Hermes Agent: Agents that grow with you

Open Source AI is entering a new era, one shaped by self-improving AI Agents, recursive learning systems, and rapidly evolving AI Tools that blur the line between software and autonomous collaborators. In this episode, Daniel and Chris sit down with Nous Research co-founder and CTO Jeffrey Quesnelle to explore Hermes Agent. Along the way, they discuss models vs. harnesses, the changing role of developers, and one of the biggest questions facing the AI Future: what remains uniquely human as AI capabilities continue to accelerate? Featuring: Jeffrey Quesnelle – Website https://jeffq.com/, LinkedIn https://www.linkedin.com/in/jeffrey-quesnelle-2490a524/Chris Benson – Website https://chrisbenson.com/, LinkedIn https://www.linkedin.com/in/chrisbenson, Bluesky https://bsky.app/profile/chrisbenson.bsky.social, GitHub https://github.com/chrisbenson, X https://x.com/chrisbensonDaniel Whitenack – Website https://www.datadan.io/, GitHub https://github.com/dwhitena, X https://x.com/dwhitenaLinks: Nous Research https://nousresearch.com/Hermes Agent https://hermes-agent.nousresearch.com/Sponsors: Framer: The enterprise-grade website builder that lets your team ship faster. Get 30% off at framer.com/practicalai http://framer.com/practicalaiPrediction Guard: A self-hosted AI control plane for running agents in high impact environments. predictionguard.com/practicalai https://predictionguard.com/practicalaiUpcoming Events: Register for upcoming webinars here https://practicalai.fm/webinars! Midwest AI Summit 2026 https://midwestaisummit.com/

• 0:02Speaker 00

  Welcome to the Practical AI Podcast, where we break down the real-world applications of artificial intelligence and how it's shaping the way we live, work, and create. Our goal is to help make AI technology practical, productive, and accessible to everyone. Whether you're a developer, business leader, or just curious about the tech behind the buzz, you're in the right place. Be sure to connect with us on LinkedIn, X, or Blue Sky to stay up to date with episode drops, behind-the-scenes content, and AI insights. You can learn more at practicalai.fm. Now, onto the show.

• 0:41Speaker 01

  Welcome to another episode of the Practical AI Podcast. This is Daniel Whitenack. I am CEO at Prediction Guard, and I'm joined, as always, by my co-host, Chris Benson, who is a Principal AI and Autonomy Research Engineer. How you doing, Chris? Hey, doing great today. How's it going, Dan? It's going really good. I've been excited for this one, I guess, ever since a conversation that we had back in 2024 on the show with one of the co-founders of Noose Research. Today, we've got another one of those co-founders with us, Jeffrey Cannell, who is co-founder and CTO at Noose Research. Welcome.

• 1:21Speaker 02

  Hi there. Thanks for having me on.

• 1:22Speaker 01

  Yeah, it's great to catch up. Of course, big admirers of a lot of the things you all are doing and really enjoyed the last conversation. That was, though, in 2024, so it's been a couple of years, and that's like eternity in the...

• 1:38Speaker 02

  Twenty years in AI time, yeah.

• 1:39Speaker 01

  Yeah, yeah, 20 years in AI time. So I believe, if I remember right, kind of at that time, Noose Research, which, for listeners, I would encourage you to go back and listen to that episode, which was, at a certain point, primarily a kind of distributed community of folks on Discord and elsewhere. But I believe that was kind of morphing into more of an actual company or organization at that time. Could you kind of help us understand how that's evolved over the last couple of years? Maybe some highlights from the Noose history books over the past couple of years?

• 2:16Speaker 02

  Yeah, like you said, it was two years ago, so 20 years in AI time. And we did sort of start out, like you said, as sort of this loose collaboration of the homies on the Discord, as I always like to say. And that sort of grew organically just through Twitter and other places like that. People who are fundamentally interested in open source AI and making sure that this, you know, this tech that we think is, you know, the transformational technology of our, of our, of our generation wasn't going to just get locked behind a few closed companies. And at the time, we were sort of looking up at, you know, GPT-3.5 had just come out. The ChatGPT thing had happened fully. And us who cared about open source were like, how is this ever gonna,

• 3:01Speaker 02

  how are we gonna keep this, keep this alive? Because it seemed like the, the sort of curve of capitalization was already starting. If you didn't have a ton of money, you were never going to be able to catch up. But what we, what we were able to find was that because the research space in this is actually quite like, at the time, especially two years ago, was really quite nascent. And there were a lot of like low hanging fruit sort of things that could be discovered by just like one or two people, you know, doing independent research. And we brought together some of the people who had made some of these discoveries. And, you know, it kind of gave us credence to the idea that like, maybe the, you know, David really can beat Goliath, or at least, you know, get on, get on the same field.

• 3:43Speaker 02

  And so we brought everyone together and decided to say, you know, it was really just sort of a way for us to say, we have these people who are doing this for free, basically, you know, on their spare time. Is there a way we can form this into a company so that we could take people who care about this and let them devote their whole, you know, their whole, their whole experience, time to it? So we brought the company together, maybe about two years ago, and, and sort of went through a path of, of different experimentation. The North Star was always like, we have to keep this tech, you know, open and make sure that as many people can use it. And that was always the North Star. But the question was, what was the modality in which that was really gonna, you know, express itself? We spent some time looking at different aspects of sort of like the AI pipeline as it is, and figured out where are the ways we can

