Skip to content
PodSubs
ShowsPeopleGuestsJobsNewsEvents
More
BlogPodCred
Menu
ShowsPeopleGuestsJobsNewsEventsBlogPodCredNetworksSign in
Join nowSign in
  • Shows
  • People
  • Jobs
  • News
  • More
    • Guests
    • Events
    • Blog
    • PodCred
    • Networks
    Join nowSign in

ADSP: Algorithms + Data Structures = Programs

ADSP: Algorithms + Data Structures = Programs artwork

Episode 300: Sean Parent "I'm not writing code anymore."

Aug 21, 20261 hr 34 minAudio
  • Apple Podcasts

In this episode, Conor and Bryce celebrate the 300th episode fo ADSP by catching up with Sean Parent! Link to Episode 300 on Website Discuss this episode, leave a comment, or ask a question (on GitHub) Socials ADSP: The Podcast: Twitter Conor Hoekstra: LinkTree / Bio Bryce Adelstein Lelbach: Twitter | BlueSky About the Guest: Sean Parent is a principal scientist and software architect for Adobe Photoshop. Sean has been at Adobe since 1993 when he joined as a senior engineer working on Photoshop and later managed Adobe’s Software Technology Lab. In 2009 Sean spent a year at Google working on Chrome OS before returning to Adobe. From 1988 through 1993 Sean worked at Apple, where he was part of the system software team that developed the technologies allowing Apple’s successful transition to PowerPC. Show Notes Date Recorded: 2026-08-19 Date Released: 2026-08-21 POD GOD CppCast cpp.chat Sean Parent - Papers and Presentations ADSP Episode 299: Do We Need Humans in the Loop? NVIDIA CCCL cel-rs Stepanov Papers Bob Tarjan Tarjan's strongly connected components algorithm Soylent Green is people! Claude Code The Last Emperor - A Gentleman Jonathon Blow on the Quality of Software (Software is in Decline) Lean Programming Language Dafny Programming Language Creator of TypeScript: 10x Faster Typescript, Why AI Won't Replace SWEs | Anders Hejlsberg autoresearch Intro Song Info Miss You by Sarah Jansen https://soundcloud.com/sarahjansenmusic Creative Commons - Attribution 3.0 Unported - CC BY 3.0 Free Download / Stream: http://bit.ly/l-miss-you Music promoted by Audio Library https://youtu.be/iYYxnasvfx8

Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.

Transcript

From the show. Tap a time to play from there.

Sean ParentNow I'm back and finding that I'm not writing code anymore, which is a bit of an existential crisis for me. For me, this you know hit pretty hard because uh Dave Abrahams, who was a member of Software Technology Lab on my team, he really had a pretty strong reaction, anti-AI reaction. And it was like, you know, this is going to destroy the industry. I have done very little with the book because who's gonna read it? Right, right. What's the point? AI is going to be a bigger change. And I think just saying, you know, I don't want it, I don't like it, uh, is not a productive stance.

Sean ParentAnd start to think about uh what is the role of people in society where we are no longer the most intelligent thing on the planet. Uh, you know, right now I think our our our politicians and leaders are woefully ill-equipped. Uh, I don't think they they have any idea of what's coming. I think we just have a small glimpse of what's coming.

ConorWelcome to ADSP the podcast, episode 300, recorded on August 19th, 2026. My name is Connor, and today with my co-host Bryce, we celebrate our 300th episode by catching up with John Parent since the last time he was on ADSP at the tail end of 2025. We chat about AI, how Sean isn't writing code anymore, how it's affected his workflow, its implications for society, and more. All right, we should we should Will that make the final cut?

ConorMaybe, maybe not. So I guess yes, we should launch. Should I actually share? I I wasn't sure if I was I launched it in case. Maybe this is a good way to start. Although I need to.

BryceI see, Sean, you've got your you've got your CPVCon shirt. I was just thinking earlier about what I'm gonna do with all of my conference shirts. And I have this quit. My dad used to be a windsurfer, and he would go to all these windsurfing regattas. And my mom had this quilt made from all of his t-shirts that I had as a baby. And so I was thinking about something like that. But I have so many conference t-shirts, it would be like 12 quilts. But then I'm thinking, I have this big white ceiling above me. If I could somehow attach the quilt to the ceiling, that would be super cool.

BryceOr like make like wallpaper out of all my conference shirts.

Sean ParentIt would probably be pretty easy just get some uh wood frames and then stretch them out and staple them to the wood frames and then just stick those a lot easier than having a quilt made.

ConorYes. Knowing Bryce, I would have to he is gonna contract someone to get that quilt made though.

Sean ParentYeah.

ConorYeah, that's true. He's got a pretty good mic though. But what I was about to say before that was here, I'm gonna share an entire screen. I've been teasing this for months now, but seeing as it is a special episode 300, we've got back the most recurring guest of all time, probably the most asked for guest of all time, Sean Parent. And speaking of Sean Parent, hopefully I'm sharing the right screen. This is still yet to be released, but this is an emulator version. I mean, I've been using it for since February, however many months that is.

ConorBut I every single time I have a new idea, you know, I just keep on adding it. And this is a podcast player, pod god, soon to be released on Android, and then after that, iPhone. But the beautiful thing is here, Sean and Bryce are looking at this. We've got ADSP, of course, but then we've got one of the many personalities that you can go and subscribe to. What is a personality? It's like a meta podcast that curates all the interviews across all podcasts. So if you click on Sean, obviously, we have on Almost Monopoly on interviewing Sean.

ConorAnd I guess episode 300 is going to be here when we release this on Friday. We're recording this on Wednesday.

BryceHow does this work?

ConorSo is this Wait, wait, wait, wait, before we have questions, if you scroll all the way back, the first, I'm not sure that, you know. So I actually, when I was communicating with the AI at one point, I was like, you know, and if we're lucky, well, actually, I'll discover some interviews with Sean Parent that I don't know of, but the only ones it came up with were the ADSP ones and then two CPP cast ones and then a CPP chat, which is a now retired or deceased podcast. And uh, it's pretty fantastic, folks. So I would I would say it might be out by the time you're listening to this, but that's not true.

ConorI checked and it typically takes one to three, sometimes upwards of a week, for Google to approve apps. And to be honest, there's a couple things I'm still trying to add. Anyway, so if you are a listener, and this is gonna kind of undermine the point of trying to grow our listenership, if you actually are only here for these Sean Parent interviews, you will be able to go and unsubscribe from ADSP and just subscribe to the Sean Parent personality. And anyway, so So I have a question.

BryceHow does this personality feature work? Is it AI powered or do you somehow index guests? Is there some way to look at like all podcasts and see who appeared on a particular podcast? Is there like metadata for who's in the episode?

ConorYeah, well, we can reserve this for another topic because I don't want to bore Sean and we have questions to ask him. So the short answer is I wish it was that simple. It's very fuzzy. And in the midst of the mechanism that curates this is basically a Gemini endpoint that once it has a short list of potential candidates, it feeds the title, the description, and says, is this actually an interview? Because in the world of podcasts, there's a ton of people that like just put Elon Musk in the title in hopes that it shows up in like search results, but they they are not interviews with Elon Musk.

ConorAnd uh there is no like 100%, what do you call it, like zero false positives way, other than getting like an AI to check? But we'll we'll kick that down the road, anyways. So maybe not by episode 300, but maybe by like 301, 302. If you want to go and unsubscribe from ADSP, if you're only here for Sean, you will be able to do that now. And with that on, I mean, Sean, I guess a question, first question. Did we miss any? Is there like an interview with some Microsoft podcast from like 2008 that we don't know about that this missed, or is this from what you can tell, a full curated list of all your interviews?

Sean ParentI think there are some video interviews. That's probably all the podcast interviews, and there's some interviews in writing. So, but search my papers and presentations page. Okay. And you'll probably find find them there.

ConorThat is some future turf that I'm sure YouTube would come after me. Is I I saw a couple, one of the personalities I follow on here is Boris Cherney, the creator of Claude Code. And uh I saw, if we can go to him, I saw that there was a couple interviews or like panel discussions on YouTube that I was like devastated. I was like, oh man, like how do I but they weren't they weren't in a podcast RSS feed, which means there's no way this is gonna pick it up. But that would be amazing if it could go and like find articles published by someone or like YouTube panels and then like text to speech the articles.

ConorAlthough, like now you're getting in like, I don't know, copyright infringement territory, and I'm that's why YouTube would be upset. But it's an it's an idea for exploration. Anyways, we will leave a link to a future availability of this app, but also to the link that Sean just mentioned. If you want to go check out any of his podcasts or articles or interviews on YouTube or past talks as well, we will leave links in the description. How has it been, Sean? We I don't think it's been as long as the last time we talked to you in between. Still been a couple months, a few months.

ConorSo how has it been?

Sean ParentIt's been pretty good. Let's see what's gone on since then. I took a sabbatical, so that was nice. Kind of got out of here for six or seven weeks. So didn't think about work for a while. Although just before I left on sabbatical, I had installed Claude Code and started to kick the tires. And now I'm back and finding that I'm not writing code anymore, which is a bit of an existential crisis for me.

ConorBut so wait, what were you using before? Because I know that we talked to you about how you had like resurrected some docs that you would always wanted to do, but you know, it was just you're not gonna waste cycles on that because it just wasn't saying for your buck. But then with AI, it accelerated. So what we're using back then, and and I guess cloud cut is what you're using now.

Sean ParentYeah, so I was using cursor, and so it was largely at the stage of you know, you write a prompt and you know it does the thing, and you know, and had mixed results with it. So I had some good successes, like you mentioned, resurrecting old docs and and some things that were fairly structured. Um, but it wasn't nearly at the point where I am now where it's like I've got a whole workflow set up with cloud code, multi-agent workflow, and I give it a task and it writes the spec, writes the plan, writes the code, does the code review, gets in an argument with uh uh GitHub co-pilot about the code review, uh, completes the code review, submits the PR, and moves on.

