Algorithms + Data Structures = Programs - Episode 292: GPU MODE, PLs, Post AGI, Wingspan & Lawn Care

Episode Date: June 26, 2026

In this episode, Conor and Bryce chat about GPU MODE, programming languages, post AGI, Wingspan, lawn care and more!Link to Episode 292 on WebsiteDiscuss this episode, leave a comment, or ask a question (on GitHub)SocialsADSP: The Podcast: TwitterConor Hoekstra: LinkTree / BioBryce Adelstein Lelbach: TwitterShow NotesDate Recorded: 2026-06-10Date Released: 2026-06-26creduceautoresearchGPU ModeParrotNVIDIA CUDA TilecuTile PythonTritonJeri EllsworthCppCast Episode 218: Commodore 64 and Tilt Five AR (with Jeri Ellsworth)Intro Song InfoMiss You by Sarah Jansen https://soundcloud.com/sarahjansenmusicCreative Commons — Attribution 3.0 Unported — CC BY 3.0Free Download / Stream: http://bit.ly/l-miss-youMusic promoted by Audio Library https://youtu.be/iYYxnasvfx8

And this is like a whole new field of agentic engineering. And, you know, people have been doing programming languages for a long time. It's a lot more matured. And I feel like there's a lot more to learn and discover here in the world of agentic engineering. And like how agentic engineering impacts our programming languages, our compilers, our tooling. Like that I'm very interested in. You know, I don't have answers yet for how agentic engineering impacts programming languages. I think I'm starting to see how it will impact, you know, tools, compilers, et cetera.

But I don't yet know how it impacts programming languages. Welcome to ADSP, the podcast, episode 292 recorded on June 10, 2006. My name is Connor, and today with my co-host, Bryce, we chat about GPU mode. Are programming languages still important? Post-AGI, Wingspan, lawn care, and more. Well, so I think the biggest, a colleague said to me the other day regarding out of research that like 90% of your effort should go into preventing cheating and reward hacking. And I think that's more or less right. You know, back in the day, there was this tool called C Reduce before AI.

And C Reduce is this thing where you'd give it like C source and then you'd give it a test. And you'd use it for like reducing a compiler error. Like let's say that you had like an internal computer. compiler error that you hit with some, you know, code base with GCC. And so you would, you would, like, create a pre-processed header of that, like, or you'd create a pre-processed source file of from the code base. It'd be like 500,000 lines of code. And you'd give it to C-Reduce. And then what C-Reduce would do is it would go in and it would apply a bunch of these code transformations, like, you know, like remove all the comments and, like, you know, try removing, you know, this function and then this function and try renaming variables, etc.

trying to minimize the reproducer of your error message. And the biggest challenge with writing good C-reducers is the test script. So if you gave it a crappy test script, like, you know, you give it a test script, you're like, okay, just like, you know, the way that you test whether it still reproduces is just run GCC on this file and then like grep for the error message. Okay, well, if you do that, then it's going to give you back something that'll reproduce your error message. But there will be a dozen other error messages, too. And the rest of the code will be ill-formed. And so it's like, okay, so what we really want is that this is a valid reduction, a valid minimization if the code continues to produce the error message with GCC, but it also

compiles fine with cling. And then like, okay, then now it will only give you a minimizer where the code is valid C++, but it happens to break with GCC. And then there were like other things where like if you were, if you did something subtly the wrong way and like a reducer, like it would just reduce your source file down to like being like an empty file. And it's like, hey, this, this passes your test. It passes your test. So, you know, this is a valid reduction. And so like whenever I would run into a compiler error, I would go and like carefully craft this test script to test whether the bugs still reproduced. And then I would just like put it into C-Reduce and wait a few hours.