• 4:27Speaker 02

  Democratize this and and we started first through what we'd originally done, which is through academic research. So we spent lots of time. We published several papers that said, like, take something that's currently extremely expensive in the AI space or is locked behind behind huge, you know, huge capital costs. And can we, you know, do thousand X improvements on that that can bring that back down to like, the scope of of us who, although we have like, some small amount of money, it's like, you know, the it's a rounding error. It's the it's the catering budget at some, you know, at some of these larger places. But it turns out that a lot of things in the AI space, because everyone's scaling so fast, you can, for some times, just kind of throw dumb money at it a little bit, and

• 5:09Speaker 02

  it does get better. But if you're a little bit smarter about it, there were big efficiency gains. So we spent around several years just doing research in that, putting out fine tunes that we that were aligned to the sort of models that respect you and aren't going to be like, moralizing and stuff. That was our original Hermes series of models that were very popular. This is, of course, pre-thinking, pre-reasoning, pre sort of deep-seat kind of style models. We did that and had a lot of success and people enjoyed that. The academic research, we spent a while looking at, in fact, distributed training and how that whether that was a viable path and

• 5:50Speaker 02

  put out some interesting research there about like, how you could train models over the internet. You know, this was also in response to some political things that were going on and kind of still are going on, to be honest with you, about like, what would happen if people tried to outlaw, you know, even using open source AI and stuff. So we did research on that space, too. And all of it kind of was coalesced around this idea of, you know, needing these thousand X hacks. So one of the one, one of the interesting thousand X hacks that we tried to take on, which eventually turned into this thing that is now Hermes agent, was the idea of recursive self-improvement. And recursive self-improvement is where like, the model is able to somehow

• 6:33Speaker 02

  train itself or do experiments on itself, you know, and automate that path of the Of the pipeline, because you can think of, you know, high-end AI research engineers, you know, the people who really know are like NFL quarterbacks now, basically, you know what I mean? Like, you gotta pay them like NFL quarterbacks and, you know, they are gonna decide whether your team gets to the playoff, you know, like they're that important to like your composition of the structure and places the the large corporations, because the more capitalized, like have better access to this, you know, this talent, limited talent pipeline as well. But GPUs are a piece of it, but human brains are a piece of it, too. So we said, well, how can we also try to, you know, you know, hack around that? So we started building this tool internally for our own model research team to automate

• 7:17Speaker 02

  what some of the research that they were doing and and and figure out whether there was some, you know, and do that. And that was kind of just like, uh, let's see if we can do this. And and that tool was internally just called Hermes Agent. And we started this about six months ago. And it was it was about six months ago that this was our our tooling. And we used it internally for for several months. And that's why if you sort of go back to the genesis of Hermes Agent, if you look at those first commits that were open source, it was basically all around model training. Like, all of the stuff that we had built into it was all like, all the stuff we used internally for for AI research. But we had this idea, you know, and once we had built it, we kind of were like, why are we keeping this secret? You know, that's, you know, we were sort of default open source unless we can say there's a reason not to.

• 8:02Speaker 02

  So we we released this, the repository Hermes Agent. And, you know, it was just a floodgate of product market fit, for lack of a better word, you know, but things were, you know, a lot has been said about what has happened over the last several months with agents and your harnesses and stuff. And I'm happy to, we can talk all about that, but it was kind of like, right time, right place. And over the last several months, it's kind of just like, Get over every aspect of the company, which is awesome because like I said, when I were talking a little bit earlier is that, you know, the North Star has always been open source AI, bringing this to as many people as possible. Now, the vehicle, sort of the delivery mechanism

• 8:44Speaker 02

  that we were going to use to do that kind of, you know, we were sussing out, but it's really in the last several months crystallized for us. So that's sort of the history of Noose in the last few years in maybe five or 10 minutes.

• 8:55Speaker 03

  So yeah, that was awesome. Love that. So and you introduced a whole bunch of things we can dive into. So I'm going to pull you back for a moment and actually want to go back for a moment because I think there's something that's kind of tangential to what you were bringing us up to date on. And that's that the story of Noose can be very inspirational, I think, for a lot of people out there who are interested in getting into the space and they, you know, they're perceiving the big giants and, you know, the massive amount of money that they're throwing at it and stuff like that. And also, you know, at the same time recently, kind of looking at, you know, the perception of

• 9:40Speaker 03

  open source taking a hit like with Llama, you know, kind of coming toward the end of its life. And, you know, Meta now not champion opening source within the big players and stuff like that. So could you, could you kind of lay out for a moment, like a little bit of a combo? Like, how do you see open source working in the modern AI world? And how has, and as you guys have formalized into this organization, you know, from that informal network and you're, you're having to make choices and you have this North Star, which is keep everything open, but also, I mean, you have, you have bills to pay, you have paychecks to make

• 10:21Speaker 03

  and, and all those kinds of things. Can you talk a little bit about how, you know, not only you guys see it, but in general philosophically, what's, how do people navigate that space? If you're looking at Noose as, as kind of the paragon to pursue and say, hey, I can go do that to, to some degree, how do you see that? What's the role of open and what's the role of being a company now?

• 10:45Speaker 02

  Yeah. Well, I could say there's kind of the, the inside baseball, you know, version of open source is like what's actually happening in the industry. And it has shifted several times over, over the last few years. So, you know, we start out with You know, the the the the golden age, your llama comes out, right? And you have this, you know, you have one of the fabulous five companies or whatever, you know, saying that they're gonna, you know, do open source AI. It was driven largely by Zuckerberg's personal, um, you know, I wouldn't say emotional motivations, but like, he just decided he wanted to do it. And like, you know, he's, you know, he's in charge of the company. So that's what was gonna happen, right? And the the fact of the matter was, though, is this created an ecosystem of people who were able to research AI.