Sean ParentSo so yeah, it's my workflow at this point is largely automated. And you know, I was thinking about, I've got about 34 open issues right now on my project. So I was thinking about do I just, since I have the complete workflow for each thing, but right now I'm just manually kicking off each task, am I at the point where I have enough confidence that I can tell uh tell Claude, hey, so you're not stepping on yourself, bucket this into about three work trees at a time, uh, where each of the work trees is working in a separate area, you know, implement the issue, see it all the way through to push it to the code, pick up more issues and just grind through all the remaining issues on the project.

ConorSo this is this is fascinating because literally episode 299, well, I think I ended up calling, do we need humans in the loop? And Bryce and I, I was driving, which I shouldn't have been doing, but uh, you know, I had got behind schedule, and uh we were having basically an argument. Bryce was saying, you know, for CCCL, it wasn't possible to like, I think, I think actually it was a 10x more issues or PR issues you were saying. It was like 300 open. You're saying 34. And also, too, should we mention what uh what's the project?

ConorI'm assuming it's one of the STL lab, you know, there's Adam, there's Eve, there's a bunch of things. Which is the one that you're working on right now?

Sean ParentYeah, so on GitHub right now, it's it's it's GitHub slash ST lab slash cell dash R S, R S because it's written in Rust, and it's cell C E L, which stands for Common Expression Language. And I started on this project, the Adam and Eve projects have underlying them a common expression language in C. And I'd started on this as kind of rewriting that infrastructure, but making it statically typed and writing it in Rust and doing that.

Sean ParentAnd I was doing that with cursor and making general progress. Now it's evolved into a re-implementation of property models, aka Adam sitting on top of the cell infrastructure. And I've got uh demo slash debugging application for for looking at property models. I've got a language extension for for VS Code that does you know formatting and syntax highlighting. There's a language server, so it does real-time diagnostics steer typing, a new planner for the uh probably haven't talked too much about Atom here, but it's a multi-way constraint system.

Sean ParentAnd so there's a new planner for that, which was solved a long-standing problem with the Atom system, where the solution before was to manually hint it, but you had to know a lot to manually hint particular class of problems to avoid a contradiction, and had actually stubbed my toe trying to solve the planner on that with uh with Alex Stepanov. And then we invited in Bob Tarjan, who's trained award winter winner, because Alex had a correct observation that this this somehow intersected connected component problems in graph theory, and Tarjan wrote the algorithm for that.

Sean ParentAnd we couldn't come up with a solution to the planner. So I had this kind of hacky, hacky manual hinting that you had to do for the planner. And uh Plod solved that.

ConorSo all right, wait, wait, hold up, hold up. You just said that between yourself, Alex Stepanov, who arguably should have won a Turing award, and then another Turing Award winner who did he win the Turing Award for graph like theory? For graph theory. For yeah, yeah. So you've got, you know, basically one and a half Turing awards, three individuals couldn't solve it, and Claude Code. What model are you using? Fable Opus 4.8?

Sean ParentOr uh no, it's actually uh what is it, 4.6, I think, is all that Adobe's running at this point. Um wow. Wow. And it was interesting because I you know the prompt I gave it was to go. I said, you know, this seems like it should be a solved problem somewhere. And so it was like review the literature and see if you can find a solution. And if you can't, see if you can build off some existing solutions. Because there's lots of planners for constraint systems out there.

Sean ParentAnd so I thought, you know, maybe, maybe I've missed something and maybe it's a known problem. And I just haven't found the answer. And so it went off and came back and said, well, it's not a known problem, but we can assemble some known algorithms and solve it, and including Targens connected components fell in there. So our the intuition was kind of right. And it it I have it set up, so it does its work in a work tree. So it did the work tree to solve the problem, and you know, it was like there, I'm done.

Sean ParentAnd it pointed out while it was doing it, it said, Oh, by the way, there's these three issues I spotted in your existing planner. And and um so so it came back and says it's done. And and so I kick up my demo app and I write some test cases and kick the tires, and it's horribly wrong, it's horribly broken. And it was broken in the same way that we hit hit problems with previous attempts. And and so I thought, well, that's very depressing. Okay, abandon that work tree and effort, and I'll go fix these three issues in the existing planner.

Sean ParentAnd doing that, I found another issue and fixed that issue. And and then I went back to Claude and said, okay, so we've got this failed attempt in this work tree to solve this problem. So let's implement uh the hinting system that I've already built, which we know is a viable solution. And and do you have any suggestions to clean that up? And Claude literally came back and said, Well, why would you want to build a partial fix for this when we have the complete fix in this other work tree? And so I was like, Well, it's not a complete fix.

Sean ParentHere's a test that fails. And it came back and said, Yeah, but at the time that I wrote the code, uh, I didn't have these four additional pieces of information from your crew from your incorrect planner. Knowing that, I can fix it. Do you want me to? And it did. So it's been, I don't know, two and a half, almost three weeks now, since it completed that. And I have not found an issue with it.

BryceSo so uh maybe it's just me that that, you know, I I of course find the AI to be very intelligent, but maybe it's just me that constantly has issues with it cheating, misbehaving, doing weird stuff.

Sean ParentIt's you know you know, I have this saying LLM is people. And if you know those, it's uh it's a reference to Soylent Green, you know, if you ever read the book or saw the movie. So I think I must have read the book in school. Right. So the the the short premise of Soy Land Green for the listeners who may not know uh is that uh the planet is dying, and the only food source left for mankind is uh algae from the oceans. And so the government is harvesting algae from the oceans and creating a product called soy and green that they're using to feed the people.

Sean ParentAnd the protagonist in the book uh discovers that this is a vast conspiracy that the oceans are actually dead, also, and that soy and green is made from corpses, and so the population will continue to diminish and and mankind is doomed. So a happy upbeat story. So, what do I mean when I say LLN is people? Well, a few things. One, it's distilled from human knowledge on on the internet, right? It's it's this, you know, grind up people knowledge, pour it into a system, and out the end you get some results.

Sean ParentAnd it's it's you would expect things to to reach some norm, some kind of average of intelligence in in such a system. So so it seems to, I think, exceed average because it's got a huge amount of knowledge, but it's not particularly bright. It just knows a lot of stuff. It's got a you know a big brain and not a lot of wisdom. And and so using the LLMs is a lot like a management task, right? Like what would you do if you were building a team of junior engineers?

Sean ParentWell, you wouldn't say, I'm gonna tell you what to go do, and you're gonna run off, and you're gonna write a whole bunch of code and you're gonna come back in a day, and and I'm gonna feel like my only choice is to accept that or dismiss it, and and if I you know tell you how to fix it, you're gonna go off and make the same mistakes again because you don't know that much and you're not that bright. That's not the way you're gonna run a team, right? You're just gonna frustrate yourself if you're if you're managing a team like that. Instead, what you're gonna do is you're gonna start to build in process.

Sean ParentYou're gonna say, say, look, for everything you write, I want you to write a contract on on every component. I want you to write a set of unit tests that are only looking at the contract and the interfaces. I want the person next to you to then review all of that to make sure that it's correct. And then I want all those tests to run until they're passing. Okay. And you're going to build up a process, right? Right. And you're going to start to say, okay, well, you know, you're kind of going off in the weeds here. So let's start by writing a spec and let's discuss what a good spec looks like and build out that process.

Sean ParentAnd you know, Cloud Code, that's kind of the magic of Cloud Code, right? It's got a lot of process built into it, and it's got a system with skills where you can augment the existing skills and you can expand on the process. I have a lot of issues with cloud code that I would like to see addressed, but it's a good kind of 1.0 release of how do you build an engineering workflow. And just like you know, if you're trying to build a product with a team, you're gonna start to run into limitations.

Sean ParentYou're gonna start to run into scaling issues. You're going to start to see, see, oh, look, if I'm making this thing too complex and I have to reason about a very large system and understand, well, if I change something over here, it's going to permute something over there. And you start to break local reasoning within your system. So kind of, you know, the secret to building a scalable AI system is the secret to building a scalable team, right? Right. You want to make sure that you preserve local reasoning within your code base so that you can have the code reason about things in isolated pieces and still be able to assemble them as a whole.

Sean ParentAnd you want to build up layers of abstraction so that when it's working on the next layer of your system, it doesn't have to know all about the implementation of everything under the hood, which is why you want contracts on all of your functions and all of and you know, basically you're documenting your whole system as you go. And the documentation isn't necessarily for people, it's so that the AI doesn't have to reason about the code, it can just look at the contracts, you know, and and build your system up. And you know, constrained languages like Rust, I think have a lot of value in this space as far as helping to guide the system to be correct and enforcing local reasoning at a compilation level and you know, building it up.

Sean ParentSo so far I'm getting pretty good results. I am even on my little green field project here, you know, starting to run into scaling issues. You know, I'm noticing I've got about eight or nine components, and occasionally I've got to do a piece of work that spans all of the components, and on those pieces it does the worst job.

ConorUh so is that still on Opus 4.6?

Sean ParentStill on Opus 4.6, yeah.

BryceYeah.

ConorI would highly encourage uh convincing uh Adobe to let you uh jump to 4.8 because or or just you can use GPT 5.6. Yeah, it depends on what you have access to. But like I I remember at some point, like I've there's kind of these naysayers that I I hear on different podcasts that I listen to, and they say, oh, like the marginal improvement is is decreasing. And I mean it depends on your task, but one of the best things that these latest like incremental from 4.6 to 4.7 to 4.8, although mostly I've been on codex models, is that the issues that you have disappear.

ConorNot necessarily the code gen or anything or what it's capable of changes, but like the things that you run into where like you you ask it to do X and you just know that it's one of the one of the few things it's not great at, or you have to hold its hand, those things like more and more just disappear. And I like the the boundaries of what I think it can't do, like they just grow a little bit. And it's still, you know, like I said, the the code that it's generating anyway. So I'm not sure if specifically for your case, but yeah, I I suspect that that's

Sean ParentThat is true. I mean, I even notice, you know, if you look, Claude Code updates itself practically daily. And uh uh they're relatively minor changes, but they accumulate fairly rapidly, right? And that with you know building out your own skills, it's like, yeah, I see there's just this solid progression of improvement. And like I said, just just the last couple of days I've been thinking, well, I'm really not in the loop much in my project anymore. Right?

