Learning to Code with AI and Steve Klabnik

There's something new from our sponsor, There's something new from our sponsor, Text Control. For decades, TXT Controls Text Control. For decades, TXT Controls Text Control. For decades, TXT Controls rendering was tied to Windows rendering was tied to Windows rendering was tied to Windows functionality, but now it's a new era. functionality, but now it's a new era. functionality, but now it's a new era. TXT text control is platform TXT text control is platform TXT text control is platform independent. You can run your .NET independent. You can run your .NET independent. You can run your .NET applications on Windows or Linux. Deploy applications on Windows or Linux. Deploy applications on Windows or Linux. Deploy with Docker containers, Kubernetes, or with Docker containers, Kubernetes, or with Docker containers, Kubernetes, or host directly in Azure App Services. host directly in Azure App Services. host directly in Azure App Services. Seamlessly integrate document editing, Seamlessly integrate document editing, Seamlessly integrate document editing, signing, collaboration, and PDF signing, collaboration, and PDF signing, collaboration, and PDF processing into your ASP.NET Core and processing into your ASP.NET Core and processing into your ASP.NET Core and Angular applications. Are you ready to Angular applications. Are you ready to Angular applications. Are you ready to see it in action? Check out the live see it in action? Check out the live see it in action? Check out the live demo at demos.extcontrol.com. Hey friends, I'm Scott Hansselman. This Hey friends, I'm Scott Hansselman. This is another episode of Hansel Minutes and is another episode of Hansel Minutes and is another episode of Hansel Minutes and today I have the pleasure of chatting today I have the pleasure of chatting today I have the pleasure of chatting with Steve Clavnik. He's a software with Steve Clavnik. He's a software with Steve Clavnik. He's a software engineering manager at Oxide, the engineering manager at Oxide, the engineering manager at Oxide, the co-author of the Rust book. You were a co-author of the Rust book. You were a co-author of the Rust book. You were a legend in the Ruby community. You only legend in the Ruby community. You only legend in the Ruby community. You only do work in uh programming languages that do work in uh programming languages that do work in uh programming languages that start with R. Is that a fair statement?

start with R. Is that a fair statement? start with R. Is that a fair statement? >> Apparently. Yeah. Yeah. The other funny >> Apparently. Yeah. Yeah. The other funny >> Apparently. Yeah. Yeah. The other funny thing is I have a Ruby tattoo uh on my thing is I have a Ruby tattoo uh on my thing is I have a Ruby tattoo uh on my wrist and then I have a little pearl wrist and then I have a little pearl wrist and then I have a little pearl camel up here. So, people were asking me camel up here. So, people were asking me camel up here. So, people were asking me when am I going to get a rust tattoo and when am I going to get a rust tattoo and when am I going to get a rust tattoo and I say I only get tattoos of languages I I say I only get tattoos of languages I I say I only get tattoos of languages I don't use anymore. So, uh you you'll don't use anymore. So, uh you you'll don't use anymore. So, uh you you'll know that's once I move on someday. Uh, know that's once I move on someday. Uh, know that's once I move on someday. Uh, >> if we spot you on the street with a rust >> if we spot you on the street with a rust >> if we spot you on the street with a rust tattoo, we'll know it's the beginning of tattoo, we'll know it's the beginning of tattoo, we'll know it's the beginning of the end. the end. the end. >> Yeah, exactly. >> Yeah, exactly. >> Yeah, exactly. >> Oh my goodness. So, you and I have known >> Oh my goodness. So, you and I have known >> Oh my goodness. So, you and I have known each other on the internet for a very each other on the internet for a very each other on the internet for a very long time and we kind of like have these long time and we kind of like have these long time and we kind of like have these elliptical orbits and every couple of elliptical orbits and every couple of elliptical orbits and every couple of years we kind of come together for years we kind of come together for years we kind of come together for various reasons. And um I declared various reasons. And um I declared various reasons. And um I declared myself on Blue Sky a couple of weeks ago myself on Blue Sky a couple of weeks ago myself on Blue Sky a couple of weeks ago a bit of an AI vegan. a bit of an AI vegan. a bit of an AI vegan. >> And people did some people some people >> And people did some people some people >> And people did some people some people were like, "Yes, I know exactly what were like, "Yes, I know exactly what were like, "Yes, I know exactly what that means." And other people were like, that means." And other people were like, that means." And other people were like, "What? What do you mean vegan?" And it's "What? What do you mean vegan?" And it's "What? What do you mean vegan?" And it's like, well, there's things that I choose like, well, there's things that I choose like, well, there's things that I choose to eat and there's things that I choose to eat and there's things that I choose to eat and there's things that I choose not to eat. And you know, when I promote not to eat. And you know, when I promote not to eat. And you know, when I promote AI things or mention AI things, some AI things or mention AI things, some AI things or mention AI things, some people on online are like anti. This is people on online are like anti. This is people on online are like anti. This is bad. I will not use it. It is it is not bad. I will not use it. It is it is not bad. I will not use it. It is it is not ethical in any flavor. But I think ethical in any flavor. But I think ethical in any flavor. But I think there's a slider bar of like what AI can there's a slider bar of like what AI can there's a slider bar of like what AI can do and what I will accept and what I do and what I will accept and what I do and what I will accept and what I will allow. Where are you within the AI will allow. Where are you within the AI will allow. Where are you within the AI veganism slider bar?

