Episode 276: Mini AI / Cursor Update (+ Running)

0:00Conor:I I work more now because it is intoxicating what you were able to do with this stuff. Which is kind of like uh I've heard on podcasts being like, wasn't we, wasn't this supposed to free us from work? And it's like, this is not work. I am I am Harry Potter with the Elder, the Elder One. Welcome to ADSP the podcast, episode 276, recorded on February 26, 2026. My name is Connor, and today with my co-host Bryce, we give a mini update on our AI and cursor usage as well as chat about running and more.

0:44Bryce:Oh, I I I bought running shoes, by the way. I did buy running shoes. It is better. You were correct that I needed to own running shoes if you're gonna run.

0:52Conor:This guy's saying his knees hurt while he's running or whatever, and I'm like, well, what kind of running shoes are you running? And he's like, Oh, do I need running shoes? I'm just like, yes, you need running. I guess maybe I should I'm I'm being, what's the word, elitist about running knowledge. Maybe it's not a well-known fact. If you are having knee troubles, shin troubles, and you're trying to get into running, especially if you are above the age, we'll just call it 30.

1:13Conor:I'm not saying if you anything about people over 30, just when you're young, it doesn't really matter. The older you get, the more important it is. You need a decent pair of running shoes. The more cushion, the better for protecting joints and stuff. And if you've had a pair for like four years, you probably need a new pair. I get a new pair every like 600 kilometers. I won't say how frequently that is, but uh it's it's pretty frequent. Because you want to be able to exercise and walk for a long time.

1:39Conor:We may not be thinking about it in our 30s, but at some point when we get to 60s, 70s, 80s, you're gonna start to have joint problems. And the better the shoes, the longer your joints are gonna work for.

1:49Bryce:So I we we we did not end up doing the 5K on Valentine's Day because Ramona was very sick and it was very cold, and I could not I could not make the sale on going through with it. But uh, we are going to sign up for some other 5K. But I had I stopped running for a little bit after the first snowstorm in New York, and it's been hard for me to get back into it. Part of the problem is it's been too cold for Ramona to come running with me, and I am not as motivated to run when my girlfriend is not there to embarrass me by running a lot faster than me.

2:22Bryce:So I keep telling her, you need to come back and start running with me again because it will be better for me if like you are there to force me to keep going.

2:33Conor:You just gotta you gotta run enough until you get addicted to it. I have a I have a race on Sunday called the Chili Half Marathon, which I've run twice before, and it's usually been right above freezing, you know, zero degrees for Canadians, 32 for Americans, or I should say Canadians and the rest of the world.

2:51Bryce:Yeah.

2:52Conor:And this Sunday, it's supposed to be minus 12 feels like minus 18, which is gotta be like potentially below zero for Fahrenheit folks. And I'm very unexcited about it, but you sign up for it, you gotta do it. Only one time in my race have I ever missed a race, and it's because I was deathly ill because my nephew Franklin gave me some virus which made it impossible to leave bed for like a couple days.

3:17Bryce:One of the big factors in us canceling was a misperception about the timing that I only realized at the last minute, which is Ramona's been taking these uh acting and then these speech classes, and she has one on Saturday. And we signed up for the race, and they said like the starting time was like at 8 a.m. And I'm like, all right, that's great. Like 8 a.m., 30, like a 5K will take like, you know, like 30 minutes, you know, tops for us. So then we'll be done and she'll have time to get to her class at noon.

3:45Bryce:And then I realized that they don't probably don't have all the people start at the same time. And we, the like very inexperienced runners, are probably not starting in the first group, which is probably the like professional or very fast runners who have run a lot before. So we probably would not, it would like not have been uh possible for us to have done that, anyways, probably.

4:06Conor:Yeah, that makes sense. Well, I look forward to your future race, your future times. Yes. I'm glad you got running shoes.

4:13Bryce:I I have a I have a question for you, a a technical question, not related to our the other stuff we have going on, which is have you started playing around with clawed code at all yet?

4:26Conor:No. Although we can chat about this. I'm gonna cut it into the next episode, folks, because there's a lot of here's so here's the preview. Bryce, because I don't have time to record for a couple hours today. Bryce and I are gonna record sometime next week, and uh that's where we got a lot of stuff. We gotta talk about Parrot, we've got to talk about Array Box. I've been dying to talk about and also in general, we gotta talk about the state. AI's back, folks.

4:51Conor:I mean, it never left, but it's it's is it back? Sure, we'll call it we'll say it's back. The topic of it is back on the podcast. It's better than ever.

4:59Bryce:Yeah, I asked this question less as like a podcast question to lead into a discussion, more as like like I just need an answer to the question.

