Algorithms + Data Structures = Programs - Episode 245: High on AI (Part 2)

Episode Date: August 1, 2025

In this episode, Conor and Bryce continue part 2 of their chat about AI, how it's changing the way they work and more.Link to Episode 245 on WebsiteDiscuss this episode, leave a comment, or ask a question (on GitHub)SocialsADSP: The Podcast: TwitterConor Hoekstra: Twitter | BlueSky | MastodonBryce Adelstein Lelbach: TwitterShow NotesDate Recorded: 2025-07-01Date Released: 2025-08-01AI Poll ResultsAll of Conor's Vibe Coded ProjectsCursorClaude 4C++Now 2019: Hana Dusíková “Compile Time Regular Expressions with A Deterministic Finite Automaton”GPU ModeIntro 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

I don't know. Are we an AI podcast now? No, although I will say, I have a hard time getting excited about conversations where I'm not allowed to mention AI. What does it even mean to be talking about anything, not in the context of what is going to potentially be the biggest, like, paradigm shift of our lifetimes? Do programming languages even matter now? Like, obviously they do. But, like, as someone who was a huge PL enthusiast, I now find myself caring less about language paradigms. And, like, I already kind of know a lot of that stuff, but it's just like, when I can get a program to do all the heavy lifting for me, why do I care? I want the language that's going to work best with that tool. If that's JavaScript instead of Python, I prefer JavaScript. If that's Rust instead of C++, I prefer Rust, you know?

Like, it's, sure, I used to like one language versus the other for reasons X, Y, and Z. But now that was because I was the one having to do the typing and the iterating. I'm not doing that anymore. It's the LLMs they're doing it. So it's like in a world where you are building libraries and languages, I feel like the number one thing we should care about is like how do these interact with LLMs. Like are we making it more difficult or worse? This has been, I've been making this point to a lot of people that we need to start thinking about how do we design libraries, how do we design software, how do we design docs to be consumable by alums. Welcome to ADSP, the podcast, episode 245, recorded on July 1st, 2025.

My name is Connor, and today with my co-host, Bryce, we continue part two of our two-part chat about AI, how it's changing the way we work, and more. So let's just get into another question, which is another topic, rather, which is, what are your practices and techniques for debugging issues that you have with models? And I'll give you one example of a thing that I've started doing recently, which is when I'm working with a model and it persistently disregards instructions that I've given it, I will, instead of just trying to find the right set of instructions to get it to listen to me, I will sometimes ask it to explain why it did not do what I wanted. And I found this to be very helpful. As an example, I was using, I think, perplexity and then 03 to, like, prepare like a markdown deep research type report on something. And I told it, like in my prompt, like prepare me like a markdown report, like research this topic, prepare me a markdown file on this. And in the markdown file, make sure to cite your sources. but you must cite them as markdown style links.

So the square brackets with the text, and then the prins with the URL to the thing, do not include your own citations. And the way that chat GPT and perplexity, they both have this format for citations where they have a little superscript number, like a superscript one, two, three. And you click on those and then that,

they have some UI feature where that opens up a little box that shows you the source. And I told it, like, I don't want that. I want you to cite sources. But don't put these little superscript citations in. And I also told it in the markdown file, no unicode. Because I don't want the m dashes. I don't want you to use emojis.

And also, like, I don't want you to do the superscript thing. Like, just make it like an asking markdown, like, file. Don't do anything cute. Because I find that telling it no unicode is easier than telling it don't use emojis. like the other things that it tries to do with the other like it catches a lot of things that I don't want it to do. But so I gave it those instructions and it kept giving me a markdown report where it had the citation style that it tends to use, where it would insert in what looked

like gibberish characters because it was some unicode for a superscript that I told it to do ASCII, so it just showed up as gibberish. But I could tell that it was trying to insert its own citation style. And I eventually, like I asked it like to explain why. And I think one of the models explained the reason, but then the other one I think with 03, I saw it in the reasoning trace, which is I saw part of the reasoning trace where it said, okay, the user has asked me for the citations to be in this style, but the system prompt says that all citations must be in this style. I think I'll listen to the system prompt instead of the user. And as soon as I had that information, I knew that the reason that it wasn't listening to me was because it was, it had conflicting