veganism slider bar? veganism slider bar? >> Yeah. So I mean in I'm in the same place >> Yeah. So I mean in I'm in the same place >> Yeah. So I mean in I'm in the same place in general in the sense that uh like I I in general in the sense that uh like I I in general in the sense that uh like I I use AI tools regularly but that's like use AI tools regularly but that's like use AI tools regularly but that's like for programming. I have a lot of for programming. I have a lot of for programming. I have a lot of concerns about AI and how it's going to concerns about AI and how it's going to concerns about AI and how it's going to impact everything. I think it's funny impact everything. I think it's funny impact everything. I think it's funny the the veganism thing first of all the the veganism thing first of all the the veganism thing first of all because you're totally right that like because you're totally right that like because you're totally right that like there's a sort of I'm choosing to eat there's a sort of I'm choosing to eat there's a sort of I'm choosing to eat some things and not others and there's some things and not others and there's some things and not others and there's like kind of like an ethical component like kind of like an ethical component like kind of like an ethical component to it but I think a lot of people think to it but I think a lot of people think to it but I think a lot of people think about it as abstaining and they have about it as abstaining and they have about it as abstaining and they have would assume by saying AI vegan that you would assume by saying AI vegan that you would assume by saying AI vegan that you mean that you don't do anything with it mean that you don't do anything with it mean that you don't do anything with it as opposed to like vegans do eat a as opposed to like vegans do eat a as opposed to like vegans do eat a pescatarian. pescatarian. pescatarian. >> Yeah, exactly. Like there's some sort of >> Yeah, exactly. Like there's some sort of >> Yeah, exactly. Like there's some sort of like I mean I think the ethical part and like I mean I think the ethical part and like I mean I think the ethical part and the veganism like makes total sense of the veganism like makes total sense of the veganism like makes total sense of the analogy but I also think it's funny the analogy but I also think it's funny the analogy but I also think it's funny because I received a DM a couple days because I received a DM a couple days because I received a DM a couple days ago. I had talked about how like um on a ago. I had talked about how like um on a ago. I had talked about how like um on a different podcast about how like uh one different podcast about how like uh one different podcast about how like uh one of the concerns about environment stuff of the concerns about environment stuff of the concerns about environment stuff is like it's like well I eat beef and is like it's like well I eat beef and is like it's like well I eat beef and like beef is like pretty bad for the like beef is like pretty bad for the like beef is like pretty bad for the environment and somebody messaged me environment and somebody messaged me environment and somebody messaged me they DM'd me and said like you know well they DM'd me and said like you know well they DM'd me and said like you know well you admitted you eat beef so I'm not you admitted you eat beef so I'm not you admitted you eat beef so I'm not taking any of their appear opinions taking any of their appear opinions taking any of their appear opinions seriously so bye and block me seriously so bye and block me seriously so bye and block me preemptively and so I guess that like preemptively and so I guess that like preemptively and so I guess that like the regular vegans are also mad about the regular vegans are also mad about the regular vegans are also mad about the AI veganism aspect too. So, I just the AI veganism aspect too. So, I just the AI veganism aspect too. So, I just thought was funny. And to be clear, I thought was funny. And to be clear, I thought was funny. And to be clear, I also spent a portion of my life being also spent a portion of my life being also spent a portion of my life being vegan. So, this is not inherently to vegan. So, this is not inherently to vegan. So, this is not inherently to knock on. Yeah. I had a um there's a knock on. Yeah. I had a um there's a knock on. Yeah. I had a um there's a whole lot, you know, punk rock and whole lot, you know, punk rock and whole lot, you know, punk rock and there's a whole section of punk rock there's a whole section of punk rock there's a whole section of punk rock people that are vegan adjacent. And so, people that are vegan adjacent. And so, people that are vegan adjacent. And so, I was living in Los Angeles in like a I was living in Los Angeles in like a I was living in Los Angeles in like a punk house where everyone was vegan and punk house where everyone was vegan and punk house where everyone was vegan and so, you know, it's how it goes.