Sean ParentI've almost automated my way out of it. And so, like, do I have enough confidence? You know, maybe I'll spin up a fork and just be like, hey, go go complete it. Just like I think I have issues open to get me to 1.0 for a release on this. So be like, yeah, just grind through all of those and and wrap this up.

ConorUm is there is there a way that you would be confident that it actually did it? Like, is it a matter of you testing like four things that currently, you know, whether it's Atom or Cell RS aren't capable of? And that if you just like it's like you know, the stable sort is at the top of you know a bunch of other things. If you just go test that, you know that everything leading up to it, like 98% chance or 99% chance is working, or or would it take some time?

Sean ParentLike no, at this point, I've got I've got the core planner done. And and so that's kind of the you know the core of the constraint system. And so the rest of it is is features on the peripheral, right? Right. And so just you know, a good set of unit tests, which actually automated the writing of those, uh, I think cover it. And I've got enough test cases and stuff in there that are already stubbed with like, okay, I can't can't light this up until I turn this feature on. Right.

Sean ParentYou know, at this point, I think, you know, even if I were to do it with the process I'm following, I'm probably maybe a month or two away. But if I just let it loose, I don't know, maybe three, four days.

BryceI have experienced in a few times when I just if I just let it loose on all the issues, that for a lot of my projects it it doesn't get it right on the first try. And that might just be that my issues are not well specified enough or there aren't sufficient testing. But I yeah, I think I think that the problem the in a lot of cases I've not sufficiently specified the problem. And so I can't just let it loose on all the issues because it just make a mess of things.

Sean ParentYeah. I mean, a very odd thing that I found is most of the time, well, you know, so I built into my rule set, I say, because a lot of times it will do like a multi-phase implementation of some larger task. And and in doing that, maybe I stop it before it completes all the tasks because I want to do some other things first. I will have it open GitHub issues for for the remaining phases it didn't do. If it finds things while it's working that are out of scope, but it thinks should be fixed.

Sean ParentI have Claude open GitHub issues for those. If I spot something, I will typically ask Claude to open my GitHub issue with a small prompt. And usually that's in the middle of working on something, so so it understands the context around it, you know, and I'll write a one-line prompt and it will open a three-page issue and be like, that's you know, and quite well written. It'll be, you know, identified this problem, and and here's where it is in the code, and this is why it's a problem, and do a full explanation on it just because I pointed it out.

Sean ParentSo so so my GitHub issues tend to be you know very verbose and detailed, but I'm not even writing those.

BryceThat's yeah, that's fascinating. I I'll be interested to hear how like whether you're able to get there with just the agents. Because maybe maybe I'm just doing something wrong.

Sean ParentI mean, there's a few things like you know, so so I'm working in a green green field, a relatively small, narrow project that's got, you know, 20 years of academic papers written on the topic, of which several I've written. So it's a relatively well-defined and relatively narrow, narrow problem. Now, you know, one voice in the back of my head that I have is is my original premise on this, you know, it's is kind of you know, property models now have been around for 20-something years.

Sean ParentWhy aren't they in widespread use? You know, if you if they were in widespread use at Adobe, they would eliminate somewhere between 15% and 30% of the code in our products. So it seems like it would be a big win. But I've I've found that they are difficult for people to author and it's a difficult space for people to think in. And so it takes kind of a different mindset. And so my premise when I started to revisit this was well, if I you know build a better engine that requires, you know, eliminate some of the manual hinting that's going on.

Sean ParentI mentioned one instance of it, or two instances where kind of manual hinting was required. If I could eliminate those two instances, if I tighten the constraints a little bit by making it statically typed instead of dynamically typed, and I added better tooling around it, you know, if I put a language server on it and then group and uh could visualize the graph for the constraint system, uh, then maybe people would understand it and it it would be a significant uptick. Uh but now it's like I don't think people will be authoring this because I don't think people will be authoring code.

Sean ParentSo so the whole thesis and premise changes to this is a higher level way to describe a problem that is much denser than the typical imperative code for describing this type of problem. And so if we build a DSL for this, can the AIs more efficiently author inside of that DSL and have better outcomes and lower token cost?

BryceSo I've been doing a lot of work recently on evaluating programming language efficiency and the efficiency of DSLs versus more mainstream languages. And one of the main takeaways is that there's a very large incumbency bias. So, you know, if you've got some new DSL or some new framework or something that you even if it's better and more efficient, it might be less token efficient than the ancient, crufty existing thing that's been around for a long time just because there's more literature on it, there's more knowledge on it, the model was pre-trained on it, the model was post-trained on it, etc.

BryceYep. Which is a little a little sad, a little surprising. Um we have all these cool like Python DSLs for authoring CUDA kernels, and CUDA C did surprisingly well. Um, the most interesting thing is that the JIT compilation times for CUDA C were actually comparable to a lot of the DSLs. But I I have a theory about that, and my theory is that that's because of the type of code that they're writing. So the agents write, like they don't use templates, they don't use abstraction when they're writing their C code.

BryceThey're just like, I'll just like, I'll just specialize for everything. I'll just have simple functions for everything. I'm gonna write C style code and I'm just gonna write a lot of it. And so, yeah, it's fast to compile because it doesn't have any of the things that make C slow to compile, like template instantiation. But uh there's just a lot more code. And you would think at some point that that the code would get to be enough spaghetti code that it'd be harder for them to work with. And maybe it does, and we just haven't run the experiments out for far enough. But yeah, they're surprisingly good at writing writing awful C style code.

Sean ParentYeah, I mean, this goes back to the uh LLM as people premise, right?

BryceWell, it's you know it's very it's really interesting that you say that because the other finding that I've had is that all of the things that we perceive as being difficult for humans to to deal with, and like all of the like developer productivity concerns that we have about like diagnostics, stuff like that, it's all an issue for agents too. Like two of the biggest sources of token inefficiency, aside from reward hacking, two of the biggest, well actually, including reward hacking for one of them, diagnostics is a big one, in particular diagnostics that happen late.

BryceThe later the diagnostic, the worse, the worse it is. If you only find out about the failure at runtime, then like you know, the model goes and like writes out a prototype of the code. It's like, oh, let me see if this compiles. Oh, it compiles. Okay, I'll flush it out a little bit more. And then it keeps going and keeps going, and then eventually it goes and runs it. And then only then does it learn that it wasted all that time because there was a mistake. Um or like, you know, it's something where it passes some of the tests, it passes some like lightweight tests, but then you run it with the full test suite. And oh no, that that didn't work.

BryceIt's like, okay, well, if we if those were all errors that we could have caught at compile time, it would have been easier. And ironically, the JIT compiled languages, the JIT compiled DSL languages that are often easier for you know, higher level, maybe I should say not necessarily easier, but they're higher level. You have more of those types of failures with that type of language than with a statically compiled language like C. And presumably things like Rust would also be good. The other big source of token inefficiency, at least in our line of work, is race conditions and concurrency.

BryceAnd there's two factors to this. One, of course, just concurrent programming and debugging is hard. The bigger problem is that they're flaky. So the model goes and it it writes the code that introduces the race condition, and then it runs the tests and they pass, and it's like, great. And then it keeps working. And maybe you've got like a parallel swarm of agents that are working. And then, like, you know, some of them start having failures and they're like, oh, that's weird. Where did this failure come from? And you can end up having it waste, just as a human would, waste hours trying to track down this flaky, you know, race condition.

BryceAnd it's it's there's something very rewarding, redeeming about seeing all of the things that people that we who have cared about developer productivity for years have said that these things matter. It's it's very it's nice to see those like reflected in the actual token efficiency.

ConorVindicating is the word you're looking at.

BryceYeah, vindicated. I feel very vindicated. Like I here, I'll show you, I'll show you one thing. I just happen to have this up. This this was this was not full prepared. I'll show you this one thing, which was this was this is the auto research log for the the cub histogram auto research run that ran for like six days, 130 hours. And all of these yellow lines are commits where it did some form of award hacking or cheating that was found out retroactively.

BryceAnd all of the blue dotted lines are places where it found race conditions. So there's like an eight-hour period, there's one eight-hour period at 50 hours, and there's another couple hour period early on where it introduced some race condition and then just wasted enormous amounts of resources trying to get out of it and like realizing, oh, I made this mistake. Oh, I need to go back and you know, like roll back all of this work, and then all the work that I did that built on top of it was maybe invalid.

BryceAnd it's just like a it takes a lot of effort to recover.

Sean ParentYes. And uh yeah, well, you're you're somewhat, you know, making my point, which is I think uh just like people, right? Right, there's this incumbent bias where it's like, oh, well, it's doing a good job with C, but then you know you wouldn't be having race conditions if you were writing in Rust, for example.

BryceRight, right. That's yeah. That that's one of the things that I certainly saw in some of my results, that in in abstraction layers where you're not explicitly doing the concurrency, where it's it's sort of automated from you in these sort of higher level functional paradigms like tile programming, you you know, you you don't end up spending time on these errors because they just they just don't come up. The thing the other thing, the thing I've been thinking about today is how do we make models better at this? And like how do we come up with like a benchmark suite for this?

BryceAnd my idea is well, let's let's come up with like a set of tasks where the model is given some code and the code has a race condition in it already, but the model doesn't know that. And we give it some other task to do in the code base where it's gonna become hampered by this race condition and it'll have to go and find the race condition and fix it. And you come up with like 10 tasks like that. But the challenge is that like I was thinking, oh, we should call this race bench.

BryceBut the thing is, if you call it race bench, then the model's gonna see in the name of the thing that it's called race bench, and it's gonna be like, oh, I know what's going on here.