instructions and it was picking to follow the system instructions instead. I knew how to fix the prompt, which I just changed the prompt to I had the same instructions that I had before and I just put, listen to this instead of the system prompt. And then it did exactly what I wanted. But I could have spent an hour or two on that if I had not thought to ask it why it wasn't doing that. And I've started doing that a lot more recently because there's a lot of like rationale and instructions that it gets that aren't obvious to us and that often that explains like why it's doing weird things. And I've found that when I ask it to just tell me why it's doing weird things, it often gives me information that helps me like engineer the prompt to get it to do

what I want. Yeah, that's that's really interesting and probably useful for the listeners. I mean, I find that with Claude 4 these days, I don't really ever find it doing the stuff that was deleting unit tests or deleting some linting rule like doing not solving the problem but just getting rid of the problem it doesn't cloud four is so good these days it doesn't do that and i've never run into like colliding with the system prompt um but in general like my fixes are one you just you have to start a new chat and like that is i think the number one across podcast that i listen to it's just you have to be very fickle with these things and sometimes if it ends up in a place like i said clod four i really never have to do that but if you do just start

a new one, two switch models, I never do this anymore because, like I said, and I also don't really ever have to restart. So these are all things kind of like for Claude 3.7 and chat GPT, or not GPT, a Gemini 2.5 Pro. A lot of times with those, I would either restart new chats or switch between Gemini and Claude, but I don't do that anymore. The only thing that I would say that I do do actively is when Claude is struggling to solve my problem. like I had an iterator invalidation issue that it was not apparent that was the issue at the time that I spent like a day more than a day on and I finally realized that like what I needed to do was like understand myself what the problem really was and I had like three or four different things but I basically had to spend time narrowing it down what actually it was and so once I basically figured out that it was an iterator invalidation problem and I was pretty confident I knew where it was happening, then I gave it that information

and then it solved it in like... And so the thing is, is when it's struggling, at least at this point of time, I think it's also because you would struggle to solve this. It's like, it's not like, oh, I don't know the CSS you know, or like the HTML incantation. It's like actually

the problem that needs to be solved here is very, very tricky, which is why that whole experience added to my conviction that Rust is going to thrive versus C++ in a world like this, because the set of issues that the compiler will allow is way smaller for Rust than it is for C++. And that was part of the problem is that, like, I had a, you know, a pretty well-designed

feature on this library. But I even did think at the time I was like, this could be a little bit tricky with the way, like, we don't have a borr checker and stuff. And sure enough, it was, it was an issue. And then it ended up costing me. It's still net. I'm, like, weeks ahead of, you know, like, people will say, oh, it cost me an extra day. And I was like, yeah, okay, but it saved me weeks right now. So, like, I'm still

net way ahead of this. But yeah, my, so my, if you're using the latest, greatest models, my advice is like if you do run into a problem that it's struggling with, that's when you really have to stop just being like, solve this, solve this, solve this, solve this. You have to go and actually like do some forensic deep diving yourself. And then once you are pretty sure you know what the problem is, then come back and don't just say solve this. Say, here's what I think the problem is and here's what I think the solution is going to look like and then you can even there sometimes I really love doing this and you pointed this out in your C++ plus now talk or no C++ on C talk a while ago is you ask it to give you options you know like especially when

I'm designing stuff I'll say I kind of want some modern design like give me your top 10 options of what what you think you could do nicely well and I think that this is really important for people like I if I like give it a prompt like I start off with like a prompt and it goes in the wrong direction and like it becomes clear that I need to modify the prompt instead of like telling it to correct itself in that same chat all oftentimes just like start a new chat and like like with the corrected prompt and sometimes if I don't get like the result that I'll like all like you know I will just spin up a new chat with the same prompt. Because all the models have this temperature thing. So you're going to get slightly different responses, even if you use the same prompt. And I mean, usually I'll structure the prompt. So I'll structure the prompt to ask it to give me the top three

or like give me three or five options or something like that. There are some cases where the models are not well designed to do this. Like if you're doing image generation with like 03, which is a thing that I do somewhat frequently for like, graphics for PowerPoints. It is sometimes tricky to get it to actually, like if I want to be like, hey, like generate me like four images, like four candidate images.