so, you know, it's how it goes. so, you know, it's how it goes. >> Very straight edge. >> Very straight edge. >> Very straight edge. >> Yeah. I literally have straightedge >> Yeah. I literally have straightedge >> Yeah. I literally have straightedge tattoo as well, actually, although I'm tattoo as well, actually, although I'm tattoo as well, actually, although I'm very much anymore. Um but yeah. Yeah, very much anymore. Um but yeah. Yeah, very much anymore. Um but yeah. Yeah, totally. So, totally. So, totally. So, >> well, for me it was like I don't see >> well, for me it was like I don't see >> well, for me it was like I don't see business value or a reason to do any business value or a reason to do any business value or a reason to do any kind of AI video generation. And every kind of AI video generation. And every kind of AI video generation. And every time Google announces something horrible time Google announces something horrible time Google announces something horrible where you can Oh, now that like they where you can Oh, now that like they where you can Oh, now that like they just announced real time AI video just announced real time AI video just announced real time AI video generation. generation. generation. >> Yeah. >> Yeah. >> Yeah. >> And I just there's no reason for that >> And I just there's no reason for that >> And I just there's no reason for that other than it's an interesting math other than it's an interesting math other than it's an interesting math problem. problem. problem. >> Yeah. I think this this gets in an area >> Yeah. I think this this gets in an area >> Yeah. I think this this gets in an area where I guess the other context for my where I guess the other context for my where I guess the other context for my like opinions about AI is I was very like opinions about AI is I was very like opinions about AI is I was very anti until a couple months ago. I was anti until a couple months ago. I was anti until a couple months ago. I was like, "Absolutely." like, "Absolutely." like, "Absolutely." >> So, you were that person that >> So, you were that person that >> So, you were that person that >> Yeah, I was that person. Um, and that's >> Yeah, I was that person. Um, and that's >> Yeah, I was that person. Um, and that's partially because I had tried it when it partially because I had tried it when it partially because I had tried it when it first came out and I thought this is a first came out and I thought this is a first came out and I thought this is a fun parlor trick, but not really much fun parlor trick, but not really much fun parlor trick, but not really much more than that. And the problem is more than that. And the problem is more than that. And the problem is technology updates itself pretty technology updates itself pretty technology updates itself pretty quickly. And so, essentially, it was the quickly. And so, essentially, it was the quickly. And so, essentially, it was the release of like Claude 4. And I was release of like Claude 4. And I was release of like Claude 4. And I was like, you know, I want to be an informed like, you know, I want to be an informed like, you know, I want to be an informed hater, so I should like actually give hater, so I should like actually give hater, so I should like actually give this like a real try again. And then I this like a real try again. And then I this like a real try again. And then I was like, this is good actually and I was like, this is good actually and I was like, this is good actually and I kind of like it. And so, it became this kind of like it. And so, it became this kind of like it. And so, it became this really big like, you know, thing. So, so really big like, you know, thing. So, so really big like, you know, thing. So, so anyway, there's also there's also that.

anyway, there's also there's also that. anyway, there's also there's also that. So, I'm not trying to like uh you know, So, I'm not trying to like uh you know, So, I'm not trying to like uh you know, bismerch anyone's opinions. You should bismerch anyone's opinions. You should bismerch anyone's opinions. You should have whatever opinions you want to have have whatever opinions you want to have have whatever opinions you want to have about this stuff, but I do think that about this stuff, but I do think that about this stuff, but I do think that like yes, for coding is a very different like yes, for coding is a very different like yes, for coding is a very different question than for other things. The question than for other things. The question than for other things. The video stuff, I like agree that I think video stuff, I like agree that I think video stuff, I like agree that I think that that's some area. It's an that that's some area. It's an that that's some area. It's an interesting math problem. I think that interesting math problem. I think that interesting math problem. I think that like the way they're kind of going after like the way they're kind of going after like the way they're kind of going after video games is kind of interesting. video games is kind of interesting. video games is kind of interesting. Like, can we respond in, you know, with Like, can we respond in, you know, with Like, can we respond in, you know, with to to in semi-real time to like players to to in semi-real time to like players to to in semi-real time to like players trying to move throughout a space? But trying to move throughout a space? But trying to move throughout a space? But again, it's like interesting. You know, again, it's like interesting. You know, again, it's like interesting. You know, the other big story today is like the other big story today is like the other big story today is like related to that. I know this is not related to that. I know this is not related to that. I know this is not going to be out literally the same day, going to be out literally the same day, going to be out literally the same day, but uh Grock has a spicy mode and it but uh Grock has a spicy mode and it but uh Grock has a spicy mode and it made naked pictures of Taylor Swift and made naked pictures of Taylor Swift and made naked pictures of Taylor Swift and like like like >> yeah, I a couple of hours ago. So like >> yeah, I a couple of hours ago. So like >> yeah, I a couple of hours ago. So like when did responsible like like I work at when did responsible like like I work at when did responsible like like I work at Microsoft in my day job and I'm in a lot Microsoft in my day job and I'm in a lot Microsoft in my day job and I'm in a lot of meetings and in every meeting like of meetings and in every meeting like of meetings and in every meeting like okay, let's talk about where responsible okay, let's talk about where responsible okay, let's talk about where responsible AI fits in. Like nothing goes out AI fits in. Like nothing goes out AI fits in. Like nothing goes out without a filter on front. It's without a filter on front. It's without a filter on front. It's effectively a firewall. How does Grock effectively a firewall. How does Grock effectively a firewall. How does Grock let that content in and then once it let that content in and then once it let that content in and then once it gets in and it makes something naughty, gets in and it makes something naughty, gets in and it makes something naughty, why is it being allowed out? Like that why is it being allowed out? Like that why is it being allowed out? Like that does not seem okay by any means.