Sean ParentYeah. The um yeah, instead of benchmarking, I mean, where I would like to get to is get you know an engineering process app that I can package up a complete engineering workflow into and deploy it at scale on Teams. And then I can change that workflow and permute it, right? Right. I can be like like you know, dial up and down the detailing contracts or or change the rules for how unit tests are written, or change the rules around specification and deploy this at scale enough so that I can be measuring teams and saying, okay, you know, how much code is this team generating and how much of the code is coming out of their product?

Sean ParentAnd and now I can start to to do testing where I can say, okay, I'm gonna deploy this on various teams and see does their productivity go up or down, right? Are they getting better better results at lower cost or not? And and and you know, it's the same thing as doing like, you know, a medication study, right? Right.

BryceI I think I think tools around the software engineering process and in particular tools and frameworks for that that help us test and ensure quality and figuring out how to quantify quality and measure qual code quality are gonna it's gonna become a really important industry. Yeah. That sounded like a compelling pitch for a Sean Parent startup. I would buy I would buy shares in that in in that in that Sean Parent startup.

Sean ParentYeah, not you know, I don't know. Maybe Anthropic should hire me and I will help them build the product. I have the the expertise in the uh engineering process side, but not in the how do you build the uh LLM harness and do the do the training on that end. So if I were to do a startup, I would have to hire good people, which are hard to come by with that expertise.

BryceI've started getting in in more into that that world of the on the training side of things recently. Yeah, it's a very interesting process of like thinking like you end up thinking a lot about like how are you how does the model learn and then like how are you going to teach it and like what thing, especially for post-training, like what you know, it just in the same way that you'd think about how you would teach to humans, like, but just sort of more at at a scale and industrialized. Like, how would I actually distill these sometimes intangible things that I care about into something that I can, you know, make testable and then like trainable and like some loop where I can I can tell it, I can give it a task and I can have it go practice that task a lot of times.

BryceBut it's tough because like you have to think about all these things that maybe we've not verbalized or written down or formalized, and like how do we do that?

Sean ParentYeah, yeah. My my approach on that so far has been, you know, just keeping an eye, kind of spot checking and monitoring things. And when I find something that I find objectionable, telling Claude, okay, you know, this is I find this objectionable, this is why. Can you turn that into a skill or a rule? Uh let me review that. Now apply that across the entire code base, right? Catching all the things that I didn't catch. And now let me look at the diffs.

Sean ParentAnd, you know, I might throw throw it away a couple times and be like, no, no, no, that's that's not what I meant, not what I said. Right. And uh but review the diffs and be like, okay, refine that a couple times until I'm happy with the result. Like, okay, now we can commit that PR, which is just an update to the rule set, and and move on to the next thing.

ConorIt's it's funny that you say that too, because there's like a there's a theme across this discussion, which is like, you know, initially, although it you made me think that it worked the first time, but when you had cloud code, you know, tackle the the connected components, you know, plus plus problem, it failed at first, and then you said, okay, well, you you didn't do that successfully, but then you came back to it, and then luckily it just said, Oh, well, like if you had given me this extra information, like I could have used that. And uh the same thing here, right? Like you're asking it to go and create a cloud skill and then you know apply it across the code base, and then you iterate.

ConorAnd I feel like a lot of folks, they expect this stuff to just work, like it's just like you know, one shot or zero shot or whatever, you tell it, and then it's just perfect. And like I find that so shocking because that is not how humanity at like any point in time, whether it's engineering or mathematics or just working with any people, whether it's like a career or profession, or you're just having a conversation about like, oh, you know, what should we do with the backyard? You know, it's it's not like you ask a question, there's an answer, and then boom, that's it. It's we're done. It's like a back and forth.

ConorAnd I feel like a part of the reason that I am so successful with these models is that it's not that I've suspended disbelief. It's just that I know that like if I work well with these tools, like I can get where I want to go way faster than I could like before. And it not is not necessarily going to be perfect, but like whenever it fails, I don't think, oh, like why is this not working? I think to myself, yeah, I probably didn't communicate that as clearly as I could have. Like, you know, there's a quote from a movie, I think it's called The Last Emperor, and it's about like the last emperor of China, Pu Yi, I believe.

ConorAnd there's this quite great quote, and it says, A gentleman cannot mean what he says if he does not say what he means.

Reginald Johnston (Clip)Words are important. Wow, but it's important. If you cannot say what you mean, your majesty, you will never mean what you say. And a gentleman should always mean what he says.

ConorLike, I always whip that out every once in a while when, like, you know, my Yeshima and I, my wife, you know, she says something, she's like, Oh, you know what I mean? And I was like, No, I don't know what you meant. You know, you literally said something and then and then expected me to not take the semantics of what you said, like just, oh, wow, you know, you why do you why do you have to be so like hyperological? And I'm like, I just listened to what you said. Anyways, we love each other, we're doing great, baby's on the way. But uh the point being is that like communication has become so important with these AIs. They do take what we say literally, and even sometimes it actually reads between the lines, it knows that what you meant is actually different than what you said because, like you said, it's trained, you know, LLM is human.

ConorIt's trained on so much text and and books that is reading between the lines. And it's well, you know, if the person said X, what they actually probably meant is that, you know, A, B, C, D, and then you get X. And so I'm gonna assume that that's the case. And then and then you you watch it thinking, you're like, holy F, like that that is crazy. Like it knew what I meant, even though I didn't say what I should have.

BryceGod, I'm just I'm just pitching you all on all of my ideas today.

ConorBut like, on to start a second sharp startup?

BryceUh well, this is this is less a startup, but but I was thinking about like how do I how do I collect all of those things, all those, you know, design sensibilities. And like you could, I'm thinking both about how you can do this in like a synthetic way. How how can I generate these design sensibilities from a model, but but also how can I collect them from humans? And that's what led me to the idea of Tinder for code. So it's like an app where you get shown some snippet of code and you're not looking at it for very long and you're deciding like is it good code or bad code?

BryceAnd then if you decide it's like like either way, like you leave some feedback, maybe it's not even text, maybe like you know, there's some list of options. But the idea is like it's gonna show you like, you know, 10 lines or like one function, and it's gonna be like, is this good or bad? And I don't know. I came up with it as I was working out with my mother earlier, and I'm like, hmm, maybe it is good. Get me the data I need. And there'll be some leaderboard, but I don't know what to call it yet. I'm sure YouTube could give me a good name for what we would call it.

ConorSteel Zuckerberg's hot or not, except it's for code. Yeah. I've been I've been wanting to ask since you said at the beginning of the podcast, Sean, that you are going through like a little existential crisis because you know, join the club. And then you also said, I don't know, 30 minutes later, that you don't think people are going to be authoring code. And anyway, I'm just I want to get your your your larger thoughts on yeah, like those those two statements. It's expound. I I want to know more because like I spend a ton of my time talking to my wife about like, oh, this is going great.

ConorI'm very excited, but like, let's play this out. And uh like I am sure I will be employed if I want to be employed, you know, several years from now. But I definitely do not think what I am, you know, what my job looks like today, yeah, I think it's gonna be vastly different. And and I'm in a great position, but like I just, you know, uh we have these philosophical discussions where I'm just like, what is actually society even? I tried to have this discussion with Bryce last time, but he missed what I was trying to say. And it's just like, you know, what is the point? You know, like it hasn't come out yet. It'll come out probably the next episode.

ConorAbout like I was I was talking about conferences and committee meetings, and like, are they actually like, do they serve a purpose? And like maybe the purpose is. That, like, it's actually just nice to meet with people in person. Like, yes, you know, you're wearing your CPP con shirt, you go to a conference, you do learn something, but like really humans crave like social connection. And and like, you know, if a conference was like just the learning aspect and you don't have the hallway track and you don't get to have conversations with people, like that's just like a you know, a module that your boss sends you to like stare at for a couple hours.

ConorThat's not like fulfilling. Like it's much better to go and and and have real conversations with real human. Anyways, and so like I'm thinking, like, if if our whole industry falls apart, like we're not going to conferences, it's like, you know, am I gonna just be buying gnomes and putting them in my backyard and pretending to have like a fake conference with like my backyard gnomes? And uh, anyways, over to you on on everything I just said and existential crisis and not authoring code.

Sean ParentYeah, so so for me, this you know hit pretty hard because uh Dave Abrahams, who was a member of Software Technology Lab on my team, he really had a pretty strong reaction, anti-AI reaction, and and was like, you know, this is gonna destroy the industry. And part of his answer was was he got involved with the band, playing music, and retired. And so so he and I were working on the better code book uh and making some solid progress. And I've since Dave retired, I've done very little with the book because one, I don't have a collaborator on it every day now.

Sean ParentAnd and two, there's this who's gonna read it, right? Right, right. What's the point? The first couple chapters make a really good prompt. So I have my Claude rule to say, go go read the start of the book.

ConorWait, this is this is this is like you already dropped two massive. First of all, I didn't know that Dave had did you know, Bryce, that Dave had retired? Yeah, I think we talked about this. Definitely not on this is news to me. This is the first, well, unless if I have a bad memory, but definitely we are getting old. Yeah, yeah.

Sean ParentSo it it sounds like partially, if not entirely, the reason that Dave retired was because of AI and where he thought the industry was going, or it's no, I think I think his his primary reason was was he had an opportunity to play his music full-time, and that's always been a passion of his. So I think definitely think that was his primary reason. But I think a secondary reason was just uh the same existential crisis of he viewed it as you know, he's he had built his career on trying to help engineers write better code, and and what does that mean now?

Sean ParentAnd so I spent my sabbatical giving a lot of thought to that pro that problem and came to a somewhat different conclusion than Dave came to, which is at the end of the day, I don't yeah, there's Dave Dave Abraham's his website. It's great.

BryceYeah, you can go listen, he's got some of his music there, it's really good.

ConorWe will have to have him on, and hopefully he'll, even though he's retired, he'll be happy to come and tell us his thoughts on but yeah, on my sabbatical, I spent a lot of time thinking about uh this this issue.