Sometimes it's tricky to get it to like do that because it has like usage limits on doing things like image generation. And so sometimes it's like resistant to the idea of generating multiple images at the same time. So sometimes I'll just like spin up like. two chat windows and give it like the same prompt and just see see what I get out of that. I think it's like it's like really important to remember that there's like a random aspect to these to these models. Yeah, I think that's why like I said, the number one thing is just to restart if it's going in the wrong direction. But honestly, like I said, like the models these

days are they do not suffer, at least in my experience, using Claude 4. And that's what people say, oh, it's only slightly better. I don't think people realize how much, like the quality of life improvements that you're getting aren't necessarily in the code gen it's in the oh it's doing this thing and like it just deleted all my unit test it's like it doesn't do that anymore like that's that's a very frustrating thing that is going to scare a ton of people off like i asked it to solve a problem it like churned spent a bunch of money or like killed a bunch of trees and then like just deleted all my code at the end of the day like that's the worst experience ever and now it doesn't do that that's like unlocking a whole new set of folks um anyways you're about to say something yeah yeah yeah well

I've only just started using it because I was on the Europe tour. So I think I left for the Europe tour before it came out or right around when it came out. So I've only just started using it. But I have noticed that it seems a bit better. One thing I've been doing that I've seen a few other people do is when they're like taking like notes during like a meeting, like a one in one with something, that doing it in like a, like with a text editor that has an AI assistant can be really helpful. Like if I want to like, if I'm like chatting with somebody and I want to like brainstorm something, I'll like pop, I'll like open up a new like cursor window and I'll just start like prototyping or brainstorming the thing with them in not in the agenic mode, but in the code complete mode. And I've found that that's been a real productivity boost. I know we've talked about that we don't really, that you don't really use, I guess neither, most of us primarily, both of us primarily use the agentic mode.

the agentic mode but I have found for things like that where I'm like interacting with another person that the code complete mode can be pretty helpful I yeah I don't really I mean if the code completion is the tab completion kind of like skipping around I use that all the time I mean

I've heard people go on record saying that they're not a fan of like the agent stuff but just for the tab complete where it like it predicts where your next change is going to be and like it it, you know, oh, you made one change on this line, and you're going to make it the same change, seven places that look similar.

I know people that love that, and I love that as well. I can't say that I've ever done it for, I mean, the closest thing I've done is when I'm creating the show notes for these podcasts, I do it in Cursor. And I have to be careful, though, because I did it once, and it auto-completed the wrong link. Yeah, you got to, yeah. The killer thing that I'm waiting for

and have been asking around that NVIDIA about is we don't have Gemini turned on for our Google workspace yet and that means that like I don't have an AI assistant in Google Docs and like I spend a lot of time in Google Docs like working on like design documents or collaborating with other people at NVIDIA or coming up with plans for stuff, et cetera. And if I just, if I had Gemini or literally any model turned on in Google Docs, it would be like a 10x productivity increase for me.

Just because like today, like I have to go and take the thing from the Google Docs and I have to either put it into like chat GPT or perplexity or something like that and I don't want to do that. I just want to have, I want to be able to just have it be natively integrated with Google Docs. I mean, I also want like a, I also want cursor for PowerPoint specifically. It is, man. It is crazy how like so many times you're thinking something. you just say like the nuclear thing and the transhuman thing.

While you were saying that, I was thinking that like, oh, I should mention to Bryce that like also on the top five list of things I'm going to do with these tools is I'm not going to add it to PowerPoint. I'm planning on building my own PowerPoint that is specifically for code presentations and that like it's going to have LLM capabilities built into it. Like I showed you the Matrix landing page for my Viving Projects. Like imagine being able to create any custom animation or like graphic. or transition, you know, and then, like, you can add it to, like, oh, like, we,

we both love morph, but, like, imagine you want something specific. And then also, like, what I really want is I want to be able to add, like, my code to mark down, have the, you know, word transition, but then also, like, make sure all that code depending, even if I've got 20 languages, I want it all compiled, testing and, like, you know, syntax highlighted the exact way, because there's a bunch of these, like, JavaScript-based things. They're all terrible. PowerPoint is king.