does not seem okay by any means. does not seem okay by any means. >> Yeah. And it's I think it's like, you >> Yeah. And it's I think it's like, you >> Yeah. And it's I think it's like, you know, I don't I don't want to say Taylor know, I don't I don't want to say Taylor know, I don't I don't want to say Taylor Swift doesn't matter. I'm not here to Swift doesn't matter. I'm not here to Swift doesn't matter. I'm not here to argue the Swifties and she is also argue the Swifties and she is also argue the Swifties and she is also human. So it does matter on some level human. So it does matter on some level human. So it does matter on some level as a member of the Beehive. I can as a member of the Beehive. I can as a member of the Beehive. I can recognize what feels like. But I think recognize what feels like. But I think recognize what feels like. But I think that like celebrities have a certain that like celebrities have a certain that like celebrities have a certain amount of like understanding that they amount of like understanding that they amount of like understanding that they are looked at by everyone in a certain are looked at by everyone in a certain are looked at by everyone in a certain like way you know like this isn't while like way you know like this isn't while like way you know like this isn't while it is new while it's like while it's a it is new while it's like while it's a it is new while it's like while it's a thing and it's bad uh I think that like thing and it's bad uh I think that like thing and it's bad uh I think that like the fact that this technology becoming the fact that this technology becoming the fact that this technology becoming accessible so that like for example accessible so that like for example accessible so that like for example normal people who are not up on stage in normal people who are not up on stage in normal people who are not up on stage in front of thousands of people can have front of thousands of people can have front of thousands of people can have deep fakes made of them like and that deep fakes made of them like and that deep fakes made of them like and that kind of stuff I think is going to be kind of stuff I think is going to be kind of stuff I think is going to be more like society a problem even if like more like society a problem even if like more like society a problem even if like again just to be clear it is a big again just to be clear it is a big again just to be clear it is a big problem and I hope she sues and takes problem and I hope she sues and takes problem and I hope she sues and takes all of Elon's money like it's not an all of Elon's money like it's not an all of Elon's money like it's not an okay thing to do but I think that like okay thing to do but I think that like okay thing to do but I think that like that happening at scale is the thing that happening at scale is the thing that happening at scale is the thing that I'm like more worried about in a in that I'm like more worried about in a in that I'm like more worried about in a in a like bigger picture sense. Um like I a like bigger picture sense. Um like I a like bigger picture sense. Um like I just finally I think have my 80-year-old just finally I think have my 80-year-old just finally I think have my 80-year-old mother where she can recognize fishing mother where she can recognize fishing mother where she can recognize fishing and now they're going to call her and and now they're going to call her and and now they're going to call her and say that I've been kidnapped and I'm in say that I've been kidnapped and I'm in say that I've been kidnapped and I'm in like I need her to like wire me money.

like I need her to like wire me money. like I need her to like wire me money. >> Yeah. Absolutely. And you know, for for >> Yeah. Absolutely. And you know, for for >> Yeah. Absolutely. And you know, for for you and I that are not, you know, Taylor you and I that are not, you know, Taylor you and I that are not, you know, Taylor Swift, but also aren't like somebody who Swift, but also aren't like somebody who Swift, but also aren't like somebody who doesn't have any social media at all, doesn't have any social media at all, doesn't have any social media at all, like they're absolutely is enough audio like they're absolutely is enough audio like they're absolutely is enough audio and video of both of us freely available and video of both of us freely available and video of both of us freely available on the internet for pretty much anyone on the internet for pretty much anyone on the internet for pretty much anyone to make copies of. And so, you know, to make copies of. And so, you know, to make copies of. And so, you know, that's like a an interesting thing. So, that's like a an interesting thing. So, that's like a an interesting thing. So, yeah. So, I'm like definitely worried yeah. So, I'm like definitely worried yeah. So, I'm like definitely worried about some stuff like that. And I don't, about some stuff like that. And I don't, about some stuff like that. And I don't, you know, I don't know how it's going to you know, I don't know how it's going to you know, I don't know how it's going to play out like but I do think it's a play out like but I do think it's a play out like but I do think it's a thing we're going to have to kind of thing we're going to have to kind of thing we're going to have to kind of like reckon with. I'm sort of I remember like reckon with. I'm sort of I remember like reckon with. I'm sort of I remember people sort of declaring like that people sort of declaring like that people sort of declaring like that literacy was going to be dead when literacy was going to be dead when literacy was going to be dead when Google and Wikipedia happened. You know, Google and Wikipedia happened. You know, Google and Wikipedia happened. You know, it was like okay like you can you can it was like okay like you can you can it was like okay like you can you can you know what happens when you read a you know what happens when you read a you know what happens when you read a web page and it has something bad on it. web page and it has something bad on it. web page and it has something bad on it. And I think we've sort of figured out And I think we've sort of figured out And I think we've sort of figured out that the answer to that is bad things do that the answer to that is bad things do that the answer to that is bad things do happen actually. But like also we did happen actually. But like also we did happen actually. But like also we did figure out some level of like ways of figure out some level of like ways of figure out some level of like ways of getting around that society or at least getting around that society or at least getting around that society or at least like you know I think people sort of a like you know I think people sort of a like you know I think people sort of a joke you being an older millennial it joke you being an older millennial it joke you being an older millennial it was like it's kind of funny that the was like it's kind of funny that the was like it's kind of funny that the boomers all told us don't believe boomers all told us don't believe boomers all told us don't believe anything you read on the internet and anything you read on the internet and anything you read on the internet and now they're the only ones on Facebook now they're the only ones on Facebook now they're the only ones on Facebook you know reading all this you know you know reading all this you know you know reading all this you know >> don't get into strangers how cars and >> don't get into strangers how cars and >> don't get into strangers how cars and now we we that we do that regularly.