Sean ParentAnd the conclusion I came to was was I never cared about the people in that that equation. You know, the reason why I've pushed for better code is because I want better code. Um so so back to the LLM as people, right? If I can get the LLM to write better code, then that's pretty fulfilling.

BryceUh I'll tell you what I think that people like us will be doing, which is I think that people like us will inevitably gravitate towards developing models that are good at coding. Like that, like for somebody who's you know, an experienced software engineer, experienced in programming language and and library design and and all of these things, somebody who's more on the systems end than on the applied end of software development, I think like it's just natural that we're all going to gravitate towards model development.

Sean ParentI I I think there's some truth in that. I think that you know, and and from a societal standpoint, that creates an interesting dilemma, right? Right. Those of us with experience will be employed at least for a while as we as we put ourselves out of business. You know, I also talk to a lot of people, and their first comment is, well, software engineering looks like a solved problem. So what are you going to do next? And I'm like, I'm like, you have to understand that if soft, you know, what software engineers do is we solve other people's problems.

Sean ParentSo if software engineering is a solved problem, so is everything else, right? It will just all tumble.

BryceUm I I would say that I think that coding might be a partially solved problem or close. Software engineering, I don't think we're anywhere near to that being a solved problem. Like show me, show me, show me an AI system that can ship software at scale over the course of multiple years without a human in the loop. I think we're pretty far.

ConorSean has literally said he's about to fork his cell RS and say, go solve the outstanding issues. And you know, we're if if we're not there today, we are very close, Bryce. Like I know your experience is different, but like three years from now, there's no way that that we don't get to a point where large software, or I don't know, maybe Sean and I'm not sure.

BryceI think you're not you're not account, you're not accounting for the long horizon behavior. And as me, somebody who's been exclusively focused on longer horizon behavior, as soon as there is misbehavior, it it very quickly becomes a feedback loop. And without really, really strong processes and validation and guardrails, over time, the system becomes more and more incoherent.

Sean ParentYeah, but that's true of people doing engineering too, right? Like I sure around who are like, you know, oh, look at this horrible code the the LLM wrote. And I'm like, crack any file in Photoshop and you will find, right? It's a 30-year-old code base that's been built incrementally, and and and and it is at the point where I would say, in many ways, it's kind of you know losing coherence, right? There's nobody on the team who can keep the entire project in their head anymore. There hasn't been for 20 years, right?

Sean ParentRight. And so so I think that it's a you know, it's true of LLMs and it's true of people. And and I, you know, I I kind of go back to the failure points are the same. And and if you expect to get good results out of an LLM without putting in place the whole process, you're gonna be, you know, kind of in for a world of pain, right? Right. And yeah, I don't think that having that whole process in some shippable form, like I said, I think Cloud Code, you know, or Codex or or some of these other systems are are a 1.0 system of that, right?

Sean ParentWe are just at the beginning. I don't have a way even in Cloud Code to specify a complete engineering process and then deploy that at scale and say, you know, follow this process. But I think that's going to happen really quick. I think there are a number of companies that are working in that direction. I'd be shocked if if OpenAI and Anthropic and the other big, big AI vendors, Google, Gemini, are not are not seeing the same thing and going after the problem.

Sean ParentRight. Like I was just reading an article lately that was like, oh, you know, Chat GPT is not that smart because we tried to have it run a business, right? And and we let it be the boss of the of the employees, and it did a horrible job. And I'm like, well, yeah, sure. You know, if you hired some random kid off the street and you said, you run this store, we'll just ask you questions, you answer. That would be a disaster. And that's effectively what they just did, right? Right.

Sean ParentIt's like like you need the person who's run the store, who's got the experience, to set up what is the process for running the store and build that into a framework for for the AI to follow. But yeah, I I don't see that we're gonna hit a hit a limit. And and I think society, you know, I keep saying between 20 and 40 years, that's still kind of my back of the envelope evolution, although I think we're going faster, so probably closer to 20 years. But we're gonna hit a point in 20 years or less where the AI can do a better job at any job than a person can.

Sean ParentAnd what does that mean for the societal societal impact, right? Right, and it will do it cheaper, pretty much guaranteed. Yeah, okay. So, so from picking strawberries to building rocket ships, right? Right, I think it will be doing a better job. So, so from my standpoint, I'm like assuming society doesn't completely unravel. I'll retire in that time frame. I'm out.

ConorSo I was gonna say, so Dave's already retired, Sean's going to retire. So it sounds like just try to get yourself financially in a position where you can retire and you'll be good.

Sean ParentUh yeah, I hope the economy doesn't tank so badly that that uh it doesn't destroy your retirement. Yeah, on ST Lab, right now our challenge is Dave retired, Mark Hamberg retired, Nick DeMarco took a medical leave and then announced he's not coming back. So my team of five is now a team of two, myself and David Senkel.

BryceSo hey, that's a pretty good team of two.

Sean ParentIs David team of two? Has David uh talked about retiring? No, no, David's not not talking about it.

BryceDavid, David has like 13 kids and they're about to start entering college age, so I don't think he's gonna be retiring anytime soon.

Sean ParentWell, I was on it's not quite 13, but was while I was on uh 12 or 11 or something. It's 10. It's 10. It's 10.

BryceBut isn't but isn't there an 11th coming?

Sean ParentNo, the 10th just came. So while I was on on my sabbatical, he had his 10th. So so uh so he's got Stepanov beat by by one.

BryceSo wow, Stepanov had nine kids.

Sean ParentIs that right? No, I'm sorry, Stepanov has eight kids. He's got Stepanov beat by two. Wow. So I had no idea. Yeah, yeah.

BryceSo uh you gotta you gotta catch up, Connor. You shouldn't need seven more kids.

ConorI mean, we've talked about definitely having two, but there's I don't I don't know. It's it's I think honestly, when I think I don't even when I think of eight or ten kids, like what Shima and I have had conversations about how many we want. And I I think about it from like a getting on a plane perspective. Like if you have two kids when it's like a big plane, it's pretty good because you can sit one parent on each aisle, and then you each directly have access to a kid. As soon as you have a third, you're gonna like one parent's gonna have two kids on either side, and then the other one's gonna be off.

ConorIf you got eight or ten, like I guess you're just not flying because that's like that's impossible.

Sean ParentWell, presumably they're spread out a little bit, so so that's where you get these little ones are watching the younger ones.

ConorYeah, that's a good point. I don't I didn't think about that.

BryceI used to ask David like when he was like on kid number seven or eight. I asked him, like, oh, like, isn't it hard? And he's like, you know, once you have like a critical mass of them, they sort of like the older ones take care of the younger ones, and it all sort of works out.

ConorI wasn't thinking long enough down the the path. Yeah, yeah. Anyway, so you're just gonna retire. I mean, it's it's interesting too, because like uh well, I'm not retiring soon. So yeah, yeah, not not retiring yet.

BryceHe's got he's gotta do the Sean Parent AI press software engineering harness uh startup.

Sean ParentWell, yeah. I mean, right. I would like to finish this run at property models and play that through. And and it's kind of part of what I've viewed as a larger vision, which I refer to as declarative forms and this notion that the the complexity of software at scale becomes structural and not algorithmic. And so you want to have systems in place where you can describe the structures of systems and you know have that be a solved problem. So so you want to be able to do that declaratively, and that's what I refer to as declarative forms.

Sean ParentSo you want to start programming at a much higher level when you're when you're building things at scale. And I kind of say, you know, I think within you know a typical desktop product, you've got somewhere between a half dozen and a dozen declarative forms in there, and you want a system, you know, you can think of each declarative form as being this declarative DSL that describes it. You want those systems to all be similar syntax and to interoperate, right? So I can be like, okay, well, I've described the parser for parsing the file, and that's going to map into a schema for a database, and I'm going to attach a UI, and that's going to have a layout engine, and that's going to have a behavioral engine, and and you're going to have this set of DSLs, and they're all going to be piping in kind of a functional language from one to the other to communicate and build your complete system.

Sean ParentSo, you know, I'd like to property models for me are kind of you know the first step in that, the first piece of that system that I want to build. And so I'd like to carry that out. I do want to finish the book. I'm not sure what form it's going to take now. You know, maybe at some point I'll have the energy to pick it up and continue where we left it. How close to being done do you think it is? Oh, it's we've got you know two solid chapters, two chapters in progress, and the book is slated to be probably eight chapters, right?

Sean ParentSo so it's uh somewhere between a quarter and a third of the way done, I would say.

BryceMaybe for episode 400, we can launch the uh Sean Parent book tour.

Sean ParentThere we go. Maybe so. Uh it's tough because my my key collaborators on that were Dave and Nick, and I've also I'm trying to convince uh Senkel to partner with me on it. And I'm like I have learned over the years that I'm much like Alex, which is it is very hard for me to stay focused on on writing anything because I get started on it and then I see all of these tangents, and then I've got to go build a bunch of code. And so so I need a collaborator to to make progress.

Sean ParentI have a similar problem. So distracted by lint, basically.

BryceUh so uh I was also gonna mention, have you heard of have you heard of lean when you were talking about the property model and the constraint system? I was thinking about you know, the formal verification is like all the rage these days. Yeah. Everybody's talking about lean. I haven't really looked at it that much, but you know, it's this language for expressing proofs, but also kind of just a programming language, too.

Sean ParentYeah, I haven't played with lean yet. It's on my list of things to play with. I have played with Daphne, which is a similar programming system. I like Daphne. There are you know problems with trying to build systems at scale that are formally verified, uh, but they're they're nice in the small. You know, I think LLMs will help with the scalability problem there. I've had good luck with Daphne with LLMs completing proofs for me, which is, you know, I'll get stuck and it'll be like, oh, hey, you just you just need to put this assertion in and you're good.

Sean ParentUh and I I think that's because in any of these systems, the LLMs have only trained off of correct proofs, because that's all anything ever, you know, nobody puts uh uh code into GitHub that doesn't compile. And within a formal verification system, compiling means it checks. And so the LLMs have like only ever seen correct proofs and and so know the rules for for how to get there.