Yeah. PowerPoint's better, and you could imagine, though, a PowerPoint-like thing powered by LLMs, man, it was... But the thing is, like, I specifically want it to be PowerPoint because I have a couple different reasons why I want to stay in PowerPoint. The first and biggest one is I don't make my slide decks in a vacuum. I interact and collaborate with a bunch of different people at the company and outside of NVIDIA, too. and oftentimes the language of interchange, the language of collaboration is through PowerPoint. So somebody else needs to use some of my PowerPoint slides in their deck or I need to use some of their PowerPoint slides in my deck, et cetera.

And if it's anything that's new that's not PowerPoint, then it makes it harder for other people to use my stuff or me to use other people's stuff. Right, that's fair, that's fair. And the second big thing for me is I think there's a reason that PowerPoint is king. and I think that PowerPoint's Layout Engine is, I guess I'll say, really good. I do think that it has some things about it that annoy me. And there are some ways in which, by Layout Engine, I mean like the PowerPoint's UI and engine for like creating like a slide and like putting things in particular places

and drawing things of particular shapes and sizes. I think it's really powerful and I think it's more flexible than a lot of the other solutions I've seen. A lot of like the JavaScript-based solutions that I've tried, I can't be I'm not as agile. Like, you know, I have a vision in my head of like,

I want the slide to look like this and it's going to have this graphic and this graphic here. And it would take me like half a day to get it done in something like Reveal.js. And I wouldn't even be able to get it to look exactly like what I want. Those tools, we are completely on the same. same page they're they're awful for what yeah and and i mean we're probably uh it's probably sickening for the listener to hear this but like you and i are like two of the best like slide deck

makers and like the stuff that we care about other people don't care about like alignments and like i think like honestly if i you're probably make the best slides of any person i know and i forget in between like seeing your talks and then i'll see a slide and i'm like oh my god like and then like my thought is like how much time and effort went into this slide and then Not that the Reveal.js presentations are bad. They still look good, but just, like, if you're looking for a certain style and, like, just level of whatever, you never get that with those things. Yeah. And you have to cut out a certain category of stuff that you want to do because it's just not possible.

It reminds me of, like, latex where, I don't know if you've ever had to use latex, like, read a paper or something. I mean, I had to use it, like, for my 100 page master, so I know a ton about it. Sometimes with latex, you just. you simply have to accept that, like, a thing, like, latex wants to make a thing look this certain way, and in theory, there might be a way to get it to do exactly what you want, but the time investment that would be required to get latex to do that, it's just, it's simply not worth it. I have been there, man.

I had, like, six custom fonts in my master's thesis, and then also, too, like, I had a paper accepted to a em workshop at one point and then they had these rules and stuff but like about like how on the the final page of citations like you need to have the same way anyways I've spent and this was pre

LLM days like days like downloading different packages and font specs and stuff like that to get to way to work the way I want it is it's awful it's awful but yes it's not worth the investment unless if you're like OCD

I do wonder to what degree, somebody could build a PowerPoint alternative that uses the PowerPoint format, because that would address many of the, like, that would address my first point of being able to interoperate with other people's decks. And I mean, I could, like, certainly I think if I sat down and thought deeply about it, I could think about ways in which I would want PowerPoint's like Engine to be, like, one thing that drives me bonkers is that if you have a table in PowerPoint, you typically, most tables cannot be grouped with other objects, which just makes it so hard and annoying to deal with, like, alignment in, like, getting things to look the way you

want. And like the way that stuff snaps to locations in PowerPoint can be a little finicky. So I certainly could imagine somebody making something that would be comparable. But I wonder whether somebody could make, like whether the PowerPoint format could be the thing that could be used so that you could open it up an actual PowerPoint or share it with somebody in PowerPoint. I don't know. I know that PowerPoint has some AI tools built in today, but they, they're, it's not like a chat mode. It's like a thing where like it just suggests slides. I want something where I can tell it like, hey, like I want like, like create for me like three, you know, circles like with this color and arranged in this format. I want to be able to tell like I have specific instructions