5:06Conor:No, so the the answer is no, I have not tried claude code yet. Still, I'm still cursor-pilled.

5:12Bryce:So, so but with with cursor, the thing I'm increasingly finding with cursor is it's been a force multiplier for me, but I think it could be a lot more of a force multiplier if I didn't have to approve the commands.

5:25Conor:And so at NVIDIA, we they said I found in an email, and also too, we can actually talk about this. I mean, I I So there was an article published by Cursor that said 30,000 people at NVIDIA are daily active users of Cursor. But I was I I hit my peak rating of 168, which put me in the, I don't know, whatever, top percentage. And I've I've been really loving Cursor. And that is the main thing though, because it's a corporate, you know, version. It has a lot of safety restrictions and a lot of that it requires us to, you know, basically approve any shell command.

6:03Bryce:But they changed it recently so that you can now do allow all.

6:06Conor:So they they changed it back in January saying that they were rolling out an auto, you know, approve for a list of things. I have not been able to get that to work.

6:15Bryce:Wait, I I thought so I thought that there were three modes. I thought the modes were I thought the modes in our version were that there was approve every command, there was allow, there was like auto-approve with allow with an allow list where you can enter in like commands that are okay, and that then there was like an uh like just always auto-approve like full YOLO mode.

6:34Conor:Yeah, we don't have the YOLO mode. We have to I thought that we had it.

6:37Bryce:No, I think you're right.

6:38Conor:They're rolling out the allow list, and the allow list is gonna contain most of what you need over time.

6:43Bryce:So here's here's my thing. I increasingly find because like what I like I I tell it to start, and then you know, I usually try to go in context list to do some other task. I have not yet set it up to to be doing like multiple chats at a time. Or sorry. I sometimes cursor or cloud code.

7:03Conor:With cursor. Sometimes with cursor. Cursor, it's just by default. You don't have to set anything up.

7:07Bryce:No, no, no. But like like I would need to like set up like Git work trees or something. If I want to have like, if I want to do two tasks that might touch the same files and I spin that up in like two separate chats.

7:16Conor:Oh, you want you want multiple agents working on different tasks, not multiple agents working on a single task to get you the best response as fast as possible.

7:24Bryce:No, because like the responses that I do get are generally like good enough. Like I don't need more power for each individual request.

7:32Conor:You're not pushing it. You're not pushing it hard enough, Bryce.

7:35Bryce:Um I guess I guess maybe I do need it. I guess, but no, maybe that's not true. Because if it did take if I got better responses or if it took less time, that would accelerate me too. But but it almost certainly the thing that's increasingly getting me is the like command approval. And part of it's because one of the things I've been doing a lot has been working on our like educational content and on like the basically the DevOps setup for that, which I think is a little bit more like command-oriented.

8:04Bryce:It's not just like purely writing code, it's like write some code and then like go and test something. So I really want to be able to give it a task and then like let it go and do its own thing. What I've heard is that Claude Code has some sort of sandboxing mode where it will go and run its thing in a sandbox, and like as a sandbox, it doesn't have network access, so it has like limited damage that it can do. I'm scared of the allow list, I guess, because I I think even with the allow list, I would feel uncomfortable like working on the production code base on a machine where like I could mess things up.

8:42Bryce:I I thought maybe about just like setting up a containerized environment and then in the containerized environment running running a cursor where like it doesn't have access to anything that can touch the corporate net. But yeah, I was wondering if you tried it yet. I think I'm gonna try to set it up like sometime next week because I've got a big backlog of stuff I gotta do. I think if I can have it go off and do its things on its own and then come back to me with like a full PR I can look at.

9:12Bryce:I think that'll be better. The other thing, and I'm gonna have to show you this next week once I get it fully set up, but I've come to the determination that I think that I I I it would be very challenging to me for me for me to go work at anywhere else that's not NVIDIA, because I'm increasingly starting to believe that NVIDIA has the best access to AI tools to use for our day-to-day work. Yeah, I I I think this was maybe not true three or six months ago, but you know, like that precursor blog post that went out, like I think that's indicative like about NVIDIA using cursor.

9:50Bryce:I think that's indicative of like a change here. And I think there's some pretty interesting tooling that we're like now dog fooding and playing around with. And uh like it's funny to me how like how now it's become like a job, like a requirement for me in any job I would go to would be that I would have to be able to have access to like AI coding tools. And you know, you and I, I think have never really worried much about the budget for our token usage.

10:18Bryce:And I think that that's in part because we're at a a big company and at specifically NVIDIA, where our business is the token generation. But I think that other people, you know, who are not here or who are paying for themselves for their tokens, you know, are a lot more constrained by that.