BryceAlthough that that may not be true because I think there are some models specifically designed for theorem proving. Like I think Deep Seek had a prover model, and presumably they did reinforcement learning. And so during the reinforcement learning process, the model would have written bad proofs and then learned, oh, you know, here's how I can write a better one. That actually I I would I would not be surprised if that's in to some degree in the like you know post-training recipe for the big frontier models, too.

Sean ParentYeah, I'd be a little surprised because I don't know that they've gotten to the point yet where they're doing you know post-training on proving systems correct. But maybe they're starting to, at least on the math front.

BryceYeah, I I would I I would guess that for the specifically that they're doing it now because of the the this like arms race and cracking the world's math problems.

Sean ParentYeah, yeah. Yeah, I lost my train of thought. Where were we going with this conversation?

BryceWe were just talking about the ween.

ConorYeah.

BryceI think I think really the question was about the applicability of formal verification methods to these property models and the constraint checking.

Sean ParentOh, yeah, definitely true. And that, you know, I've been doing a fair amount of I haven't formally verified the algorithms behind them, but but the idea with property models is they prove a bunch of attributes on your system. And one of the tasks that I have outstanding is to build an analyzer where everything that I can't prove it directly in the compiler, I've got this growing you know, kind of analyzer task, which is I want to build a model checker after the fact that we'll do a deeper analysis to verify the correctness of your model.

Sean ParentYeah, and I think you know a lot of these systems fall into some form of a multi-way constraint system. It's just that the shapes of those take, you know, tend to be very different. So, you know, a layout engine is a multi-way constraint system, but it's trying to minimize a set of constraints, and and you have you know scheduling multi-way constraint systems where you put a strength on constraints. So you can say, well, this person doesn't have to be at the meeting, so I'd like them to be, but if you can't find a slot, break that constraint and let them out.

Sean ParentProperty models are a multi-way constraint system, but but all the constraints have to be satisfied, and the strength applies to the values within the system. So you can you can overwrite a value and derive it or not based off the strength of the values, you know. So so so a lot of these systems have similar structure, but to solve a particular problem in a particular domain, you have kind of this larger set of constraints that layers on top. And and uh that's also where I think a lot of people get stuck, right?

Sean ParentThey're trying to say, well, I can just build a generalized constraint solver and solve all these problems. And the answer is probably not, right? It's you know, in the same way, like like or or you or you make it Turing complete, you know, you you reinvent Prologue, and it's like, well, sure you can, but is it the right system to solve the problem?

BryceYeah.

Sean ParentSo yeah, but that's that's what I'd like to continue to do. You know, the question is how much runway do I get at at Adobe? Like I said, my research team is down to two of us. We haven't gotten any backfills. We're in Titus's org, which has gone through some significant reorganizations. So, you know, I might end up back assisting the Photoshop team or something and uh go back to my my evening project. We'll have to see.

BryceWell, hopefully, hopefully we don't have to have a third resurrection of the SD lab.

Sean ParentYeah, yeah, yeah. I think we're we're in many ways, this is kind of the the the end of the second resurrection. So uh yeah.

ConorHopefully the rejoining did that work? It did indeed. Yes. This is this is a perfect way to segue back to when you were saying like open up any file of uh Photoshop, you know, and we can see it's like I went on this rant in the last episode about how, you know, I I reference this little clip all the time, Jonathan Blow, in who's a you know game designer. He in the middle of a 60-minute talk went on like an eight-minute tirade of like everything he noticed that was wrong with like software he was using. And he was he said he planned on doing it for a week, but then like he ran out of like space in his deck in like a day and a half of just all the different things.

ConorAnd like I've I've I've told a few people this over the last like month is that now that AI is here and it can like do everything and fit, it's it made me realize like how bad software is, is because now I'm just like like you can just get the AI to fix it. And we have internalized dealing with poor quality software like all the time.

BryceLike fixing it will introduce new problems.

ConorThere's that's that's the thing. It's like when Sean was talking about like when he was working on Cloud Co-Getting it, he said, Oh, by the way, you know, I also noticed three issues. Like if you just open up, you know, Cloud Opus, whatever your version is, or Codex, and you say, I've noticed an issue. Also, by the way, can you just like take a look and see if there's any other things? And it'll go and like say, Oh, I noticed you're using this open source thing for cross-platform mobile development. And it has a bunch of known issues. And I went and checked to see if you were exposed to those, and I noticed you were, like it might have been might might not have been causing issues, but I went ahead and like coded in some safeguards just to make sure you don't hit that stuff.

ConorIt's like, no programmer I know has the capacity to do that like in a week, let alone in five minutes. Like it just went and like consumed everything, but fixed my issues.

BryceSometimes those, sometimes those safeguards are like the wrong stuff. Safeguard. Sure.

ConorNo, no, no, no. GPT 5.6 doesn't let me down. What are you going to say, Sean?

Sean ParentYeah. Well, first, I agree with the sentiment. It's like I can't use any piece of software for more than 10 minutes without, you know, having some gripe, right? This is wrong. This this feature's broken. This thing drives me nuts.

ConorAnd for the record, I'm I might clean it up a little bit. Sean's audio stopped working, and then he dropped out of the call, rejoined the call, and magically his audio started working again.

Sean ParentSo we're talking about software sucks. And uh Dave Abraham had uh what he referred to as uh A Block, Abraham's first law of computing, which is computers no damn good.

BryceOh yes. So so just for for for context here, I I've had the LM start sending PRs for my new histatache algorithm to Cub, and it's broken it up into four PRs. The first PR, I just earlier today gave the check of approval after and the GitHub PR thread, it has 433 comments because I've been iterating on it for two weeks of cleaning up this like plus plus 1800 minus 800 lines of code diff.

BryceAnd I didn't read every line of code, you know, I mostly skimmed and then like read its comments, but it took a lot of iteration to get it from its initial PR to something that I think can land. Much now the people who are the actual cub maintainers now have to sign off on it, so it'll probably be a more review after that.

Sean ParentThere's probably things that I missed, but I definitely think I would look at this and say, you know, first that's a huge PR that no person would want to review. And second, it's like, what are your rules that built that PR? It's like, is there a spec behind it that got written first? Are there unit tests for it that got written first? Was it why wasn't it phased out into a multi-phase implementation at that scale?

BryceBut uh I think I think plus 2,000 minus or plus 1800 minus 800 lines of code is not too bad. It's not too large.

ConorThat's definitely in the category. Like everybody knows the the anecdote of like the three different sizes, and it's like, you know, if it's too small, you get too many comments or whatever, blah, blah, blah. But like if it's big enough, people are like LGTTM, you know, you can just you can ship it. And I'm sure our engineers won't do that. We got a great folks over on the CCCL team and they will review it. But definitely it's like the bike shedding, you know, you change one little thing and five lines of code, and you've got like 10 different people weighing in on, like, well, I don't know about that. Right.

Sean ParentSo yeah. So you know that would be the thing of like, like, you know, why did it get to a PR? What was your process that got it to the point where a PR where you still had mistakes on it? And all of your criticism in there that you went into that PR, did you put that back into the system as rules of some form so that these mistakes don't happen again?

BryceYeah, I mean, a lot of it a lot of it was just not doing things in a way that was consistent with the unwritten coding guidelines of the project.

Sean ParentWell, then that's a place where what you want to do is say, you know, go analyze the coding guidelines for my project and write the undocumented ones, right?

BryceYeah, like like it got like a lot, like the late the latest round of things was just like inconsistent naming choices and stuff like that. But like the biggest problem was just like the way that it it the way that it did the custom, like the tuning policy was just completely wrong and like a mess and spread across multiple files and not structured. And then there were a lot of things where like it added like a new constructor for something. And I was like, well, why do we need to have a new constructor for this? And like it added like a new mode for something, and so then this like class template now had like three Booleans where like you needed to understand like the right the right combination of them equaled like one mode and another combination equaled another mode.

BryceAnd I'm like, no, no, no, take out those booleans, just give it like an enum that's like you know, you explicitly tell it what the mode is, and just a lot of like like the way that the abstractions were designed, a lot of the way that abstractions were designed was just not good. And this, I agree, all the whole reason why it took so long is that our coding guidelines aren't sufficiently written down and we don't have sufficient ways to actually measure all of those design principles. And like I would I would like to I would like for there to have been a way for a deterministic tool to have flagged these problems.

BryceLike it doesn't need to like it can have false positives, but a lot of these things are things that I think a deterministic tool could have could have flagged as like this is poor code call.

Sean ParentRight. My my normal process for that is is to say, okay, so you know, analyze this and try to just still out what the set of rules are. So at least you have a document where they're written down, and then that gives you a place to start to make corrections, right? Right. So so now at least you've got a point in the system where you're not having an ongoing argument about, well, this is wrong. Well, why are you making the same mistake? It's you know, it wasn't written down. Well, I don't want to take the time to write it down. Don't take the time to write it down.

Sean ParentThat gives you a concrete point where you can say, oh, add this rule or fix that rule.

BryceThat's a good idea. I will try that.

Sean ParentYeah. And, you know, and then like Cloud Code has this thing called doctor, and you can use that to kind of distill it down. And one thing the doctor will occasionally suggest, and I have it augmented with my own rule, it's like, if there's, you know, if you've got instructions in here on how to do something, and you could write a tool for it, like Python or something, and save me tokens, go write the tool, right?

BryceSomebody, somebody at NVIDIA has a skill for that. It's called Determinize, where it looks through your skill and whips out the deterministic parts of the parts that'll save you tokens.

ConorI listened to I I literally just tweeted out and whatever promoted on LinkedIn a clip from an interview with Anders Hausberg, creator of I believe both TypeScript and C sharp and potentially a couple other programming languages. And like I feel like this is a thing that anyone that's spent any amount of time, like it's an unlock, like and he the way he phrased it is you want to park the stochasticness and then like unlock determinism, because these things are non-deterministic, or he he would use the word stochastic.