in mind for like, like I have a specific vision in my mind of what actions I want it to do. It's just that like doing those myself would be very repetitive and so i want to be able to tell it like hey go in like a line all 12 of these boxes you know yeah yeah it's i mean i definitely know the problem that you're thinking of and like the initial PowerPoint equivalent isn't going to have that it's going to be be mostly like a a markdown based thing yeah but my goal down the line is to evolve it into basically, like, I'm not sure if you recall Hannah's automaton version of her compile time, and she had these beautiful, like, imagine a generic,

yeah, actually, we should mention Hannah when we're talking about beautiful slide decks because that is one of the most beautiful, I mean, her, but the thing is she's building custom JavaScript, like, for her talks. Like, she basically, like, I remember she said she spent, she wrote more lines of code in JavaScript for like her presentation than she did in the actual code of the C++ she was showing and imagine like a tool like that

that's like a generic thing where you can just say I want this to be Matrix themed across the whole deck and I want you know morph transition but like I think if there's things that I've always wanted to do in PowerPoint but they're just you can you can mimic them but you can't do them perfectly like I've always wanted an animation of starting from I was born in Vancouver, BC, and then every single, because I didn't take a flight until grade nine when I went to the National Science Fair.

And so I would love to see, like, over time, like, how I flew or drove or whatever. And so you can imagine, like, I drove from Vancouver to my hometown, Prince George, and then, like, back and forth. And then at some point I went across Canada, but, like, it'd be very cool to see, like, a little car or plane that animates from place to place. But the thing is, how would you do that? In PowerPoint, the way that I would think is if you use a curved arrow and you use an animation that pans from right to left or left to right or top to bottom, depending on the direction

you're going. But that doesn't actually give you the nice linear, like on the curve. You're getting this kind of swipe motion that it does simulate it very well. But anyways, you can imagine just giving an LLM and say, hey, I need a JavaScript animation of a global map that these are the sequence of places I can. go by date and like i want you to animate this for me and it's i guarantee you what it gives you is going to be nicer than whatever you kind of scaffold together in powerpoint you know is there no way to do like um visual basic or any type of scripting in powerpoint like like uh there's actually

you can do uh you can do vb a um uh and you can you can do vb a in every single office uh you can do it in excel is where i've done it the most but i've also done it in access and uh how does how is Microsoft not have like a chat box like an agenic chat box for PowerPoint yet like does it exist and I just don't know about it I mean how is this not a thing that's a good point yeah that's a really good point if you work at Microsoft and are listening to this please yeah and send us a check when you uh I actually I was talking with with Jonathan Mueller who he worked for for think cell And they make, like, PowerPoint plugins.

And I was telling them, like, this is what y'all should be doing. Yeah, like, can you imagine, like, the themes that ship with PowerPoint, I mean, no offense, but they suck. Yeah. And, like, I don't think either you of I, I mean, when we're making decks for Invidio, we're using that one. But when we're not, I think both of us, we just kind of use, like, white or black backgrounds with text. Yeah. I'd never use a built-in theme. And that's, like, one of my top recommendations is just don't use the themes because they look tacky.

and it's so clear very quickly that, like, you just chose one of the themes. But, like, imagine you had an LLM, you just ask whatever theme. Like, that's the fun part, or one of the fun parts of these tools is, like, you're building a website, and you just say, like, I don't like the way it works. Like, and that's the wedding consolidator that I, the first one it gave me kind of looked tacky. Then I said, I want something more professional. I didn't like that. And I was like, okay, these are our wedding colors, like, add a flower emoji and something like that.

And then the last one that I was like, oh, this looks pretty good now. But it's just like you, it's like having magical. fairy dust in your hand and you just you just blow on it onto the screen and you just and it's like it's like I said this earlier in a different podcast is like that scene in inception where um uh Elliott page at the time uh you know is building the dreams and it's just like folding the world over in on itself it's just it's just crazy it's crazy that is what we have right now when it comes to like styling websites it's it's nuts well and one of the things that bothers me a bit with PowerPoint is some of the defaults are just not good.

Like, the default font sizes are too small. They should be larger. The default, like, text box, the border, or, like, the default shape, like, you just open a new presentation. The default shape, the outline is, like, too thin if you're thinking about, like, presenting it up on a screen. Like, you want, it's not, it doesn't have good defaults for, like, high contrast. And, like, another one that drives me nuts is, like, the default transition time, and I cannot figure out a way to check.

