this whole time. So whenever a blog drops from him, I scour for clues because it shows where we're going to put our feet, where we're going to climb up that mountain. It really leaves the footprints that we can follow. So some things that stood out in here that I'm definitely going to be trying out in my own orchestrator systems and flows, one of them being reputation. I thought this was a really smart takeaway. The idea of having a record, a core system that's an accurate record of the work that needs to be done, who did it, and then the level of accuracy and completion at which they did do it.

11:03Ben:All of that exists within a ledger. This can be something that's almost like immutable. 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, other types of technology, especially things like blockchain technology as well, that's how they operate together. 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.

11:38Ben:And so being able to accurately and reliably judge that work and if you can trust it is how I would be able to let my Gastown or my specialized agents in my Gastown 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 one of our news segments, Ben, about like, I was like, oh, what's going to happen? Is like my Gastown going to call your Gastown? and now like egg on my face oopsie i was definitely wrong because it's a wanted board it's a wanted board that is where this is going wanted board in telephone however you want to dress it up it's it answers to a almost like a one level higher than like the a to a protocol of like how to like how does this mass of agents and this mass of agents work together 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 like a mutual understanding of trust.

12:45Ben:Obviously, within your own company, you probably don't need this level of granularity in order to interop with your co-workers. But when we're talking about, you know, the Wild West or out in the opens or in this case, wasteland, this is the kind of system you need to protect yourself.

13:00Andrew:Yeah, I mean, Yege, of course, you got to always remember he's working with a large open source community at this point say that's a very different you know you know it's it's hard to build trust in that environment 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 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 think we need to steal that angie like we're going to steal that idea all of our all of our agent orchestrators are going to get their own character sheet uh and yeah they're going to have bounty systems wanted boards are going to have all that stuff i think amazing all right let's talk about this perplexity computer what do we have here andrew yeah so this is another side of a similar

13:56Ben:coin, the idea of how do you, you know, combine 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 orchestration system. And what makes this different from, you know, other harnesses or operators is that the Perplexity computers operating more on a granular level, 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.

14:36Ben:Because I've said on the show before that agents are arrived in the internet that's not yet built for them. And 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 Press last year of Amplify Partners. He wrote a really great guest article about programming languages and how they should be designed for agents. 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 protecting the rest of the technology stack on a kernel level in terms of what the agent can do.

15:14Ben:There's a lot of benefits in this and complications, but one thing I think is for sure. It's 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 proven as time goes on.

15:30Andrew:So when I was reading this, 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,

15:39Dan:or is it something else? It seems to be.

15:42Ben: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, there's also a technology like this called Scout that I've seen as well. And these are long-running, like, search agents. You basically set them on some search queries or some, like, certain kinds of, like, 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 just like this, you're designing and executing the workflows with like an answer, like a long-term answer that you can't get from one query.

16:22Yeah.

16:23Andrew:I feel like this space is like getting competitive about as quickly as like the foundation model space has gotten competitive, you know, and so that, you know, I'm not personally a perplexity user. I have used it in the past, but I have always been fascinated by what they do because I think they, they do often take very creative approaches in this space. you know 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 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 application that's now starting like everyone else has sort of caught up to that and done their own version of it and they've also done a lot of interesting innovations around like content generation collecting feeds of information so yeah it totally makes sense that they continue to innovate in this space and you know for now 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 which is why we've stuck with like clod code for example 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 would benefit you.

17:40Andrew:Does that seem right?

17:41Dan:Yeah, if you want to operate

17:43Ben:with long-running answer engine agents as a service, then Perplexi Computer is probably something to look for. Of course, if you're orchestrating and collecting that knowledge on your own with workflows in the background, maybe this is already covered. But this is definitely a sign of more types of services like this to come.

18:01Andrew:Yeah, I'll definitely give them credit because 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 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 this story from friend of show Jeffrey Huntley about how software development is now cheaper than the cost of hiring a minimum wage worker. What do we have here, Andrew?

18:27Ben:Yes, this is the scoop on software development and how that practice is dead compared to software engineering. This is Jeffrey Huntley's core operating thesis. And he's famously written that software development now costs$10.42 an hour because that's how much it costs to run a cloud code session on a loop on a virtual machine. 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 people in the room that aren't traditional engineers coming from all sorts of different backgrounds embracing the tools. I think this is like really speaks to the widespread availability of it, but it also speaks to the almost like immediate devaluation of a specialization where if your output was just writing code, then, you know, that time has changed.