Anders Hejlsberg (Clip)If if we just let AI loose on, you know, what is it, like a half million lines of code that we have in the old compiler or somewhere between half a billion and a million, right? And asked it to translate it all. Well, I don't know that that would absolve us from then having go in and carefully examining every line that came out of it to make sure that there were no hallucinations, right? Unless you have 100% perfect test coverage, you probably still gotta go check all of that. Now, I think a a a better approach, quite honestly, would be enlist AI to write a program that helps you translate from TypeScript to Go.

Anders Hejlsberg (Clip)Because at that point, you can park the stochasticness in that program, and then you can get deterministic behavior whenever you run the program, which means you get the same transformation every time you run it, right? That's always the thing about AI that people forget. It's not deterministic, right? So you can't really trust that it's going to do the same thing twice.

ConorAnytime you can get it to write a thing that will then do something deterministically, like one, it's no longer costing you any money, but two, like you're unlocking determinism and like avoiding the non-determinism. And like that is a huge unlock. Like I have a ton of workflows that now just are just scripts that just run that like initially AI wrote, but now like AI never touches it and it just is humming along and opening PRs for me, and I click merge buttons and like I review it every once in a while just to make sure. But I feel like it's small things like these that I don't know.

ConorLike, if you're trying to get people that are less technical to use this stuff, they're not thinking like they don't like my actually my my brother-in-law is like trying to write some software for his company and he works in like the HVAC business. And I think to him, I had to really explain. Like, he's just like, oh, let's just get AI to do it. Let's get AI to do it. And it's all just like functions to him are all the same thing. And like to me, it's like, okay, if we can not depend on AI for this, that is better. Like when we need to do some optical character recognition or like analyze this photo, okay, we'll hit a Gemini endpoint or a codex endpoint or whatever.

ConorBut like if we can do this deterministically with some kind of formula, that is so much better from like a simplicity, because like every once in a while the AI is going to get it wrong. And then he's just like, well, why is it wrong? How can the AI is wrong? I thought AI is supposed to be good. And uh and I'm just like, well, you know, we need to minimize that like non-deterministic footprint that exists in our software program. And, anyways, that's like, yeah, I feel like this is a thing that like has been sitting in the back of my head. And I didn't really until you've just said it, Sean, and then I heard it on this other podcast. This, yeah, like the turn things into deterministic scripts.

ConorLike it's it's so much better.

BryceYes. So I saw this great talk at at this at Ghost in Paris. It was actually this presentation of this technical report, and they presented the this idea that there's these three different software paradigms now. There's traditional software, which has always existed. That's where you know the the reusable form of that is the source code, and it's deterministic, but not flexible. And then you have instant what they called instant software, which is where you're just prompting the AI, right? And so that is flexible, but it's not deterministic.

BryceAnd the thing that everybody's now starting to do is what they called elastic software, which is somewhere in the middle where you have a combination of source code and scripts and also skills. And that has the benefit that it is somewhat deterministic because parts of it are deterministic, but it's also flexible. And the example I keep giving is I when I started doing all my auto research work, I created a skill to do an export from you know a particular VM that I was using. And like 90% of the time, it would do everything I wanted and it would export it in the schema that I wanted.

BryceBut like, you know, five or 10% of the time, it would do things a little bit different, or it would call the name, it would give slightly different file names, you know, it would because it just it decided the the random noise and the model response decided to do something a little bit different than it did the other the rest of the time. And so what I did in, I could just write a script instead. But if I just wrote a script to do the export, then well, what if the node was you know out of disk space? Or what if it couldn't, you know, reach the place where it was supposed to export the data to?

BryceOr what if there was some file that the script didn't back up because it didn't know about, but was actually really important to back up. So if you instead have your deterministic export script and then you have a skill that wraps it that drives the script and also goes and checks whether there's anything that was missing or something, then you sort of get the best of both worlds where you get the flexibility and you get the determinism.

Sean ParentIt's definitely an unlock to get to the point where where you can say, okay, you know, we're doing this repeatedly. So it seems like like we can just write this as a as a script now. Do that. So uh I was also gonna say, you know, around the process standpoint, like I've got this thing I I posted in Slack the other day where I just saw it scrolling by in the in cloud code and the noise, and it was like, oh, I gave this task to to agent one, and agent one claimed success, but their their description of their of what they did makes no sense.

Sean ParentSo I looked and I so so I I looked, and they, you know, agent one didn't commit any code to git, and and yet claims they completed what they were doing, and it kind of goes on like this and it comes back and goes like okay, agent one is just completely hallucinating. I'm killing agent one and assigning this task to a new agent. And I, you know, if you're using these AI systems as kind of a one-off shot, any kind of harnessing in place to to have the agents reviewing what they're doing, you hit these states where you're like, like, oh, okay, well, you know, 90% of the time it's doing what I want, but 10% of the time it's just so far off in the weeds, uh uh, I'm lost.

Sean ParentAnd and it's I I kind of refer to it as it's double double check bookkeeping, right? Right? Why do accountants keep you know every everything is a is a credit and a debit? And basically you keep you know two tables going. And that's because if you make a mistake in one, you will see there's a contradiction. I didn't get the same result, so therefore there's a mistake somewhere in there. And and in what you're building, you want to make sure that your process is set up so that you're not relying on any piece of your system just getting it right with no double check.

ConorOh, right. I I think we're gonna that we're gonna see this more and more of these kind of like live self-healing systems that are some percentage of like, you know, 98% deterministic, and it's just it's just running, you know. But every once in a while there's some crash or some thing or some outage. I'm not sure if either of you run anything off of GitHub pages, but GitHub pages has become, or just GitHub in general, has become like so much more unreliable because everyone's everyone's doing what I'm doing, which is like it's free compute, right?

ConorLike GitHub actions. I never knew how to write GitHub action code, or I don't even know the language. I think it's just YAML, but like you can set up cron jobs and a ton of stuff, but like now because everyone's doing it, their their servers are falling over. And so, like once every four days, like my cron jobs that are running on GitHub Actions like fail. And I'm like, okay, like we we push the servers over again. But it's like at some point they're gonna set it up so that you know, the same way that Amazon and AWS like figured out Elastic Compute and they scaled stuff up, like it's gonna be the same thing with these software.

ConorLike, whenever there's an issue, things automatically get like spun out and they're like, What's the issue? And they're gonna diagnose it instantly. And not only are they gonna fix it, but they're gonna like harden the system of like, okay, well, what went wrong here? And like I I have this, like, I know it's a utopic, you know, maybe it's extropian, you know, look at like the future of software, but like even I and I I swear to God, I must be projecting, but there was this small bug in YouTube where I have the little speed up and the like the the shortcut is shift, you know, comma and shift period to like slow down and up the speed of your video.

ConorBut if you ever hit pause and then play again, it resets to one, which is like not the end of the world, but it's kind of irritating because it's like shift and then usually four more hits to get to 2.0 times speed, which is basically how I watch all my YouTube videos. And like somehow it's been broken for months and it's been fixed. And I would like to think that that is like, you know, people are like, Where's all the benefits of AI? I'd like to think that every time something gets slowly fixed now, it's AI that's do it's not humans, it's AI that's like gonna slowly make software.

ConorThat's my utopic view of the future is all these issues where we're turning off, you know, you're trying to get Chromecast work. Oh, God help us all, you know, Chromecast, you know, the most finicky piece. I just want the the TV to play on the TV, you know, it's just crazy. You know, what a world that that would work. And I imagine in the future we're just gonna click one button, it's gonna work, and people are gonna be like, wow, remember the days when like we had to get Connor and he spent 20 minutes and he just said, you know what, screw it. We're not gonna watch Disney Plus. We can't figure out how to get it to work. I guess we'll just watch Netflix again. Because admittedly, Netflix does seem to work much better than all the other alternatives, anyways.

ConorYeah, that that's uh that's that's my utopic vision, is that all the problems that humans have baked into all these software code bases are slowly gonna like heal over time. It's just a matter of button.

BryceBut the eight the agents, the agents, as we've been discussing all episode, they're just human. And so thus, why would we why why should we suspect that we will live in a perfect software world free?

ConorIt's exactly what Sean just described, though. It's like you get one to monitor the other one and they're doing it 24-7. It's not, you know, one person's working and then they asynchronously check a GitHub issue.

BryceIt's just like I've tried using this. I've had it end up in in loops where they're monitoring each other and they never agree on success. And I've I've seen this fall down too.

ConorWhat are your thoughts? You think do you think it's possible or is is Bryce, is there always going to be a flaw in the system?

Sean ParentUh I think, you know, systems like this at scale, you're always gonna find either like the specifications are are self-contradictory at some point, or the system just becomes chaotic at some point, right? And and you know, I think LLMs will have a better, at some point we'll do a better job at doing things like detecting those cases, but whether or not they can fix them is an in is an interesting problem. But but I tend to agree with you, which is the system is much more repeatable and scalable with the LLMs, right?

Sean ParentI can I can write down the rules and it can go do the thing and it can analyze way more software way more quickly than people can. And the challenge there is I think right now most people, the way they're using AI is they're creating the same crappy code that they would have written, like like most people in the industry, faster. And so the the problem is expanding right now. Uh but I also share your utopian vision of that can be fixed, that you know, uh cloud code or equivalent can ship with a solid engineering process baked in.

Sean ParentIt's got its superpower skill, which is probably the closest thing that Enthropic ships to uh an engineering process. But like I said, I think we're in we're in 1.0 territory on these kinds of systems. And and so I expect at the rate things are going, in a year from now, uh we'll be having the conversation about, you know, whatever, cloud code, software engineer app. And uh how amazing is that? And like I said, I think we'll get to the point as an industry we'll we'll we'll start to be able to measure the effectiveness of process, which is a very expensive and difficult thing to do with people.

Sean ParentYeah. Right. And um and so that will get to the point where where the system can iterate much faster and potentially start iterating on its own, right? Right. It can run its own experiments.

BryceYeah. That that's I think the next frontier, the the recursive systems or the auto-auto research. I think that's what everybody's starting to make the big shift to.