Like, the default shapes and default text boxes, you can set that per presentation. It gets stored in the theme, thankfully. And you can set the default, like, with the slide master, you can customize the default, you know, fonts and whatnot, which I always do. But you cannot, as far as I can tell, change the default transition duration, which is two seconds, which is just so long, so long. It should be, like, it should be half a second, which is what I always said it to. I have been, I've been using morph a lot more recently, and not just for, like, word morph things, but also, if you do morph right, there's this, I don't know if I've shown you this, but you can go into the arrangement box, and you can give a particular name to a set of objects, and then, like, it lets it, it allows between two different slides, it, if, you have, you have, two different things have the same name in a different slide, then they'll morph to each other.

And that has been so powerful for me. I've gone a little morph crazy in some of my decks. It's all your fault. It's all your fault. It's the best thing to happen to PowerPoint or Excel in my lifetime. Like when I used to spend hours building up animations of like individual boxes moving here and there. And then when morph happened, it was life change.

A life changing event. For someone, for people like you. me that make a lot of decks and take pride and how they look like morph is and that's the thing is it's not perfect but like you can finesse it by adding a couple morphs in between and like you first you delete a line of text and then you have a second morph so that like you don't have some word flying across the screen like yeah it's not perfect but you can definitely massage it to get it to look like the way you want and the lLMs are going to make it possible i i'm curious how if you just ask i want morph in a simple like markdown thing can it do it

Like, could an LLM add the morph transition to reveal.js? Because I think that would, it would make RevealJS like 10 times more attractive. I probably would have been using it by now. I think that there's a, I think that it's not that hard because I suspect that there's a CSS thing that, there's a CSS or JavaScript thing that's built in that more or less does this, would be my guess. You think? I would, I would, I've seen like effects like that on websites. And, yeah, that would be my guess.

I would not be shocked if that's the case. Yeah. I mean, it's been on my long list of things to do. I mean, the Kuda ecosystem dock site, that's been on my list ever since I saw your GTC talk. I finally, I wiped that one off. I've got the language one. I've got the PowerPoint one. I've got a couple other ones.

But it's just, it's, I don't know. We've got to wind this down at some point because this has probably gone like 45 minutes longer than I. I wanted to, but it's inevitable talking about this stuff. But I am really like, I implore the listener, and I'm sure Bryce does as well, you got to give these tools a fair shot. And like, it would be the equivalent if using the accounting example, VisiCalc and Lotus Notes came on the scene. And for whatever reason, you were like, oh, it's going to lead to more mistakes or it's going to be bad for whatever. It's the way that accounting is done now. You're like, Excel took over the world after Lotus Notes and VisiCalc went.

the way of the dodo. And you don't have to use an IDE for it. I mean, I don't know whether you've tried Claude Code, but everybody seems to be raving about Claude Code. It's got a command line interface. Like, there's multiple different options for how you can interface with this. If you're a command line person, there's command line tools for this, like Claude Code. There's, you know, if you want to use an IDE, there's things like cursor or, you know, insert any of the other cursor like clones. Like, there's tons of different options. Yeah. I haven't used Claude. I was talking to Asher, a co-worker about this yesterday

or two days ago. And he's up to date and has tried because we have a bunch of access to this stuff at Nvidia. And CloudCode, I think you need to jump through a couple more hoops to get it set up locally and working. And Cursor, you just sign him with your

your Nvidia email and you're good to go or your Nvidia linked GitHub email. And I've just been having so much success with Claude, Cloud 4 and Cursor. and you get access to all the models, right? So you can try them out from time to time, but Plod 4 is the latest and greatest.

I don't think Gemini has released anything. They're still on 2.5 Pro. And in general, I have found that the open-A-I models don't work as well with Cursor. They're still good, but I just mean like the amount of like a reasoning description that you get. Oh, yeah. Sometimes you don't get any reasoning trace from them at all.