10:35Conor:Yeah, I well, we have to wrap this up. And this is technically already not airing till next week. But uh yeah, I've got so much to say. Yes, I agree. I mean, I'm not going anywhere. I love working for NVIDIA. Obviously, it's an amazing company to work for right now. If there are if I were to leave, there's only two companies I would consider leaving to. One's Anthropic and one's Any Sphere, the company that makes Cursor. No. For basically the same reasons that you said.

10:59Conor:Like, I am now I'm trying to completely re-architect the way that I think about everything. Like me too. And this this we'll talk about this more like next week. But literally and and Shima is to thank for this, my wife. Because I've been building all this stuff, like Array Box, dashboards behind a Ray Box. I have another website that and and like I'm writing a book that's built on top of a Ray Box. I'm building a whole other platform built on top of uh a Ray Box, and then I have a whole other things that I'm gonna build.

11:30Conor:And I was whining about D script and these AI podcast editing tools, and I was just like, they're all just garbage. Like, and she I was whining about it to her, and she hears me like nonstop, ad nauseum, saying how amazing these tools are, and she sees what I'm doing with it, and she's just like, I she understands why like I I work more now because it is intoxicating what you were able to do with this stuff, uh, which is kind of like uh I've heard on podcasts being like, wasn't we wasn't this supposed to free us from work?

12:00Conor:And it's like this is not work. I am I am Harry Potter with the elder, the elder wand. I don't know. Anyways, there's some wand, it's like the the ultimate wand. That's what it feels like. And I was whining about this stuff, and she's like, Why don't you just go build your own podcast uh podcast editor? Because like I want to be in the world, like I spend so many hours a week on like content creation of just like removing ums, cleaning up audio tracks, like you know, all this stuff.

12:23Conor:And like AI will be able to do it all at one point. I still want creative control of when I insert like tracks from some, you know, a movie or song or whatever, or some uh, you know, advertisement. And I was just like, well, it's it's a pretty tall task to like replace Audacity, the features that I want from it. But then I was thinking and I was like, well, I do why why can't I do it? Five hours later, I have this like minimal thing, and and now like I'm I've realized that I have complaints about everything, like the podcast players that I use.

12:51Conor:Like, like anyway, so I I just realized like I I have the ability to build the world, and I'm just gonna go build it. It literally is just the time in the day that I need in order and and and people are like, Why why would you go create your own podcast player? I spend more time editing and listening to podcasts than any person I know, and I have a very, very good like intuition for like good design and like we always whine about it.

13:14Bryce:Like most importantly, like you spend a lot of time doing the editing, so why not automate it?

13:18Conor:Exactly. And and the the other thing is even just consuming podcasts, like there are so many complaints that I have, and like you know, super simple ideas. First of all, no no ads at all in the podcast player. I don't want to make money off of this thing. I wanted this for myself, so it's a better experience. Second thing, so that's it's no ads, but what if we could do better? What if I could use AI to skip automatically skip the ads for me? In the in the daily, it's 30 seconds at the beginning, 60 seconds in the middle, sometimes you know, 15 seconds at the end before the other things you need to know.

13:48Conor:In other podcasts, it's like you know, eight minutes at the beginning of the podcast, but 10 seconds at the end.

13:53Bryce:If this takes off, you're gonna get cancelled by all the podcast creators who are gonna be like, hey, you take in my revenue.

13:59Conor:No, I it's you know what? We've got ad blockers on on Chrome, and you know, I'm already skipping the ads myself manually. Yeah, just like I and that's the thing, is like I I know, I know that's why I know the daily has 30 seconds of ad at the beginning, 60 in the middle, and like I have my podcast player set up. You can customize like the skip ahead 30, skip back 10. Like, like, anyways, and and and also too, like there's just in the podcast player that I use Castbox, it's so awful.

14:26Conor:It's got all these community features, it's got all these like top podcasts. And and and the thing is, I want to switch to Spotify, they don't have a cue. How do what podcast player in there anyway?

14:35Bryce:It's like I I use podcast addict and it's like okay, because I'm on Android, and it's like okay, but not yeah, like like a lot of the same problems I have.

14:44Conor:None of them are good. And Shima was saying that even I was playing around with her Apple podcast because she's on an iPhone, and she was like, Oh, I've got so many complaints. The same thing that happens on Castbox is like after a certain number of days, if you haven't listened to it, it like removes it from your device. They separate downloaded episodes versus the anyways. The point being, there's a whole episode we have to have on like, you know, just being like an idea guy.

15:05Conor:Like, I have had so many ideas for so many years that I just didn't have the time or the the knowledge to like go and implement. Like why I I would never go create my own podcast player, like uh app. But now, like you could probably do that in a day on a weekend.