• 11:29Speaker 02

  And every, you know, ton of the researchers now at places started out by downloading llama and and stuff like that. So it really was quite, quite important at bootstrapping the AI researcher space that we have right now. But as we saw, as he released Lama one, Lama two, Lama three, um, you know, the the price tag of that kept going up. And with Lama four, they made some, you know, decisions that were, you know, architectural decisions within the model, seemingly minor thing at the time, you know, could have gone one way or the other. But they made a few mistakes and the model really didn't come out that well. And, you know, they had to look down at themselves and say, we just spent 200 million, 300 million,

• 12:11Speaker 02

  400 million dollars on like essentially a paperweight, right? And so that's kind of where I think, you know, that the question really became, everything's fun and good when everything's working, right? Like, and I think that first failure case sort of, you know, made people question, what are the motivations for having open source models, right? So and one thing you have in a great American, you have one of the largest American companies sort of have a a come to Jesus moment about why, why, why are we spending our money on this for? I was aligned with our business objectives. And then you have the deep seek sort of situation, which happens, right? Where you have this Chinese company drop a model that's, you know, was trained and is was at the time nearly soda equivalent, come out of nowhere.

• 12:54Speaker 02

  And now you have this, now it goes from being a dollars game within the Western AI space to having a geopolitical underpinning to it as well. And it always was gonna get here, but like, it was forced through there. And you now have open source squarely within. You know, the vectors of this geopolitical, of this geopolitical thing. It wasn't just that there was a closed model provider out of China that, you know, was Sota. It was that we had an open source one that was, you know, that was near Sota coming out of China. And then now this playbook started to get replicated with throughout China as sort of a growth hack mechanism. Right? So within China, they realized that if you could put out an open source model, you could, you know, you could get your company, you know, to the top and get it in the press.

• 13:37Speaker 02

  So insofar as in America, it was sort of realized that this was played out and wasn't going to be profitable. As that, you know, fizzled out over in China, the, it still was quite profitable in the sense to throw your money into open source models with the hopes that it sort of elevated you to this, you know, top tier of, you know, players in the game and we'll figure out the money stuff later. And, you know, for different various reasons that may, may or may not work differently over in China than it, than it comes over here. But the functional difference was that all of the open source was now coming exclusively, you know, our miles are coming exclusively out of China. And so that's sort of the inside baseball and then, and that's more or less where we stand right now,

• 14:18Speaker 02

  except for what I would call a very significant recent development, which is Nvidia and Jensen. So Nvidia and Jensen at his last GTC keynote came out and said, you know, we are going to be the, we're going to try to carry the financial flag of Western open source models. And he committed something like $20 billion over the next several years, you know, towards training open source model, Western provenance, open source models. And I think this is an interesting development because if you sort of pull the threads of the sweater about, who does it really make sense for someone to be training an open source model? You know, I think Nvidia is a company where you could actually credibly make that argument, that it does make sense for them, you know?

• 15:03Speaker 02

  It's because, you know, at the end of the day, They're all running on Nvidia, you know, whether it happens, it all ends up running on Nvidia chips. And more things that need to run on Nvidia chips, you know. So for them, it is like aligned with their business interests. And anything where you can't sort of eventually really see how it's aligned in the business interest, those things will always kind of follow the money, right? Like that'll tell you, show me incentive, I'll show you your outcome. So I think Nvidia doing that kind of, it is a potential game changer, at least on the Western side. Because it's the full, they're really the only people that has it. Because it's kind of, you know, you and Nvidia, you win a bit, you win a bit. But guess what? The house always wins and Nvidia gets to be like the house here. So on the inside baseball thing, I think there are some interesting developments right now. And I'm very, I'm currently very, you know, enthusiastic or optimistic about where it actually will, will go. At least in the short term, right?

• 15:48Speaker 02

  You know, we can't predict anything out several, several years out. So that's sort of kind of like the inside baseball story. The sort of larger question about how do, how does someone fit into, you know, the new story? Is it replicable? Who are you as a person in this space? I mean, I would say now that there's never been a time more where a single person's leverage can be more, can be, you know, multiplied or maximized. AI is a technology, is a, is a human capability multiplier. And, and I'll give you, like, this is a crystal example. And it's really like, and it is really Hermes agent itself. So Hermes agent was developed by, was first developed internally at News by a guy named Technium. He's, you guys might know who he is.

• 16:32Speaker 02

  He's on Twitter all the time. Technium is not a developer in the sense that he didn't, doesn't like really know code that much. Wouldn't have previous to this, sat down and been able to write huge, like a program that would run from scratch, you know? And, and so, you know, previously he would have been unable to make an application, right?

• 16:59Speaker 02

  But with the current AI tools, he was able to architect and write and build an application that is now the number one open source repository on GitHub. You know what I mean? And so that goes to show you that if you have the vision and the drive and the care, this technology can make you 1,000x on what you are. So there's never been a time more where a few people can have outsized impact on the industry, on the world, than it is right now. And so don't think that the opportunity in any way has passed you by. I think it's really, we're only at the very... Every industry is ripe. Every industry, every vertical is ripe for someone who has laser-focused vision

• 17:44Speaker 02

  uses these tools to completely take over and win. So I think the area is still, the grass is still green.