And it's the same thing with AI. It's the same exact process with AI that the, in particular with these auto-researchentic, you know, loop sort of workloads. Ours is more what you and I are doing is truly more of what I would call auto-research, which is something where it is iteratively following some form of a scientific process where it's trying something, then testing whether that's whether it works, then evaluating a metric, and then deciding whether to keep it or revert it. But anyways, the biggest and most important thing is the quality of your tests and your validation,

because if there are exploitable holes, it will go after those. And in particular, if you're doing something like optimization or, you know, even if it's not optimization, even if it's not performance, if it's just like correctness, like, if you're testing for like three cases and there's like some other cases that your test don't cover, like, yeah, it's going to write code for those three cases. It's not going to care about the other cases. It's going to break stuff for the other cases. And yeah, it's a challenging art and science. I wish I could say more, but I don't think I can talk too much more about the techniques. Only matter of time. Only matter of time.

Should we try and talk about some non-AI stuff for 30 minutes? What do you think? Is there stuff that we... How's the... How's the kid coming along? The kid's good. Do we know a boy or girl? Yeah, it's a boy.

Do we have names yet? We have a couple contenders. You know, I have a top name. Shema has a top name. I think both are... I think if she convinced Shima to just let the Internet decide from the set of top names. No, no, that's never going to happen.

And, yeah, baby's good. I'm in the middle of reading. I'm on my third parenting book and see how many I get through in the next two and a half months. I'd say probably I'll stop at like somewhere between 10 and 15. Not that that's necessary, but, you know,

it doesn't take me too long to crush audiobooks. And I'm learning a lot, folks. There's a lot of academic literature out there about how, to raise a baby. Olivia, who we both know and who was at NVIDIA for a long time, when our other buddy, J.F, was about to have his first kid. I was at the Sipas was committee meeting in Ulu, which was 2016.

That was my first international trip, my second committee meeting. So I'd met Olivier and J.F. at the previous meeting, and we had to quickly become quickest thieves. And so we're at, we're in Ulu in the middle of, you know, the sort of middle part of Finland. And JF's talking about, you know, like, becoming a father soon. And Olivier tells him, like, listen, we can talk about parenting philosophy now. But as soon as you have a kid, it will become impossible for us to talk about it.

Because once you have a kid, you develop your own, like, very deeply held beliefs about what's the correct way to parent. And there's like no point in us talking about it after that, because you'll have your worldview I'll have my worldview, and they may not align. All right. Well, stay tuned to whether or not that turns out to be true for me. I mean, I don't think that's really going to be the case. I always think that, like, if you're the kind of person that's worried, if you're, well, it probably doesn't apply all the time, but if you're worried, like, oh, am I being a good parent, blah, blah, blah, that art.

Hey, we just took. What? It's just one sort. Wow, that's actually, it one. One sort by a good bit. Nice. Okay. All right.

So out of GPU mode leaderboard, I'm now the number one for sort, vector sum, prefix sum, histogram, gray scale, number two for convolution. And I haven't tried Matt Mueller vector ed yet. I'm sorry, you were saying things. Yeah, yeah. On the B200, there's multiple GPUs. No, no, no. Look at the H-100.

I think I've already taken more slots on H-100 and on a number. L4. And interestingly... The sort you don't have it. Not H100. I don't think I've done sort on H100 yet. Like histogram, I'm pretty sure I now have all of them on histogram, which is the one I started with.

Yeah, I have all of them on histogram. It's a shame that you didn't choose a shorter username, like B. Lelback, because on mobile, it cuts off the gold emoji. Yeah. So the interesting thing, on the GPU mode, there's different, you know, leaderboards for each GPU type. and initially I did not instruct the model to only submit to the GPU type that it had locally. So all of my agents run on GPU nodes so that they can do local testing and evaluation.

And what happened is, you know, the models love to quit, you know, when the going gets tough, they love to give up. But they've got this directive to never quit. And so like once it feels like, well, I can't really make any more progress on an L4 GPU, it would start to take. taking its kernel for L4 and just submitting it to the other GPU types and would like get wins there. So I thought that was pretty funny. I have not run on A100 yet. I'm saving the A100 slots for a particular setup that will use Nemotron. And I want to be able to evaluate how well it does before I have all of the slots.