15:20Bryce:Like the the the idea person thing is why I I think I need to prioritize getting like the sandboxing set up because I've had this big I was just going through my to-do list and I had this big backlog of like things that like I know I know the scope of the project, I know exactly how to describe what needs to be done, and if like if if a draft of it is presented to me, I can I can direct it to the finish line. I just like but I have like 20 of these things.

15:46Bryce:I can't if the way that I'm using AI is that I'm like monitoring, like you know, monitoring it doing each one of those 20 tasks serially, it's not gonna work. But if I can ha if I can go and tell it like do these 20 things, come back to me, and then spend a day reviewing those 20 things, it's a world that reward may reward people with ADHD. But anyways, I I should let you go.

16:07Conor:Oh, and I gotta, it's so sad though, though. And that's the thing. We I was supposed to stop recording 20 minutes ago, and then it's just I'm so excited to talk about this stuff. I've recorded two different clips from two different podcasts, and one of them is from the Peter Steinberger, the guy that did open claw, formerly Molt Claw, formerly Claude Bot. And oh my god, it's just it's just he's just like you get uh what's one of the quotes is a good driver can get results from any of these models.

16:35Conor:And then there was I didn't clip it, but there was a guy, the guy that is doing ghosty, Hashimoto. You know, he's he was saying that like he was talking about exactly what you're saying, is that he's very specific about which models he uses, you know, haiku, librarian, and one other one. So for the simple tasks, he delegates there. And I do the same. Anyways, there's so much stuff to talk about. Oh, we'll leave it there. Maybe maybe I will release this episode next week, and then you'll be hearing us.

17:00Conor:Well, maybe we'll anyway, I'll figure it out. It's too much stuff to talk about. You got one final thing to say?

17:05Bryce:Nothing for the podcast. Just well, okay, I guess it is for the podcast, which is we've there's two guest ideas that we've talked about in the past and that have come up, and I have on my to-do list to like think about them. And it's uh Chris Leary, who is one of the main guys behind XLE.

17:22Conor:We've already talked about him. He's JF's co-host of uh Chi.

17:25Bryce:Should we do you want do we want to reach out to him and see about scheduling a time to record with him?

17:30Conor:Not yet. Because we're gonna record a lot next week or the week after, which is gonna be like three or four episodes of content.

17:37Bryce:Schedule it out for later in the year.

17:40Conor:That's true.

17:41Bryce:And the other one would be early.

17:42Conor:I mean, if this is gonna be on the podcast, I guess he's potentially gonna find out because someone who knows him might let him know.

17:49Bryce:Yeah, the other would be to have Emily Berger on.

17:51Conor:Yeah, we could get him on as well. What happened to Carpathy? Have Carpathy on? Didn't reply to my emails. Come on, Carpathy. The path to Carpathy. Let's go. Because that's what Bryce and I were talking offline. Who knows how much of this makes it in, but about like the guests that I want to talk to. Yeah. And honestly, I was like, you know, I used to be programming Mr. Programming Languages, Mr. Algorithms. I still love that stuff, but like, let's be honest, programming languages don't matter anymore.

18:15Conor:Ideas matter. And actually, I was talking to Michael, my boss, and and he was like, no, ideas are a dime in the dozen. Insights are what matters. Insights are ideas worth keeping. And I love that quote. I love that quote. I'm gonna put it on a t-shirt. Insights are ideas.

18:28Bryce:That's a very Michael Garland quote.

18:30Conor:Yeah. And but like Ilya Suscover, Andre Carpathy, who are the other people that I mentioned? There were four people and I couldn't figure out a fifth that I I wanted to talk to. You know, Dario Amade, he's too CEO-ish. I don't want to talk to Sam Altman. I don't Oh yeah, Demas Asabis, he's definitely top three. But anyways, there was a couple others. If we could get those people on, but they're just, they're too we're not a big enough. We're top five pop percent podcast, but we're not a top point one, you know?

18:58Bryce:I think that like I think we ought to reach out to one or two people and see if we can schedule something for later in the year, because otherwise we'll just talk about guests and not actually pull them on.

19:07Conor:So here's a here's a what do you call it? ADSP ADSP promise? Is that the next time Bryce and I record after the next time, we'll have a guest. Yeah. Um might not be any of the people we just mentioned. You might not even be hearing this right now. Be sure to check these show notes either in your podcast app or at adspthepodcast.com for links to anything we mentioned in today's episode, as well as a link to a GitHub discussion where you can leave thoughts, comments, and questions.

19:29Conor:Thanks for listening. We hope you enjoyed and have a great day.

19:33Bryce:Low quality, high quality. That is the tagline of our podcast.

19:38Conor:That's not the tagline. Our tagline is chaos with sprinkles of information.