• 17:53Speaker 01

  Wow, it seems like we need to make an update to our website all the time. Our marketing team needs a new landing page, or we've got something really cool in our product that we need to create a new section of our website. All of this needs to happen fast, and I can't wait days or weeks for these things to go live. That's why I'm so impressed with what our partner Framer is doing. They're an enterprise-grade, no-code website builder used by teams at companies like Perplexity and Miro to move faster. Framer has a built-in, robust CMS with everything that you need for great SEO or even A/B testing. And changes to your website go live in seconds, not days or weeks. And so if you're launching a new website

• 18:38Speaker 01

  or you need a new landing page or you need to migrate your full.com, Framer might be for you. Learn how you can get more out of your .com from a Framer specialist or get started building for free today at framer.com-practicalai for 30% off a Framer Pro annual plan. That's framer.com-practicalai for 30% off. Framer.com-practicalai. Rules and restrictions may apply.

• 19:10Speaker 01

  I'm wondering, now we've kind of shifted into this discussion about agents and Hermes Agent, I'm wondering about your perspective, Jeff, on kind of, it seems like we've seen this shift around in initial, initially with AI, everyone was like, what model are you accessing, right? What model are you using?

• 19:32Speaker 02

  Yep.

• 19:32Speaker 01

  I'm going to put in an input and get an out and output from a model, so I need to choose a model. And now everybody's talking about agents or agentic systems. Some of that is obviously kind of jargon and marketing in the market, but also there is a fundamental architectural thing that's happening, which you mentioned agent harnesses and kind of this way that these applications can operate over a distributed system of things, or have all these connections that matter to tools and take action and maintain state. And we saw with, for example, when we looked into, you know, things that people were using all the time, like Claude Code and that sort of thing, like the importance of that agent

• 20:14Speaker 01

  harness, which is also, of course, like a big part of that Hermes Agent project. I'm wondering if you could kind of help me and our listeners understand, like, what is the importance of the model now in these types of agentic systems? And how, and how does that shift in this world where, you know, is the, is the important part in a lot of the, you know, potential value IP, however you see that in this kind of harness, and the model is just sort of something you can swap in and out? Or what is the importance of the model within that world?

• 20:53Speaker 02

  Yeah. So here's a, here's an analogy that's not perfect, but I'm, as I'm finding it to be instructive. So- Um, the, the, the model is the brain, the harness is your body. Think about like that inside yourself. So, um, you know, the, the, the brain was something we previously couldn't build before. You know, like that is like the true quote unquote magic of AI is still like within the model. It's all within there. That's the zero to one thing that allows any of this to happen. We could build robot bodies before they couldn't do anything kind of deal, you know? So, but that, that's really it, right? So the model is your brain and the harness is the body. So let's go on this analogy a little bit more, right? So suppose you are, um, you know, you have an IQ of 150, you know, but you're an invalid.

• 21:37Speaker 02

  You're stuck in a wheelchair, right? That will succinctly limit the amount of things, of things you can affect in the world, right? You can try and go talk to someone and tell them to do it, but like you are, there's some amount of limit that you have. And let's imagine in fact that like most of the work you want to do needs to somehow touch the, the world in itself. You'd be limited in that aspect in some capacities. Meanwhile, if you had someone who had an IQ of 95, but has an athlete's body, you know, there's certain more things that they're able to do just by virtue of being able to manipulate the world more, right? So both sides are like important and I think they exist within a sliding scale. A better harness with a worse model can beat a better model with a worse harness. And both of them are symbiotic and working with each other.

• 22:20Speaker 02

  And it's just that the, the harness itself though, is the thing that touches ultimately what it is that we humans care about, which is the, the, the world in which we live in, this, this thing that we call reality around us, right? The model itself has very little ability to touch the world. All it can do is output tokens, right? And we need to somehow allow those tokens, and we don't have speech, I think, but we need to allow that output to become instantiated into the world around us. And we ourselves are instantiated in a world where we have persistence, where we have causality, where time moves forward in a direction. And, and so all of these pieces, the harness sort of allows the, the, the model to exist within the reality that we all care about.

• 23:03Speaker 02

  Now, as far as like ownership of, you know, where's the value accrue or all that, those sorts of questions? I don't want to get ahead of my horse here and like make some sort of like, you know, Silicon Valley pronouncement about, oh, I, you know, this is where all the money goes or something like that. I would phrase it rather in a different way. I would say we are getting to the point where people will want to pay for outcomes, right? Just as in when I hire an employee. I am paying him to do a job, right? And ultimately, I want that job to be done. Otherwise, I wouldn't have hired that employee, right? Like, the prime motivating factor for me is in getting some sort of material, economically valuable outcome to be done, or something I view as economically valuable.

• 23:48Speaker 02

  And so I think that is also the similar model that will eventually pull out of this whole AI system, which is that these systems will be paid to do certain things, and they'll be valued insofar as they get the job done. Now, who owns the harness? Who owns the model? All of that will kind of get worked out in the end. But again, if you pull back and say, where's, what's the prime motivating factor? It's, I want to pay for something to get done in this world, and it would be cheaper, it's cheaper, faster, you know, more, more cost effective for me to do it this way than to do it any other way. And that's water going downhill. Follow that path that'll take you, that'll take you to the promised land.

• 24:25Speaker 01

  Well, Jeff, I, I love that analogy about the brain and the body and the harness and the model. I think that will be really helpful for people. I'm wondering now, in terms of Hermes Agent specifically, could, could you kind of, I guess, walk us through some of the agentic or automation stuff that you were seeing kind of out there as, as you all were starting to, starting to develop Hermes Agent? And some of the, like, key opinionated choices that you made about what you want Hermes Agent to be uniquely in, in the midst of kind of all of these other, other things out there?