The only reason I haven't gone after Matmole and Vectarad is I don't think that they're particularly interesting problems. because the speed of light answer is going to be pretty clear for both of them. But I don't know. Maybe I'll be wrong on that. Oh, man, I'm very happy with that sort result. Because that one, that sort one, was running with Deep Seek V4. And so that's the first time that I've gotten really good results out of Deep Seek V4 Pro. I'm very happy with that. That's really very encouraging for my future inference bills being substantially lower.

Six out of eight. You only got two to go. Yeah. So we couldn't do it, folks. do it. We tried to talk about not AI, but we ended up talking about it. Yeah. I don't, what was I even saying? For years time. I don't know. Something about parenting. I don't know. When I'm editing this before, I'll realize that I was mid-thought, and unfortunately, the listener will never get to know the end of it. I mean, what else has happened? You said you were at some conference, the singularity conference? Yeah, I was at that. I was at Go-Sim. I was the one in Paris, right? Yeah, yeah. Do you

of their conferences coming up. Do we have programming language stuff to talk about? Programming languages. I don't know that I care about programming languages anymore, Connor. Honestly. I don't know that I care about programming languages. All right. Maybe that's what the title of this episode will be.

Programming languages, do they matter? Or like, do programming languages matter anymore? Question mark. Go, Bryce. Talk for 20 minutes and round this episode out. I mean, yeah, I'm sure they're still matter. I do think they still matter and are still important. But like agentic engineering just feels like a higher priority thing for me right now.

Because, like, again, my mandate and mission is how do people program parallel platforms, specifically in Viti's parallel platform? But sort of my whole career has been around that. And like, that comes down to like, how do people get performance out of a platform? and this is like a whole new field of agentic engineering and and you know people have been doing programming languages for a long time. It's a lot more matured and I feel like there's a lot more to learn and discover here in the world of agentic engineering and like how agentic engineering impacts our programming languages, our compilers, our tooling. Like that, that I'm very interested in, you know. I don't have answers yet for how agentic engineering impacts programming language.

languages. I think I'm starting to see how it will impact, you know, tools, compilers, et cetera. But I don't yet know how it impacts programming languages. Yeah. I mean, I think the one thing I will, I will posit here, and we, you and I talked about this in the past is I think there is this question of whether higher level abstractions are more token token efficient to reach good performance than lower level abstractions. If you're using something like Parrot or Kutile or Triton, can you write good performance code at a significantly lower token cost? And then can you port that code to a new architecture at a significantly lower token cost?

And I think there's a lot of people believe that to be the case. I have not seen a comprehensive study published evaluating this. And I think it'd be great work for someone to do. And you could look at it, you could look at things like all these DSLs that popped up, but you could even just evaluate it solely on programming languages. Like, I think it might be sufficient to look at like, you know, trying to write like some, some code with like C++, C, Python, and Fortran. And, you know, my guess is that, like, a language like Fortran, which has slightly, like,

higher level abstractions and you don't have to, for stuff like numerical code, you don't have to do as much low-level tweaking, but it still gets very good performance. Like, it might show very favorably there. So it'd be nice if somebody had, like, an E-L-L-L-E-L. suite or a benchmark to do these sorts of evaluations. There probably is something out there like this. I just don't know about it. But those are the sorts of questions that I think are interesting is like how token efficient is our existing languages. Because I don't think we have enough information yet to know how we should evolve programming languages to be more token efficient and agent friendly. And I do think

the two are linked together. I think that like if you if you optimize your thing for token efficiency, you are implicitly making it more agent-friendly. Because what's the most token inefficient thing? Well, if the agent uses your thing and gets a compilation error or gets a tool failure because it was unclear how to use your thing or there were ambiguities or your thing was hard to use, well, that's going to waste a bunch of tokens. So if you just minimize token usage, if that's just your objective function, then you'll make your thing more agent-friendly. we should just put a loop around that put a loop around that