now we we that we do that regularly. now we we that we do that regularly. Yeah, absolutely. So, Yeah, absolutely. So, Yeah, absolutely. So, >> so we like we've sort of handled it, but >> so we like we've sort of handled it, but >> so we like we've sort of handled it, but we sort of haven't, you know, and so we sort of haven't, you know, and so we sort of haven't, you know, and so that's kind of like uh I think the trick that's kind of like uh I think the trick that's kind of like uh I think the trick is that like humans are very resilient is that like humans are very resilient is that like humans are very resilient and I kind of think I I maybe a little and I kind of think I I maybe a little and I kind of think I I maybe a little like optimistic about the like like optimistic about the like like optimistic about the like resiliency of the human spirit and like resiliency of the human spirit and like resiliency of the human spirit and like we'll get through this like anything we'll get through this like anything we'll get through this like anything else. But I don't know. We'll see. I'm else. But I don't know. We'll see. I'm else. But I don't know. We'll see. I'm definitely not there there are many ways definitely not there there are many ways definitely not there there are many ways in which these things are very cool, but in which these things are very cool, but in which these things are very cool, but there's also a lot of ways in which I there's also a lot of ways in which I there's also a lot of ways in which I don't know. Yeah. Basically, don't know. Yeah. Basically, don't know. Yeah. Basically, >> I've been told by my kids that I'm >> I've been told by my kids that I'm >> I've been told by my kids that I'm toxically positive. Um, so I do have toxically positive. Um, so I do have toxically positive. Um, so I do have like a it'll be okay, but I think that's like a it'll be okay, but I think that's like a it'll be okay, but I think that's also how I wake up every morning and also how I wake up every morning and also how I wake up every morning and tell myself that everything will be tell myself that everything will be tell myself that everything will be okay. But it does bring to question what okay. But it does bring to question what okay. But it does bring to question what is our value as a society for human is our value as a society for human is our value as a society for human creativity. If someone builds a style creativity. If someone builds a style creativity. If someone builds a style for 20 years, you know, alone in their for 20 years, you know, alone in their for 20 years, you know, alone in their studio apartment throwing paint at a studio apartment throwing paint at a studio apartment throwing paint at a wall and then I can train something in a wall and then I can train something in a wall and then I can train something in a weekend on their 20 years of style and weekend on their 20 years of style and weekend on their 20 years of style and then generate that. That's a thing. So then generate that. That's a thing. So then generate that. That's a thing. So then the question is, can I write kernel then the question is, can I write kernel then the question is, can I write kernel code now as good as Lionus does?