• 25:06Speaker 02

  Yep. And, and really, the, the key piece of it was the idea that Hermes, the, the agent ought to get better the more you use it. That was kind of like the, the motivating factor here. And that's, you know, maybe different than how people used to design software. So we've, we've always been trying to like, break out of like, The paradigm is different. We have to act like the paradigm is different, right? And so how did people used to design software? They would say, I think I know a problem. I think I can design the best solution for that problem, right? And they're gonna like, you know, whiteboard it all out and have all these systems. And we said, well, we don't have like, but we don't have to be like that anymore. The ARs are smart enough to just see what we do and then figure out what they, what they should be, be doing. The idea, and so what we said is just get out of the way of the model.

• 25:48Speaker 02

  Let like, give the model the ability to do what we, what we want it to do. And then you lean on it as much as possible. So a couple of the opinionated decisions was we created a very limited number of sort of bundled in hardcoded features. We gave it the minimum sort of ability to touch the world, to run code jobs, to, um, to browse the web and stuff like that. And then everything after that is an emergent property that is encouraged to develop through the prompts. And that is, the two main ones are sort of the, the, the memory system and the skill system. The skill system is extremely interesting to me because it is the thing that the first time it work, it happens to you.

• 26:33Speaker 02

  It feels like magic, um, which is that you use the agent, you're trying to solve some problem. It does something for you in the way you like it. And it notices without you telling it that this is like, I've done, I've, I've learned, there's something important here. There's something important here. And it will create a, a skill that says how to do a specific thing. And then the next time you do something that's sort of like that, it will just use what it figured out before on how to do it. So I have this, I have an example of this. So like, we were, our, our team was like going to, uh, uh, an offsite. And we were like flying in and I was like, I want, I want to see if I can get Hurry's agent to like, make a restaurant reservation for me on the flight. Right? So I'm on my flight, I'm doing it. And there's actually a bunch of stuff on these websites to keep automated systems from doing this for you.

• 27:17Speaker 02

  There's all these like bot captives and stuff like that, like to try to do that. And it's like going around, it's like, okay, it's not working. It's not, I'm getting blocked out. And eventually it actually does find like the API backend for like how they're, they can book it. It's like, oh, I see all the things here. And it was like, okay, I found the data. I put, which one do you want? Book it. And this took about actually like 30 or 45 minutes of real agent runtime to do this, right? And then at the end of it, it goes, oh, wow. Yeah, I learned all these things. And you just see skill created like Las Vegas restaurant booking, right? And then the next day I can, and it knows how to do it now. The next day I come back, I go, hey, that we, dinner was great last night. Can you book this other one? Boom, instantly it knows exactly how to do it. It just takes those learnings and applies it, right?

• 27:58Speaker 02

  And, and sort of that, rather than being like, we need to design all these different skills or stuff like to. Just let the model, you know, it's encouraged through self-reflection. So internally in the prompts, we're like, we, we, we have, uh, at News, we have a couple of like, who I would consider to be like the world's best, uh, like LLM, like they're like LLM whispers. Like they truly just talk to them all day and they just know the right words and phrasing. Karen being number one in the world, I would say, in my, in my opinion. And, uh, and so they, you know, we put in the prompts to like nudging to have that right self-reflection. Be like, when you see things being used all the time, or if it feels to you that some, you know, important achievement has been, has been met,

• 28:40Speaker 02

  that would be useful to you in the future, make note of it and put it in your skills system. And that's all we really do. And then though, like I said about getting out of the way of the model, we let it use its judgment about what it thinks is important, you know? And we just encourage it to do that. So we sort of give it the guidelines of what, not, not, not how to solve the problem, but how to think about how to, you know, how, how to think about how to think kind of deal. And then, um, and then just, you know, let the model go. So that was in the skills system. And that was sort of like our first opinionated one was just like, let the model drive it. And then the second one was, was, was the memory system as well, which is sort of this, we have this like hierarchical memory system where it, it will create, um, notes about you, about how it seems, feels like you want to be treated.

• 29:24Speaker 02

  And then it has like a, a layer of the previous sessions that it's talked to you about that it can go through. And there's like this many layer memory system that, that we have as well. But all of it is, um, mainly. Operated through the LLM's own discretion about when to activate any of those pieces. And what it means though is that like when you know, GPT 24, you know, when the next GPT or the next OPUS comes out or the next anything, Hermes agent's just better, like it's just, it has better judgment. I'm using those things too, you know, but it just kind of drops in and gets better. So, yeah.

• 29:56Speaker 03

  So, so it sounds really cool. Um, as you're, as you are talking about this and people are listening right now to the podcast, can you position it a little bit like, so one of the things that have hit people is there's, there are, you know, a lot of harnesses have come out over the last few months. Some are proprietary, some are open source and, and they, they have some different capabilities. There's a lot of overlap. How would you position Hermes for like both the users and like the context architecturally or, you know, like cloud versus, like there's a whole bunch of different like this or that or this or that. How like, when you guys are, are working on this and trying to get it out there for

• 30:41Speaker 03

  the world, what are some of those use cases and specific audiences that you're seeing it being really well suited for compared to the competition that they, that other people may be looking at and stuff? Could you talk a little bit about that? Like its market fit?

• 30:54Speaker 02

  Yep. It's primary market fit first is through your sort of power user person who wants to use AI, you know, to its full capability. Um, that was sort of the first segment that we, we, we aimed at. Um, and like I said, it's, why, why use it? It's the agent that gets better as you use it more. That's the best tag I can, I can, we can come up with and try it. Um, so if you want something that just works and gets better as it just works more, Hermes agent is the agent for you. Um, and it is open source native in the sense that we keep everything open. Um, you can run it locally using local models if you want. That's a first class citizen for us. Um, and, or you can have us host it for you as well. Um, and wherever you sort of fit on your, you know, kind of like,

• 31:36Speaker 02

  you know, line there is where, is, is, is where we are. Um, we feel pretty good about where the story is right now on that and, and the, and the broad product market fit on that. And we're currently working now on really expanding out, what does it mean to have an agent, a Hermes, something like Hermes agent? In a workplace setting or like a collaborative setting. I think like the sort of one agent, one person model is currently like pretty, we're pretty happy with where it is now. And now we're sort of exploring the multi-tenant. How does, how does it fit to have lots of these things work together on that? And we have a couple of really high level partners that we're working with right now that we don't have anything to announce quite yet. But that is sort of where our, our brain is going to right now.