yeah just like okay that's that's going to be my new answer for anybody who tells me how do I make my thing more agent friendly I'm just going to say make some eval that uses your thing and then just put an agenic loop around it that's minimizing

that subjective function is minimize the number of tokens to achieve this task yeah I guess you got to isolate though to make sure that like each time you're launching your like prompts like you're going to run into like cashing and you know context bleeding that could like affect things right i don't think across session you have to worry about cashing yeah okay maybe if you don't

have to worry about that i'm pretty sure sessions will be isolated yeah i'm pretty sure i'm pretty sure i mean i could be wrong about that but i'm pretty sure the sessions are isolated if not i'm sure there's a way that you can't isolate. We didn't even talk about Rust. So Rust would be the other language to throw in the gauntlet there because Rust has a lot of guardrails on it. So it catches a lot of like errors at compile time because it has this current Rect by construction model. So like the interesting Eval would be like, okay, if you give an agent the same task and ask you do it in Rust versus C+++, does it complete it in fewer tokens? because in Rust, it's just harder to write bad code.

The answer's probably. Again, I just haven't, like, I haven't seen the study in front of me proving that. Yeah. You work in research. You should go do that. There's already enough people working on Rust, and to be honest... No, no, no, but it's not about Rust.

It's what I'm saying is somebody should evaluate the agent readiness of programming languages. I mean, that's adjacent to kind of some of the... stuff that I'm working on. I'm working on more of like the abstraction layer, like level that you're targeting. Like not dissimilar to when you said Fortran versus, you know, C++ versus Python. But my more thing is like you could even do the same thing within a single language, right? Like, you know, some high level thing like parrot, then thrust, then cub, then just rock coot of C++. Yeah, yeah. Or just in general, like, yeah, like if something... And I think that's a really interesting point that maybe I'm conflating abstraction level with programming language here.

I do think that the abstraction level part is the more important question than the specifics of a programming language. I mean, maybe they are to some degree orthogonal, but what I was really asking about was abstraction level. And the thing is, in any language, like, I'm not too familiar with Fortran, but like even Python, you can, like, you know, open up the hood of the car and start doing some crazy stuff with basically, like, see APIs within Python. And my main thing is like which one of these layers if you're targeting is going to result in like the best outcomes. And I have my own personal theories. But that's, yeah, that's the direction. It just, what you were saying, though, makes me just think, yeah, like, I don't know. Where do you, where do you think like five years, ten years from now?

Where does this all end? Like, I listened to an interview with Boris Churney. And it was, he got asked, you know, what happens when we're post-AGI? And I won't, I won't say his answer, but. There's always, there's always going to be AI doctors. We're always going to need AI doctors. That's what you think it is. Yeah.

Yeah. No, I mean, I think if we think about the state of models today, there's a couple different paradigm shifts that I can imagine happening. One is moving more of thinking and reasoning to happen in the latent space within the model itself. My understanding is that today most of the reasoning works by model generates an output and then takes that back in as an input instead of this all happening within the latent space. So you hear a lot about the idea of looped transformers and people claiming that maybe mythos is that. But, like, I think that is a thing that is, you know, likely to be a big paradigm shift that'll have big impacts. It's not as, not something I would expect to impact the agentic engineering part too much.

Although, if the reasoning happens within the latent space, then it's going to be less visible to us than it is today. I mean, it's already probable, the thing that you see that's, that are called, like, thinking traces or reasoning traces are already, like, kind of a lie because it's, It's not really the reasoning trace, it's not really like the internal process. It's just sort of like the model, like generating for you its idea of what the internal process would be. Anyways, the other thing is around like memory.

So there's all these various systems from memory today, a lot of which kind of boil down to like, we have some series of markdown files somewhere. And I think that there's like a lot of room for more first class memory systems, for memory, longer term memory of being more of a first class part of the LLN. But there's an engineering problem here too, which is how do you, like, manage and build reliable systems that have this self-evolving memory? So almost all of the agenic workflows that I'm doing are running on ephemeral VMs.