code now as good as Lionus does? code now as good as Lionus does? >> Yeah, I it's it's definitely very >> Yeah, I it's it's definitely very >> Yeah, I it's it's definitely very interesting. Do you do you know about interesting. Do you do you know about interesting. Do you do you know about the history of source code and copyright the history of source code and copyright the history of source code and copyright actually? Because it's kind of a cool actually? Because it's kind of a cool actually? Because it's kind of a cool story, right? It was almost so for those story, right? It was almost so for those story, right? It was almost so for those that don't know essentially like what that don't know essentially like what that don't know essentially like what 1978 was the big copyright act, right? I 1978 was the big copyright act, right? I 1978 was the big copyright act, right? I think and essentially software was, you think and essentially software was, you think and essentially software was, you know, just becoming a thing when that know, just becoming a thing when that know, just becoming a thing when that happened. And effectively it was they happened. And effectively it was they happened. And effectively it was they needed to get the law passed but they needed to get the law passed but they needed to get the law passed but they were like we clearly need to address were like we clearly need to address were like we clearly need to address this software thing. And so they set up this software thing. And so they set up this software thing. And so they set up a commission that was like kind of patch a commission that was like kind of patch a commission that was like kind of patch the law in later. The law said like and the law in later. The law said like and the law in later. The law said like and we're going to start a commission and we're going to start a commission and we're going to start a commission and they're going to investigate the they're going to investigate the they're going to investigate the question about software. And that's question about software. And that's question about software. And that's because like recipes can't be because like recipes can't be because like recipes can't be copyrighted. They're they're just copyrighted. They're they're just copyrighted. They're they're just they're things that exist. You can't they're things that exist. You can't they're things that exist. You can't copyright them. This is why everybody copyright them. This is why everybody copyright them. This is why everybody talks about you know their wonderful talks about you know their wonderful talks about you know their wonderful trip to you know whatever to get you trip to you know whatever to get you trip to you know whatever to get you know that's all because that text is know that's all because that text is know that's all because that text is copyrightable even if the recipe is like copyrightable even if the recipe is like copyrightable even if the recipe is like not right. But like also novels and not right. But like also novels and not right. But like also novels and books can be copywritten. And so the books can be copywritten. And so the books can be copywritten. And so the question for that committee was kind of question for that committee was kind of question for that committee was kind of like is source code closer to a recipe like is source code closer to a recipe like is source code closer to a recipe because it's sort of like a recipe for because it's sort of like a recipe for because it's sort of like a recipe for the computer or is it like a creative the computer or is it like a creative the computer or is it like a creative work like like a book? And so they kind work like like a book? And so they kind work like like a book? And so they kind of came down on the side of you know of came down on the side of you know of came down on the side of you know okay this is like a book and it should okay this is like a book and it should okay this is like a book and it should be copyrightable. But there was a moment be copyrightable. But there was a moment be copyrightable. But there was a moment where like we almost didn't even have where like we almost didn't even have where like we almost didn't even have those things at all. And I think that's those things at all. And I think that's those things at all. And I think that's a really interesting kind of like what a really interesting kind of like what a really interesting kind of like what if you know what how things would be if you know what how things would be if you know what how things would be different if that had changed. But yeah, different if that had changed. But yeah, different if that had changed. But yeah, so like I'm also a little skeptical of so like I'm also a little skeptical of so like I'm also a little skeptical of copyright in general. I think I kind of, copyright in general. I think I kind of, copyright in general. I think I kind of, you know, being an elder millennial came you know, being an elder millennial came you know, being an elder millennial came up during a lot of the like, you know, up during a lot of the like, you know, up during a lot of the like, you know, information wants to be free kind of information wants to be free kind of information wants to be free kind of like, you know, Napster era kind of like like, you know, Napster era kind of like like, you know, Napster era kind of like attitudes. And I think it's really

attitudes. And I think it's really attitudes. And I think it's really interesting how like uh because interesting how like uh because interesting how like uh because copyright is one of the only sort of copyright is one of the only sort of copyright is one of the only sort of like effective tools that people have like effective tools that people have like effective tools that people have around these things. It seems like a lot around these things. It seems like a lot around these things. It seems like a lot of people are really interested in of people are really interested in of people are really interested in strengthening copyright. And I don't strengthening copyright. And I don't strengthening copyright. And I don't think that's like really great for think that's like really great for think that's like really great for society necessarily either. But it's society necessarily either. But it's society necessarily either. But it's like it's also true that I want people like it's also true that I want people like it's also true that I want people to be able to make livingings from to be able to make livingings from to be able to make livingings from creative work. You know, I was talking creative work. You know, I was talking creative work. You know, I was talking with somebody about this recently and he with somebody about this recently and he with somebody about this recently and he was saying like, you know, I really want was saying like, you know, I really want was saying like, you know, I really want like a band to be able to like uh, you like a band to be able to like uh, you like a band to be able to like uh, you know, make make a living. And so I feel know, make make a living. And so I feel know, make make a living. And so I feel like if anybody uses their style of like if anybody uses their style of like if anybody uses their style of music, they should have to pay them. And music, they should have to pay them. And music, they should have to pay them. And I was like, well, scenes happen when a I was like, well, scenes happen when a I was like, well, scenes happen when a bunch of different bands that kind of bunch of different bands that kind of bunch of different bands that kind of sound similarish, you know, like play sound similarish, you know, like play sound similarish, you know, like play off each other and build something off each other and build something off each other and build something better and you get like more music out better and you get like more music out better and you get like more music out of it. And so if you required like the of it. And so if you required like the of it. And so if you required like the first punk band to be paid every time first punk band to be paid every time first punk band to be paid every time the second punk band played a show, like the second punk band played a show, like the second punk band played a show, like you wouldn't have punk music in the same you wouldn't have punk music in the same you wouldn't have punk music in the same way that we do now. And so I think way that we do now. And so I think way that we do now. And so I think there's a weird interesting tension there's a weird interesting tension there's a weird interesting tension there between like, you know, you got to there between like, you know, you got to there between like, you know, you got to find a way to make people have a living, find a way to make people have a living, find a way to make people have a living, especially people that are doing especially people that are doing especially people that are doing creative works, but also like it's also creative works, but also like it's also creative works, but also like it's also not true that people being able to not true that people being able to not true that people being able to solely own creative works is like a good solely own creative works is like a good solely own creative works is like a good thing for society. And like balancing thing for society. And like balancing thing for society. And like balancing that is what copyright tries to do. And that is what copyright tries to do. And that is what copyright tries to do. And I don't really know if it's like up to I don't really know if it's like up to I don't really know if it's like up to the task of this kind of future, I the task of this kind of future, I the task of this kind of future, I guess. Um, yeah. So that's like one way guess. Um, yeah. So that's like one way guess. Um, yeah. So that's like one way I like think about this problem.