• 32:20Speaker 02

  And we are ourselves sort of are, are dog fooding this a hundred percent. So A Hermes agents written 99.99% by Hermes agent. But we also have several Hermes agents deployed within our organization. Doing real quote unquote like work to sort of, you know, to, to be the first people to figure out this sort of enterprisey, or at least like organizational story. And it's, it's really powerful. I'll give you, I'll give you an example. So we have a, we have one of our, the agents whose job it is, it's connected via MCP to all of our backend infrastructure for all of our servers. And it can get access to the databases and it's like read only, but it can like see everything that's happening. And we've used it as a, it started out as like a debugging tool.

• 33:01Speaker 02

  Where if it costs, someone comes to us and they say, oh, this isn't working on the website, so on and so forth. And these systems on the backend, they're kind of spaghetti. You have your databases versus Versal versus all these different, you know, you know, provide, you know, to get it all going. So it's kind of like, it's a little bit of a mess with all these different services. And, you know, we started saying, hey, can you figure out what these problems are? We're seeing 500, 500 is on this sort of thing. And our, our, our engineers who actually know this are talking to the agent and it, it's, oh, I can't find this. I'll go look here. And what's actually happened is over the course of like a month, it has built up a huge repertoire of skills about how to actually do everything that we need within the company. So now someone who's like our support person, who's in like our Discord or like a same email,

• 33:45Speaker 02

  can just come to that agent, ask now about like a specific customer account. And it can do all of the things that we need to do and give you all the reports and do root causing. And that wasn't something that was, that we had to code ourselves. It just emergently got created as the, as the engineers used it. But the difference is now that that one engineer had to use it once, had to show it kind of once, work through it once. And sort of passively, the agent was just got better and better and better. And now like our whole organization can leverage that, the learnings from that, that one engineer. So we're trying to work out that story too. And we think it's quite, quite powerful and interesting. And so that's kind of where we're taking it from, from here.

• 34:24Speaker 01

  If you've been listening to the show over the past few months, you realize just how transformative agentic AI is, whether that's Claude Code, or Hermes Agent, or custom-built software that you're deploying for operational efficiencies, or as new products to your customers. Regardless of your maturity now, this is the world that we're headed towards, this agentic AI world. And there's a lot of security and governance teams that aren't letting these agents go into production because of risks related to agency and autonomy, and how do you take care of things like prompt injections or insecure tool usage? There's a lot to take care of, and that's why I'm personally spending my time

• 35:09Speaker 01

  outside of the show, working with an amazing team of AI engineers to build Prediction Guard. Prediction Guard is an AI control plane that you run in your own infrastructure, behind your firewall. Developers can build on top of this control plane using everything that they want to use: OpenAI and Anthropic-compatible APIs, MCP servers, frameworks like LangChain. But all of this is plugged into a built-in governance harness that enforces your organization's AI policies. And all of that telemetry goes back to your monitoring and alerting systems. I'd encourage you to check out what we're doing at predictionguard.com-practicalai. You can schedule a demo with me and the team,

• 35:53Speaker 01

  and I'd love to get your feedback on what we're doing. So, visit us at predictionguard.com-practicalai. That's predictionguard.com-practicalai.

• 36:06Speaker 01

  I have an interesting, well, I guess, anything I ask in a podcast, I hope, is interesting. But in my mind, this is a particularly interesting thing to think about, which is, Chris and I have talked about this on the show a lot, which is, the way that you should maybe automate things or mechanize things is often different from the corresponding human process, or it should be... You shouldn't assume kind of a one to one

• 36:35Speaker 02

  Agree, yeah.

• 36:36Speaker 01

  Mapping. And I'm wondering like on both sides of this, because you're finding like the agent is developing those skills. If you've actually learned from how those skills are developed, maybe how to do things better like as humans within the company? And maybe on the on the on the flip side of that, you know, what what is what is the, I guess, the create, some of the creative ways that you've seen agents solve things that might be totally different from the way that a human would go about the problem, but it works because you've kind of fully bought into this agentic process,

• 37:19Speaker 01

  which I think are people are gradually learning through like agentic coding tools. There there are some of these like sacred cows that they just have to get rid of, right? Like, it doesn't matter if this function is duplicated a couple of places, like the agentic system, like it's fine for the agentic system. I don't need to think about that. So are there are there cases of that that have come up for you?

• 37:38Speaker 02

  Well, I would say like as far as like a guiding principle about what, where to think about what to automate and when.

• 37:46Speaker 02

  Think of the agents as humans with infinite patience. And I think this is really kind of like like infinite patience, but very low creativity. All right. And so the question is, where would I need that? Right. And and if there's a place in your workflow that doesn't require creativity, but requires infinite patience, then that's a great place to put it. And so for something like I said, with our our log system, any human theoretically could just read all the logs, right? And like step through all of them and like, but no one has the patience to do that. Right. And no one has the long context memory to like see it all at once. Right. So those sorts of areas. And if you have to do it all the time, so you know, like that, that's really the areas to think about. What you don't want to be doing is sort of like you said,

• 38:30Speaker 02

  this one to one mapping of like, oh, we need a CEO agent. We need a CFO agent like that is that is, you know, the wrong thinking. And you need to blow those kinds of ideas out. Rather, you need to think of them like an operationalistic perspective of what is the thing actually doing? And would a human ever really not could a human do this, but not really want to do it? And those sorts of workloads are the best to be put through. So that's where we start out here is anything that like theoretically could be done by a person who isn't like. A genius and super creative, but we just doesn't make sense to. As far as, you know, solving things and what things we're learning in a different way. I mean, through the coding thing, I, let me put it this way. I started coding when I was like seven or eight years old, right?