Yeah. Like I think 03, you don't, or at least the last time I tried it, you don't get anything, and it still does great work, but it just, you get nothing, and it'll think for like seven minutes, and that's just not the, like, I need to know if I'm going to wait here seven minutes,

because I have had, I have had the case where you take one of these thinking models. I think it was, it had to be open AI because it didn't have any, any description or thinking. And then after seven minutes, it said, I need to run this like LS.

L.S. command locally to figure out if you have, like, a building file. And I was like, you needed seven minutes for that? Like, what are we talking about? like just ask me that up front and so um yeah i've been very happy uh but yeah i just just you got

to give these tools a shot and it's like it's for it's for you it's not like oh i'm trying to push this is the way i think things are you know it's it's a new tool that we all are not i guess do we all have access to it i guess you have to pay for it um but but i think the easiest way to get started if you if you like the easiest road to entry is to just use chat gpte if you don't want to change your development environment, if you don't want to do anything else, just like the next time you have a question about something or the next time you're wondering how a diagnostic works,

like try chat GPT. And I think that what people will find is they'll start using that more and more and then that they'll be more willing to, you know, once you see that it can be useful for answering your questions, then you're going to be more willing to try some agenic thing like cursor. yeah i would caveat saying that you're really not it's only a fraction of the power i will say though if it's especially if you're in c++ and you have some template metaprogramming uh compile time error that's what i would recommend it's like something that you're going to actually that's the problem

is those if you're an expert you probably know how to read that right away you know so it's yeah but even even if i do know how to read it it's like i always i don't even look at it i just plug it into the large language model because it'll take me longer to read it than. I don't have time for that. I have no pride. The real power though is when you

have some thing that you're trying to build or do and you've got tests and you've got a build command and a building.md and so your workflow becomes, listen, I want you to build this feature. Here's an example of a test that I want and build a few others like that

and what I want you to do is go out, build it or like write the code then build the project if there's compilation errors you know iterate until and you don't even need to explain it in this detail you just say this is my feature make sure it builds and make sure the test pass and then when you're in hygienic mode it just goes and cycles oh you know blah blah blah and that's the thing i have set up in my local projects i've got all the clang tidy bells and whistles clangforma so like after it's done all that it then says oh let me go check and so it might it might have used some you know stood enable if which is uh you know not best practice anymore and then so the clank tidy will say oh use requires uh instead of this and so then it'll

go it'll modernize my code base with a dash dash fix on a script that i got in so like you can start it's just so great it's just so great folks uh you know i used to i used to die inside when i'm thinking about oh i got to set up another clang tidy file get the python script working correctly pointed out the right things you got to set up a custom set of rules and whatnot which is why i think probably rust is just the future you know all that stuff ships out of the box yeah you don't have to do anything. It's one command. But still, whether you're a rest programmer, C++ programmer, give it a shot.

You might only have a couple years left if the singularity happens. Yeah. Any, anyway, final thoughts from... Well, I guess I got to... The next thing I got to go do is go dive into PowerPoint because I got to finalize my slides for talking at SciPai next week. And I'm sad that I don't have my hygienic thing because I... Like, I already know exactly what I would write, the prompts I would write.

I just need three slides I need updated. So that's going to be the rest of my day. It is crazy. Knowing, like, what could be possible and then having to do it manually now, it feels like... It makes me sad. You're, like, you're coding with one hand or something like that, you know? Yeah. Or building a deck with one hand.

Yeah. Anyways, will this be one, two, three, four episodes? Who knows? Well, I don't know. You got a good name for this? Should we ask the LLMs? I was thinking like AI talk, but I don't know, I don't want to scare people away because I'm pretty sure some people see the word AI and they're like, skip.

Yeah, I don't know. Are we an AI podcast now? No, although I will say, I have a hard time getting excited about conversations where I'm not allowed to mention AI. Because there are certain, I don't want to be specific because I don't want to call these folks out. But there are certain spaces where AI has like, it's like a trigger word. And so we have to have discussions and, like, skate around it. But I'm just like, what does it even mean to be talking about anything, not in the context of, like, what is going to potentially be the biggest, like, paradigm shift of our lifetimes? It's like, I was, who was I talking?