I like think about this problem. I like think about this problem. >> Yeah. Like pre-1970s software was a >> Yeah. Like pre-1970s software was a >> Yeah. Like pre-1970s software was a service. It wasn't a product. It wasn't service. It wasn't a product. It wasn't service. It wasn't a product. It wasn't sold separately. You'd buy a mainframe. sold separately. You'd buy a mainframe. sold separately. You'd buy a mainframe. You'd buy a fridge from IBM and it would You'd buy a fridge from IBM and it would You'd buy a fridge from IBM and it would come with the source code and you would come with the source code and you would come with the source code and you would share it and it would be totally open. share it and it would be totally open. share it and it would be totally open. And academia or working at NASA, you And academia or working at NASA, you And academia or working at NASA, you know, early hacker communities, it was know, early hacker communities, it was know, early hacker communities, it was all shared. And then that when that all shared. And then that when that all shared. And then that when that commission happened, the commission on commission happened, the commission on commission happened, the commission on new technological uses of copyrighted new technological uses of copyrighted new technological uses of copyrighted work, it took six years for them to work, it took six years for them to work, it took six years for them to decide that this was a thing. And uh and decide that this was a thing. And uh and decide that this was a thing. And uh and then of course that literally in then of course that literally in then of course that literally in reaction to that copy left and GNU fired reaction to that copy left and GNU fired reaction to that copy left and GNU fired up and it's still to this day there's up and it's still to this day there's up and it's still to this day there's OSS and there's FOSS and then there's OSS and there's FOSS and then there's OSS and there's FOSS and then there's now you know a rebranding with dual now you know a rebranding with dual now you know a rebranding with dual licensing which can be super confusing licensing which can be super confusing licensing which can be super confusing and like I want everyone to be happy and and like I want everyone to be happy and and like I want everyone to be happy and have food have food have food >> you know. Yeah, >> you know. Yeah, >> you know. Yeah, >> that's it. But at the same time I was on >> that's it. But at the same time I was on >> that's it. But at the same time I was on a I was an I don't know if you knew this a I was an I don't know if you knew this a I was an I don't know if you knew this actually. This might be interesting for actually. This might be interesting for actually. This might be interesting for you to know. I was a an expert witness you to know. I was a an expert witness you to know. I was a an expert witness for a patent troll case for a patent troll case for a patent troll case >> and a patent troll had designed >> and a patent troll had designed >> and a patent troll had designed effectively an ATM machine and in the effectively an ATM machine and in the effectively an ATM machine and in the creating of this kind of ATM that would creating of this kind of ATM that would creating of this kind of ATM that would allow you to originate a loan. He did it allow you to originate a loan. He did it allow you to originate a loan. He did it very early, like right when ATMs were very early, like right when ATMs were very early, like right when ATMs were happening. One could squint with beer happening. One could squint with beer happening. One could squint with beer goggles and go, "It's client server."

goggles and go, "It's client server." goggles and go, "It's client server." >> And then if you were completely drunk >> And then if you were completely drunk >> And then if you were completely drunk and wrong, you would say, "This is the and wrong, you would say, "This is the and wrong, you would say, "This is the internet." internet." internet." And then he started suing people. And he And then he started suing people. And he And then he started suing people. And he sued like 70 or 80,000 people for like sued like 70 or 80,000 people for like sued like 70 or 80,000 people for like 50 grand. And then it became a standard 50 grand. And then it became a standard 50 grand. And then it became a standard thing. Like the job was find anyone who thing. Like the job was find anyone who thing. Like the job was find anyone who has a website that has a shopping cart has a website that has a shopping cart has a website that has a shopping cart and sue them. Not anyone big enough like and sue them. Not anyone big enough like and sue them. Not anyone big enough like Amazon that you'd wake the bear, but Amazon that you'd wake the bear, but Amazon that you'd wake the bear, but people small enough where if they just people small enough where if they just people small enough where if they just pay you off, pay you off, pay you off, >> then it'll make it go away. So, I got to >> then it'll make it go away. So, I got to >> then it'll make it go away. So, I got to for years we fought this patent troll for years we fought this patent troll for years we fought this patent troll with the uh Electronic Frontier with the uh Electronic Frontier with the uh Electronic Frontier Foundation and we finally shut them Foundation and we finally shut them Foundation and we finally shut them down. down. down. >> But the amount of energy that was done, >> But the amount of energy that was done, >> But the amount of energy that was done, the amount of pro bono work and hours of the amount of pro bono work and hours of the amount of pro bono work and hours of and and I flew around and in two and and I flew around and in two and and I flew around and in two different courts in two different states different courts in two different states different courts in two different states got to like fullon like you can find got to like fullon like you can find got to like fullon like you can find these things online. This was a person these things online. This was a person these things online. This was a person who' never actually made anything. who' never actually made anything. who' never actually made anything. >> Like there's that guy out there who >> Like there's that guy out there who >> Like there's that guy out there who thinks he invented email and to this day thinks he invented email and to this day thinks he invented email and to this day he thinks he's the email guy. You know he thinks he's the email guy. You know he thinks he's the email guy. You know what I mean? what I mean? what I mean? >> So it is a slippery slope. So then when >> So it is a slippery slope. So then when >> So it is a slippery slope. So then when we bring it to the context of of source we bring it to the context of of source we bring it to the context of of source code, there's so much source code out code, there's so much source code out code, there's so much source code out there that doesn't have a license.ext there that doesn't have a license.ext there that doesn't have a license.ext and people are just like, I don't care.