• 39:16Speaker 02

  It was the thing that made me different when I was growing up. I could do this cool thing. It opened every pathway in my life and all my success in my life has been rooted at the basic, at the idea that I could, was a really good coder at some, at this very specific point in time. You know, I was born in the late eighties. You know, I got to be there right as the internet started coming on, you know, you know, at the time when software was starting to eat the world for real. And I was young at that time, you know, like all these things that lined up. And I did create a whole bunch of, you know, in my mind, up until only like six months ago, I didn't use AI really at all. I wrote all my code myself and I thought I'm still better than all the AIs. Like they can't do what I do. And then really like in the last three to six months through using Hermes agent,

• 39:59Speaker 02

  I had to, I had to, you know, I had to admit that the time, that that time has come and gone.

• 40:05Speaker 02

  But rather than being disappointed about that, I would say it only means that I get to run the clock back and be early again, like I was when I was young, when there was like the, you know, software was eating the world. Like, so it actually is freeing in some way, if you're willing to allow it to be an opportunity. So, and to get back, you know, specifically to your question about learning things, so you do differently. Yeah, I would just say that like anything that is aesthetic, is based in the aesthetics, the AIs haven't, they have no, they have no discernment for that. They don't care if it's pretty, they don't, and like, and it's not even that they don't care. It actually is what I'm finding is that, you know, they really don't know.

• 40:50Speaker 02

  Like, they really don't have human taste. And they're incredibly smart in the vector of like what we can, what you and I would consider to be a genius person who would, you know, we try to self-select through to get someone into Stanford and like, what is that that makes a person a genius? They can do that easy aces, maids, like solve math problems, write code like, you know, you know, we needed to win the genetic lottery to do that. They can, they can do it right out of the box. But what they can't do, and what's something that like almost every human can do, is really discern, have an innate sense of aesthetic that because, and I think the reason for that is just simply because our human sense of aesthetic is grounded in the lived experience that all of us share is common, as common, you know,

• 41:34Speaker 02

  as common men and women on this planet. And AIs, if you think about how they were trained, they're just so divorced from the experience that you and I went through, you know, from being born, living in time, growing, and even our biology, from the evolutionary pressures that created us in the first place. And so our aesthetic is actually something that is quite unique and is quite very like, there could be a million different ideas. Animals have different ideas of what's aesthetically important in their pack structure. Like, you know, different, there's a million one of those. There's only one math, really. And there's only one like science, you know, like, so like, it's interesting that like, the things that are like the universal computational stuff the AIs can take,

• 42:16Speaker 02

  the things that are very unique to us, that's things that, but to us don't feel unique because it's the fish and water argument, right? Like, we don't feel them to be a unique thread because it's, we're so immersed in it. And it's only when we're sort of faced with this thing that's, that was finally, we have another example, there was only us to begin with. There's now another example that we look at it and go, oh, why is this so different? You could think about it about slop or whatever you want to call it. But getting back to what you said, they will solve things in an aesthetically unpleasing way. And you just kind of have to learn to deal with that. And you should not rely on them, at least right now, for those things that are grounded with, whose success is grounded within it being, you know, aesthetically pleasing to a human, whatever that means.

• 42:57Speaker 03

  Yeah, there's. I got a, I want a comment that to agree with you on something you said a moment ago. And then I want to actually draw out a thread that you've gone down a little bit. The comment is, I think, something I say a lot is the models regress to the mean. So they do things that may appear creative, but they don't do truly novel things. They have to have something, you know, that they've been trained on that's relative to that, that they can associate. And so if I'm going and doing something that's truly novel, there's nothing written that it could be trained on before that. They're usually not very useful in that way. Having said that, that still leaves 99.9999% of the usage out there.

• 43:41Speaker 03

  And one of the things I've noticed, not only in our conversation today, but in previous conversations that we've had on the show and privately, is that we are retraining ourselves in, you know, if you have the capability here of a Hermes agent. And what harnesses can do, and then some of the things that you guys have done to make Hermes so amazing. And what it does in terms of learning skills, they, you know, we tend to go to the common use case about coding. And the fact that we're, you know, Daniel pointed out that maybe keeping just one version of a function, you know, like, you know, we all grew up, don't do, don't have one, keep everything really, really lean and all that. But that's really for us humans.

• 44:24Speaker 03

  And you pointed out that we have so much more capability now, though it may not be aesthetically pleasing. And it may require a different way of doing that. As people use a tool like Hermes Agent, how should they be thinking about, and let's stay away from coding for a moment and look at the rest of the world of work activities that might be out there. How should they be looking for those opportunities to do it better in a way that they've never thought about before, because it's no longer human centric, but it's now agent and model centric together in terms of what they're doing? How do you optimize the use of a tool like Hermes Agent if you're the human trying to retrain yourself?