I was talking with Asher the other day about do programming languages even matter now? Like, obviously they do. But, like, as someone who was a huge PL enthusiast, I now find myself caring less about language paradigm. and like I already kind of know a lot of that stuff but it's just like when I can get a program to do all the heavy lifting for me

well you know why do I why do I care I want I want the language that's going to work best with that tool if that's JavaScript instead of Python I prefer JavaScript if that's Rust instead of C++ I prefer Rust you know like it's sure

I used to like one language versus the other for reasons X, Y and Z but now that was because I was the one having to do the typing and the iterating I'm not doing that anymore. It's the LLMs they're doing it. So it's like in a world where you are building libraries and languages, I feel like the number one thing we should care about

is like how do these interact with LLMs. Like are we making it more difficult or worse? I've been making this point to a lot of people that we need to start thinking about how do we design libraries, how do we design software, how do we design docs to be consumable by LLMs. Yeah, it's like when you mentioned the GPU mode folks doing the Kuda kernel generation,

it's like, well, the surface area of writing a kuda kernel, it's very thorny. Like, you know, it's got syntax that's not simple, and it's not surprising to me at all that it really struggles that stuff. So like if we're going to be building some next generation, you know, LLM built Kuta programming thing, it's like, well, we should really be thinking and trying to do the heavy lifting behind the scenes of making sure that whatever we're putting out into the world, LLMs do the right thing with it's easy to generate code and it also runs very efficiently you know

anyways a topic for another day i think that programming languages are still important but and actually it's an interesting it's an exciting time to be in the programming language space because we are going to see in the next few years um programming language is designed for lLMs and just the the it's like we have a new audience for programming languages like now we need to think about not just how do we design a good programming, like how do we design a good feature for use by humans, but how do we design a good feature for use by LOMs? And fundamentally, humans are still going to be interacting with the code. You can't design the code solely for the LOM. I don't think we're at that phase yet. And I think while that's an interesting research

area, and I think people should certainly explore that. I think that more practically, the programming language is going to be the interchange, the communication between the, the programmer, the human, and the LLM. And so we need to figure out how can we structure code, how can code be structured in a way where, both the human and the large language model can easily and efficiently interact with it. Yeah. I 1,000% agree. And that's why, like I said, it's hard when I enter a conversation and like all I'm thinking about all day long is

is AI and like wanting to have the AI in my sunglasses while I'm running so I can do more work and then there's other people being like it sucks, it doesn't work you know, it's not helpful and I'm like are we living in the same world? Yeah. Anyways, it'll be a, oh also too.

Small update. To Tesla not to Tesla, we did not Tesla. We bought a Toyota plug-in hybrid not because we were against Tesla but because we realized that it's actually a better option for I ended up doing opposition research

because of Elon and then discovered that if we're going to be taking a lot of trips that are, you know, are going to require two or three Tesla charges it's actually better to get a hybrid for the moment until we get fast charging. Okay, yeah, yeah, yeah. Like cheaper or just like more flexible to have the hybrid.

More flexible and like so it's going to be it's not going to be cheaper necessarily. I think the Tesla charging is still cheaper, but it's going to be more flexible in that. Tesla still take like 25 minutes for like a full charge. Yeah. And then also if you're going to like remote areas, you don't necessarily have access to superchargers.

Like especially in Canada and given that you're going to remote areas, I think you probably will have greater flexibility with like I can't imagine that in the middle of nowhere in Canada there's a ton of superchargers. Yeah, and that's the thing is that Shima does remote hospitalist work sometimes and so we might be driving like six or seven hours

to work, I'll be working remotely for a week in like rural Ontario and it's probably fine but the thing is is like if you're in hybrid mode and that's the thing is you can treat a Toyota Prius as an EV. It's got like 80 kilometers of range so if you're just local in the city you just treat it as an EV and it's only when you need to do these trips that and then you can get like I don't know it's 1,200 miles or something

but the point is a listener update we did not Tesla and maybe Elon can calm down and we'll reconsider the next time we get vehicle number two in five years or something it doesn't seem like he's likely to calm down anytime soon doesn't sound like it I think his most recent tweet was

it could be very easily that's why I guess the Trump impression I don't have an Elon impression it could be very easy to escalate but I will not I won't do it it's like crazy time to live in All right, we should wrap up.

We should wrap up because this dog has to go outside. 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.