So the agent might run for two or three or four days or even a week, but then like I'm going to shut down that VMs. So any like information or learning or anything that I take out of that, I'm going to put into skills. I'm going to put into my harness, my tools, et cetera. I'm not running like, you know, I come from the HPC world. I never run stuff on my laptop. I have like a 10-year-old laptop because my laptop's just a thin client because start of my career, I never ran anything on my laptop anyways. My laptop is just an SSH terminal to some node somewhere.

And so I've always sort of had a very different mindset than other developers. is I've never been somebody who's built stuff locally. I'm always doing it somewhere in the cloud. And so I'm never running an agent locally on my laptop. And that means that I've always had to think about, you know, what data needs to be persisted. I think a lot of people end up, you know, sort of building like an agent that has a personality over time that has memories, longer term memories, etc., that has, you know, all of these things that sort of allow them to customize it. For me, I have a lot less of that because anything I do like that,

I need to, like, embed into my skills or my config. But, like, in the future, obviously, you know, agents that know and learn about you over time are going to be the most useful thing. Like, I recognize that. I'm not necessarily using that today, but, like, things that have their own, like, memory system, those are going to be the most useful things.

But how are we going to, like, ensure that an agent that's been like running for six months or a year and has this like complex memory system that it's built up like how are we going to ensure that that's like reliable and reproducible and like how are you going to debug that when something goes wrong? That seems like that seems like a real challenge in the future. I think we're moving more and more towards a world of like these like always on, always running agents.

Maybe in the future we'll even have agents that are basically like essentially always like reasoning or inferring. You know, I mean, I don't know, maybe we're there already today. A lot of these loops tend to be moving from, like, you know, inference to sort of like waiting to, like, doing tool calls. But maybe, like, AGI means, like, a system where it's basically, like, always thinking. And I just, I think it's going to be very interesting to make those things coherent. And I think going from tasks that run for days to weeks to tasks or agents that, like, run for, like, months to years is going to be a very hard problem. in part because, like, how do we simulate and test an agent that runs for, like, months to years?

I don't know. That seems challenging. This may be the end of, like, reliability in the software space. Yeah, I always think about, you know, the fact that if you think about 30 years ago, you know, the internet is just, like, beginning. And now where we all, like, carry supercomputers and blah, blah, blah, and there's social, networks and just like in 30 years the technology landscape has changed so much that it's like impossible to be able to predict like 30 years from now.

But I do think about like the Iron Man scene and the first Iron Man that came out where he's like building his suit with like a holographic projection where he's like exploding out all the pieces and then grabbing a piece and twisting it and blah blah. And I think about that applied to like. mechanistic and interpretability where it's going to be like visual like a visual version of like mechanistic interp where you get to go into some like you know 3D holographic you're going to put on some you know futuristic version of the apple vision pro and then you're going to be able to go in and look at some version of a three-dimensional knowledge graph that some AI system is built and like there will be a way

to interpret like its knowledge store or knowledge garden or whatever you want to call it. And that is going to be so freaking cool. And like that, I think that, like, that could be a form of programming in the future, right? Like if you've got some system that's hill climbing on a bunch of, whether it's Kuda kernels or whatever your thing is, and then you can go in and come up with a visual, like, representation of the different improvements and ways that it found its way. Like, like, have you seen the Carpathies thing about, like, knowledge bases and building knowledge bases from a couple months ago? No. Is it a talk or?