• 45:04Speaker 02

  Yeah, I mean, number one would be, you know, don't tell it how to do something. Describe the outcomes and the conditions for what it is that you're trying to get to. And like I said, or a little bit earlier about like getting out of the way of the model in some ways, I think people, when they first start out using these things, they have an element of control they want to keep on it, you know, they're like, they want to say, okay, do this one step, do this one step, do this one step. The models are only going to get better and better and better at long horizon planning. And I think ultimately think being goal oriented and then being goal oriented and then evaluation oriented, right? Like, what would be the conditions upon which I would think that this goal was met, right? And if you can succinctly

• 45:47Speaker 02

  describe those, that's what the AI agent can work towards. Let it work towards, you know, fulfilling those success criteria. Now, if you leave those success criteria as unstated, you know, let me give you, like you say, write something, and then you go, well, this is slop, you know, this is, you know, not X, not but Y, not X but Y, all of the paragraphs the same length. Okay, but you told the AI to write something, and it did write something, you know, it doesn't have the judgment that like, it should not sound like slop, because it thinks slop is the best thing that, you know, it's the mean average of every word that's ever been written, you know, and it thinks it's great. So it's like your unspoken assumptions or your unspoken evaluation of the outcome, if left unspoken, can remain, you know, will remain

• 46:29Speaker 02

  persistent. So that's why, like I said about the real value, we have these like LLM whispers who can really articulate all of the suppositions that they have internally about what they want it to be in a succinct way. Now, humans, that is its own skill set, right? Like, knowing how to actively, actually communicate everything that you want and think and say is not something that we normally do, because A, we have the shared history of human common understanding that I just don't have to say it to you, because you and me feel the same way on most things that I don't have to say it. And therefore, it's so ingrained, I don't know how to like, put it all into words, right? But I think, you know, taking a step back, and you know, instead of thinking like, explain it to me like I'm five, explain it to me like I'm an alien, you know, or, you know, because that's really what the AI is. It's an alien

• 47:14Speaker 02

  that never grew up on Earth. So you really have to say what it is that you want in a way that's much more explicit. But if you are able to say what you want explicitly, and really write out your evaluation criteria about what you would, what would, all you would go into your own judgments, make it, it can, it'll find its way. It'll find its way towards that goal.

• 47:33Speaker 01

  And as we kind of draw things to a close here, I think I'm I'm excited by the possibility moving forward. Like you say, it's kind of a time where we can look at a lot with fresh eyes and experience some of that newness, even though we've been working in in technology for a long time. We always like to ask our guests kind of at the end, like, what is on your mind as you're stepping forward into the next, it could be a few months or year of your your life, like, what's at the top of your mind? What do you go to bed thinking about, both either on an exciting level, on a challenge level, on an ecosystem level, however you want to, however you want to frame that? We would love to, love to hear it.

• 48:17Speaker 02

  Yeah. What I'm, you know, I have the business answer, which is, you know, making news research continue to grow through our enterprise offerings that we're working on, blah, blah, blah. I think about that a lot. It takes a lot of my time. But something a little more over, overreaching would be, you know, thinking about what the place for someone, you know, what the place of people are in work in the next years to come. And not even only from just like an economic standpoint, but from like a humanity standpoint, using these tools, what will it do to us, you know? What will it do to us? I think that there will be, there's going to be a, you know, it already is, society has already moved towards sort of a, you know, doom scroll-y kind of tick, that tick

• 49:01Speaker 02

  tocky, like, that is, that's already like the direction we're on. And this could in some ways be one more domino on that, that effect. Because now we can sort of check out of think, check out of thinking as well, right? And if your, if your job is just telling the agent, do the thing, do the thing, do the thing, and just keep saying that over and over, like, what does that say for, for your growth as a person? You know, at News, we call ourselves being human centric AI, and that AI should make you better today than yesterday and better tomorrow than today. I think we're in that path right now, but it also requires some responsible usage by the people, by the, by the users of it. And I wonder in myself, like, what, for someone, someone could easily get trapped into, you

• 49:46Speaker 02

  know, developing no critical thinking for themselves. And, and And especially if you take this 10, 20 years from now, what do you take for someone who only, only ever grew up with this being the paradigm, right? That, that like human innovation and thought and critical thinking was just not, you don't even see it. Like, like the answer is the computer knows. And that's all the only answer there ever could have been. Cause you know, it only takes one generation. Like, once you grow up, whatever you grew up with is what you think is normal and right, you know? And so, um, I had a baby five days ago, you know? And, uh, and you know, what it means for her, you know, growing up to live in that. So that would be sort of the bigger things that are on my mind right now. But ultimately, you know, you can take that one of two ways. You can be pessimistic and be worried about it, or you can have agency.

• 50:29Speaker 02

  You can have agency and be part of the world and, and try to be part of the solution. So that's why news, that's why news research exists. That's what I'm trying to do is to be a part of the solution. And like I said, better yesterday, today, better today than tomorrow.

• 50:41Speaker 01

  Awesome. Great, great way to end it. And also, uh, congratulations. Uh, and thanks for, thanks for joining us on the show. We, we do hope to have you back. Maybe, maybe someone from news in less than two years, uh, coming back on the show. We'll, we'll try to make that happen, uh, next time. So thanks for joining us. We'll talk to you soon, Jeff.

• 51:00Speaker 02

  Really appreciate it. Thanks. Bye.

• 51:07Speaker 00

  All right. That's our show for this week. If you haven't checked out our website, head to practicalai.fm and be sure to connect with us on LinkedIn, X or Blue Sky. You'll see us posting insights related to the latest AI developments and we would love for you to join the conversation. Thanks to our partner Prediction Guard for providing operational support for the show. Check them out at predictionguard.com. Also, thanks to Breakmaster Cylinder for the beats and to you for listening. That's all for now, but you'll hear from us again next week.