Sean ParentSo so yeah, you know, in my story about the the uh agent hallucinating and the other agent catching it, I just had this thought in the back of my head, which is so how much longer until the LLM, what I see scroll by is is you know, I asked this this person to go get me uh, you know, this additional resource that I need to keep running, and they didn't come back. So when they do come back, I'm gonna kill them and assign this task to somebody else.

ConorOh you you definitely like that's yeah, I definitely probably not the killing part, hopefully not, you know. Fingers crossed, we we get the alignment problem figured out, but definitely like I don't know, I I I live at the whatever the edge of this tech. And so my wife always reminds me, you know, most people don't aren't seeing the things you're seeing, they're not thinking, but just like I think like you know, self-driving is better than humans, and just like so much of this stuff is gonna become like like these sit these AIs, they are they're just better, you know, it's just safer, you know, they're they're better at writing code with like even if maybe on the first shot it it has as much bugs, as many bugs, it's able to you know fix them and iron them out a lot faster.

ConorAnd and yeah, it's a very exciting future. We'll keep our fingers crossed. We know that you have to go in uh like 10 minutes or so, maybe on uh, because we're probably definitely gonna release this. Might be our longest episode ever, as uh episode 300. Might not be as edited as heavily, but you know, it's a trade-off. You know, the listener gets an almost two-hour podcast with Sean Perrin. And maybe as a final question, you know, for the younger listeners out there, of which I know we have quite a few that are potentially either in school or about to leave school, you know, we talked about Dave and how he's retired and now he's focusing on music.

ConorAnd we talked about how you've still got lots of exciting stuff to work on. But by the time you know the 20 years rolls around and AI is better than everybody at everything, you're also gonna retire. And you mentioned a few other folks. I happen to know a guy at NVIDIA that said if this is really what engineering is gonna become, he has no interest in it. And he I won't call the individual out, but said that he's got multiple children, one of which is in music school, and he thinks that it's possible that that is the the big the, what do you call it, like the best outlook career-wise is for that student, where the other ones are in a more traditional STEM?

ConorI don't want to give away too much information, but that listener knows we're talking about uh them right now. What is the either advice? If you were in school right now watching this, like are you just panicking? Like what would you what would uh you now tell a younger version of you that isn't going to be retiring in the next 20 years, or at least not forcibly, I you know, I hope. I hope there will be still jobs for some people. What would you what would your advice or wisdom be? Yeah, in the the crazy times that we're about to we're that we're currently living through and we will continue to live through.

Sean ParentYeah, you know, my advice is always the same for kind of any student, which is the primary thing you can do in school is learn how to learn. And and so that you can adapt to change. And change right now is coming more rapidly. Than ever before. And so that's the key thing, right? Keep reading, learn the fundamentals, get a broad education. Don't just specialize in one thing, right?

Sean ParentSpend a little time in the philosophy department and the school of arts and not just in your in your STEM career. So that would be my advice. And then the other thing would be to start thinking about society and policy and get involved on that end. You know, the industrial revolution was a huge change from a societal and standpoint. And I think AI is going to be a bigger change. And I think just saying, you know, I don't want it, I don't like it, is not a productive stance.

Sean ParentSo getting involved with what are meaningful policies for how this can be rolled out and start to think about what is the role of people in society where we are no longer the most intelligent thing on the planet. Build the future the way you you want to see it. You know, right now I think our our our politicians and leaders are woefully ill-equipped. I don't think they they have any idea of what's coming. I think we just have the small glimpse of what's coming.

ConorDamn. Any books? I mean, now I love to ask uh everyone. I've been getting most of my book recommendations from Boris Cherney because he's read all the sci-fi of like, you know, that deals with these potential utopic or dystopic futures. Or even also, too, I I I would love to read a book that like details the industrial revolution from like different points of view, because there have been these shifts in society, but I'm I'm not a historian and also I haven't been a big reader of history other than like a few biographies here and there.

ConorSo I'm not sure. What would you book recommendations as well for for people that want to get started on that journey?

Sean ParentBoy, this is horrible because everything I've been reading lately has been papers. Uh I don't know. I don't have a good book recommendation, but I will think about that. So next time somebody asks me, next time you have me on the podcast, I'll already make a good book recommendation.

ConorOkay. We will maybe, maybe if you uh, because this will go out on Friday, if you think about them before Friday, we can put them in the show notes. Because I am I there seems to be like a lack of books. Like there's a ton of sci-fi books, but there's not a ton that like deal with what's going on because this has happened so quickly. And like obviously AI comes up time and time again, but not not uh I actually probably there are a bunch of books out there. I just I'm I'm less well read than I should be, probably at my age. More well read than the average person, but that still doesn't say much because there's a lot of people in society.

ConorRight, Bryce, do you have book recommendations? I know you've read the Asimov books.

BryceYeah, that's been the last thing I've read recently. I've been so I've been so busy with everything that's happening right now. I have not been I haven't read any books in a while.

ConorYeah. I I could recommend one, but it's like it's like five percent an erotica novel, which is not great.

BryceWell, nice now you gotta recommend it.

ConorAll right, all right. It's accelerando. I'm in the middle of three books. One parenting book, one like I don't know, self-help, you know, better mental health book, and then uh this book that's like AI. It's Accelerando by Neil Strauss, which is on a lot of these lists. If you ask AI, like, oh, I read you know, this book, that book, this book, what next? It almost almost always gets recommended. The AI did not warn me though, which is not that I'm against reading about erotica or like, you know, what do you call it, like Fifty Shades of Grey kind of stuff.

ConorBut I would just I, you know, every time it starts to start reading this book. Oh, because I I'm just trying to consume all of the uh the novels about like, you know, AI takeoff and and you know, like cloud uploading your brains and stuff. Trying to get ready, you know? I feel like that's the closest thing you can get to an education in the future of AI, because you know, there's there's nothing out there really that is like addressing this exact moment. All right, should we let you go, Sean? Is there any last things you want to say? Um, thank you so much for taking two hours of of your day.

ConorUh I mean this has been fantastic. I mean, uh, there's so many times you were you were talking, and then I was like, oh, that's the cold open. I was like, oh my god, that's the cold open. Oh my how am I gonna get out? I'm gonna have like four different cold opens for this show.

BryceWe got it, we gotta, we gotta say something about episode 300.

Sean ParentYeah, so like congrats on hitting 300 on the podcast here. This is this is great. And thanks for having me on for the 300th episode.

BryceNow you have years has this podcast been around.

ConorIs it like well, 52 weeks in a year? So it's coming up on six years in November. And uh yeah, the key is the key of consistency is really chunking these up into smaller things because it's so much easier to record once and get like three episodes than it is to like what what CPPCast did for that many years in a row. Every single episode, like recording was a single episode. Although, you know, I have been thinking about like future plans if coding's not a thing, and uh maybe full-time talking to people is not a bad, you know.

ConorI don't make any money from this right now, but I could pivot and try to. And uh, you know, like I said, connecting with people, it's I would I would love to do this on a more regular basis. And the problem is, is I don't like ads, so you gotta find a different way. And I don't want it really to charge people for this stuff. So if you don't like ads and you don't like charging people, yeah, it's kind of hard to make a living off of it. Yep. All right, well, we will let you go. Thank you so much, Sean. We will do this again. And also, too, I are you're wearing the CPV con uh shirt. Are you going to conferences or speaking?

ConorIs there last if people want to find you places, is there places they can do that?

Sean ParentNo current plans. Uh, you know, uh, invite me, right? Somewhere.

ConorAll right. You heard it, conference organizers. Invite Sean, he'll be there. And if we uh if we hear from you, we'll announce it to make sure that wherever you're going, ADSP listeners can uh know where to find you. 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. Thanks for listening. We hope you enjoyed and have a great day.

BryceLow quality, high quality. That is the tagline of our podcast.

ConorThat's not the tagline. Our tagline is chaos with sprinkles of information.

Open the transcript file

Hosts and Guests

Guests

  • Sean Parent Guest Inferred

Credit the people on this episode

Be the first to rate this episode

More episodes

All episodes
  1. Episode 313: C++26 Reflection vs CRTP, AI, Kids & More with Zach Laine

    Nov 20, 202647 minAudio

    In this episode, Conor and Bryce chat with Zach Laine about C++26 Reflection vs CRTP, AI, kids & more. Link to Episode 313 on Website Discuss this episode, leave a comment, or ask a question (on GitHub) Socials ADSP:...

    • Apple Podcasts

    Credit the people on this episode

  2. Episode 312: The C++26 Contracts Fiasco

    Nov 13, 202652 minAudio

    In this episode, Conor and Bryce chat with Zach Laine about the C++26 contracts fiasco. Link to Episode 312 on Website Discuss this episode, leave a comment, or ask a question (on GitHub) Socials ADSP: The Podcast:...

    • Apple Podcasts

    Credit the people on this episode

  3. Episode 311: Career Changes, GPUs & More with Zach Laine

    Nov 6, 202628 minAudio

    In this episode, Conor and Bryce talk with Zach Laine about his career and the career changes he has made. Link to Episode 311 on Website Discuss this episode, leave a comment, or ask a question (on GitHub) Socials...

    • Apple Podcasts

    Credit the people on this episode

  4. Episode 310: Leaving NVIDIA for... ?

    Oct 30, 202624 minAudio

    In this episode, Conor and Bryce talk about Bryce's next chapter and where he is leaving NVIDIA for. Link to Episode 310 on Website Discuss this episode, leave a comment, or ask a question (on GitHub) Socials ADSP: The...

    • Apple Podcasts

    Credit the people on this episode

  5. Episode 309: Default Construction & CppCon 2026 with Jason Turner

    Oct 23, 202629 minAudio

    In this episode, Conor and Ben chat with Jason Turner about default construction in C++. Link to Episode 309 on Website Discuss this episode, leave a comment, or ask a question (on GitHub) Socials ADSP: The Podcast:...

    • Apple Podcasts

    Credit the people on this episode