I don't know. It may have been a tweet. I get all my information tweets on what's going on in AI. But I think it was very similar. It's this idea of like, you know, maybe the next step is like how do we how do we have agents like compile and orchestrate like knowledge? Like a lot of like creation of like, like, today a lot of like creation of skills is still largely like driven by like humans and like the creation and organization of skills. And we create and organize skills like of a scale that like humans can go in like look and review through. And maybe in the future we have these like knowledge bases that are like curated and prepared by models. Maybe that are viewable for humans, but also that are, you know, these basis of knowledge that the models can use for their future work. Yeah. It's just, I don't know. I don't know how. I understand there's concerns, et cetera, but I just, I'm so excited. Like, I mean, there's another, there's another thing that just popped into my head is I, at one point when we were talking to Sean Parent about her name.

name was, I think Jesse, let me look it up right now. Or is it Terry? Actually, I have this as a potential future guest. If I just go to ADSP and I scroll down, it will say Jerry. So what did I say? I said Jesse

and then Terry. It is Jerry Ellsworth and she's the individual behind a holographic-esque kind of board game tool. And I know even as far back on some CPPCast episode, So they were talking about like Dungeons and Dragons and, like, augmented reality version of that.

But like, literally like a real world example today is Shima and I, we love this game, Wingspan. We're both birders. We like board games. Wingspan is a bird. I, too, have played this game. Yeah, it's a bird-flavored game. With Olivier and his kids actually. Interesting.

Yeah, it's a great game. I have a bunch of the expansions. But sometimes it's a very point-sality. Requires like five minutes of prep to set up. And because there's so many components, eggs, et cetera, food. It's a little bit irritating to, like, keep track of everything and, like, guaranteed one out of every two games, like, we, one of us doesn't have, like, the number of turn

cubes, like, in the right order, and we have to figure out who, who didn't put a turn cube in the right place. We also, on boardgame arena.com, play there sometimes, but it's without the expansions. And sometimes if we just, we don't have the energy to set up the physical board game, even though we prefer doing that, we'll just go and we'll play. she'll come to my office she'll plan her laptop i'll play on my computer and i would love a basically like combination of the two where you have the expansions but then also like have the augmented reality version or even better like it's it's like the star wars you know monster fighting game

where they always play at the table and they've got the holographic monsters i would love to not even be able to have to put on augmented reality glasses and just have some like little you know discs that you put at the corner of your your dining table or wherever you're playing and poof, you've got the holographic version. So you're still playing in person the best way to do board games. But you don't need to do all of the point tracking and the point totaling and the moving of eggs. And oh, did you actually pay the two eggs that you were required to play in order to play, you know, the king rail as your fourth bird in your wetland?

And like, how that wouldn't, and, you know, some people probably are being like, oh, you're ruining. Like, it's nice to have a tech. Yeah, you're, there's so many, there's so many people who are going to be so upset at the words. Yeah, but like, I'm just like saying that that would be amazing. And, and also, too, like on the digital version on board game arena, you can play with a couple different settings because there's a few birds that are known as the O.P. O.P. for those that don't know the lingo is overpowered. And the two Ravens, the kill deer, Franklin's goal, and then the wood duck are considered. The wood duck's kind of like a tier two opi bird.

But you can, when you're playing competitive, which I never do, but you can enter tournaments and stuff, they remove those birds because they're, considered such an unfair advantage when you get them. And like, you can imagine like, oh, like, let's play like a different version. You can like, you'll be able to talk to some model and say, we're actually, can we play a variant of this game? And you just explain the rule change. And then it'll incorporate it. And you can like, you're going to come up with a different version of Scrabble and a different version of chess or checkers. Or like, you know, maybe you're playing with your kid and you want to have like a, you know, a handicap. Is that the right? Am I allowed to say that? All right, whatever.

Well, I apologize. If that's the wrong term to say in 2026. I don't think that that's the right term. Whatever the right term is, I don't mean to be offensive. But like, if you want to make it so that it's more competitive when you're playing with your kid in the future, and so you put some, you know, head start. You give your kid a head start or you double the points, you know, that your kid is getting. And then, you know, you can even, you could even, I was just thinking, well, isn't it valuable for your kid to be adding up the scores and,

and doing the math, him or herself. And it's like, well, you talk to the modeling. You say, you know what? We'd actually like to score ourselves. So give him a little scratch pad where he can draw it with his finger and do the 10 plus 12. But if he ever makes a mistake or she makes a mistake, give a little like corrective thing and say, oh, you know, you made a classic mistake. You didn't carry the one. Blah, blah, blah.

Amazing. Amazing. Look at you. I just like, I'm spitting off ideas here. This is, this is gold here. You know, I should start an augmented reality. board game. Well, you've just broadcast the idea to all your listeners. But if you want to invest in Conner's idea. The thing is I'm sure there's like 14 different companies, including Jerry, I know,

was working on stuff like this. But like, I don't really have the energy or the time to do any of this stuff because I'm happy at Nvidia doing the work that I'm doing. But I just, I can't wait until this stuff comes out because it's guaranteed it's going to exist in the next 30 years or something like this. It is like the last six months have been probably my best. some of my best times at Nvidia. And like, yeah, this stuff is just so exciting and fun. Yeah. I don't think I've been quite so excited about the day-to-day engineering tasks

since the start of my career. Yeah. And like, you know, I'm sure there's some people that are thinking, blah, blah, blah, blah, terrible for the world. It's not all terrible, folks. I have become a lawn, what do you call? A lawn enthusiast, you know? My Kentucky Blue Graveller.

grass, grass, front and backyard. How do I know that? Thanks to AI. You just send it photos and you say, listen, grade my lawn. I got a D-plus. We got lots of creeping Charlie. We got lots of clover. And my wife and I are environmentally conscious, so we're not using any pesticides.

It's going to be a lot more work. We got to use the... This is the Connor equivalent of Bryce's couch stuff. Yeah, well, yeah. I mean, everyone, yeah, maybe you're going to be the furniture guy and I'm going to be the lawn care guy. Because honestly, I remember my dad. My dad built a table. from some wood planks that lived on my grandfather and my grandmother's farm in Terrace, BC.

Rest in peace to both of them. But they had a wonderful farm and they had these wood planks. My dad took them. We drove him eight hours to Prince George where I grew up. He built this, like, beautiful table. And, like, he spent so many weeks slash months. And every single time he would sit down, he would, like, rub his hand on it to, like, look at, like, the quality. Was it smooth enough?

That we need to put, like, another layer of liqueur or whatever they call it on, a lacquer? and we would all, me and my three sisters would always make fun of them, like, because he's always, like, we'd sit down to eat and what is he doing? He's, ah, you know, this table, you know, maybe got to do some stuff. I have now become my father because every day I basically walk out, especially if it's rained, and I am like assessing, you know, oh, did the iron kill enough of the, uh, the creeping Charlie or the clover or whatever. And it is like, it brings me so much joy. And also, we have a skunk. We named him Wilbur. And we had to have a discussion, Chima and I about whether we were going to get.

rid of the grubs that are living beneath our grass because it is the lunch buffet and dinner buffet for Wilbur the skunk who comes and just digs up these little holes and feeds himself and Shima said that she was very happy that our lawn was the skunk's lunch and dinner so we're just going to leave let Wilbur tear up the lawn but anyways I have to go around and like fill in these little holes that Wilbur keeps on digging in our front and back lawn and like all of this is thanks to AI I didn't care before and then And I was like, you know what, I bet AI could tell me how to like, you know, improve the quality of my lawn. And sure enough, it's... I'm going to buy you a chair so you can go yell at the kids and say, get off my lawn. No, no, no, no. The kids want to play on my lawn. They can play on my lawn.

Anyways, the point is, it's not all bad, folks. If you, you know, give it a chance, it'll make you fall in love with your lawn as well. Be sure to check these show notes, either in your podcast app or at ADSP thepodcast.com for links to anything we mentioned in today's episode, as well as a link. to a get-up discussion where you can leave thoughts, comments, and questions. Thanks for listening. We hope you enjoyed and have a great day. Low quality, high quantity.

That is the tagline of our podcast. It's not the tagline. Our tagline is chaos with sprinkles of information.