and people are just like, I don't care. and people are just like, I don't care. Here's some code. Here's some code. Here's some code. >> Yeah. I think most people don't even >> Yeah. I think most people don't even >> Yeah. I think most people don't even understand the licenses that they're understand the licenses that they're understand the licenses that they're like that they put on their code. Like like that they put on their code. Like like that they put on their code. Like it's really interesting sort of the it's really interesting sort of the it's really interesting sort of the social expectation is completely social expectation is completely social expectation is completely different like you know nowhere in this different like you know nowhere in this different like you know nowhere in this in the MIT licenses it says that a in the MIT licenses it says that a in the MIT licenses it says that a project can accept external project can accept external project can accept external contributions or that has open contributions or that has open contributions or that has open governance or that like anything right governance or that like anything right governance or that like anything right it says like you're given this no it says like you're given this no it says like you're given this no warranties no disclaimers like asis warranties no disclaimers like asis warranties no disclaimers like asis sorry that's it but like culturally we sorry that's it but like culturally we sorry that's it but like culturally we expect there to be some sort of like expect there to be some sort of like expect there to be some sort of like place to talk about things and like place to talk about things and like place to talk about things and like there should be some sort of like way to there should be some sort of like way to there should be some sort of like way to make decisions and like there's all this make decisions and like there's all this make decisions and like there's all this kind of like building stuff that I think kind of like building stuff that I think kind of like building stuff that I think that you know the the kids these days that you know the the kids these days that you know the the kids these days kind of understand to be what open kind of understand to be what open kind of understand to be what open source is actually about and they don't source is actually about and they don't source is actually about and they don't really like think about licensing the really like think about licensing the really like think about licensing the way that I think some of us that are a way that I think some of us that are a way that I think some of us that are a little older that had to kind of like little older that had to kind of like little older that had to kind of like deal with a lot of that stuff kind of do deal with a lot of that stuff kind of do deal with a lot of that stuff kind of do because you know like and there's it's because you know like and there's it's because you know like and there's it's also true that like I do this as well also true that like I do this as well also true that like I do this as well like you know I want to support the like you know I want to support the like you know I want to support the projects I mean I don't do that I don't projects I mean I don't do that I don't projects I mean I don't do that I don't support that many open source projects support that many open source projects support that many open source projects anymore but there was a while where that anymore but there was a while where that anymore but there was a while where that was like all I was doing and like I was was like all I was doing and like I was was like all I was doing and like I was putting a lot of effort into giving that putting a lot of effort into giving that putting a lot of effort into giving that support and like I never actually support and like I never actually support and like I never actually technically had to do that but I kind of technically had to do that but I kind of technically had to do that but I kind of felt like socially it was the right felt like socially it was the right felt like socially it was the right thing to do and also a good thing to do thing to do and also a good thing to do thing to do and also a good thing to do and but like I would stress myself out and but like I would stress myself out and but like I would stress myself out on a thing that I've technically said on a thing that I've technically said on a thing that I've technically said like I don't have to support this at all like I don't have to support this at all like I don't have to support this at all like just deal with it you know but I like just deal with it you know but I like just deal with it you know but I was burning myself out trying to do that was burning myself out trying to do that was burning myself out trying to do that stuff and so I think it's like a little stuff and so I think it's like a little stuff and so I think it's like a little tricky basically like I don't think that tricky basically like I don't think that tricky basically like I don't think that licenses are the full story around how licenses are the full story around how licenses are the full story around how we like develop collaborative software

we like develop collaborative software we like develop collaborative software projects basically there's other stuff projects basically there's other stuff projects basically there's other stuff going on there going on there going on there >> I also think that there is a someone >> I also think that there is a someone >> I also think that there is a someone needs to have a conversation about needs to have a conversation about needs to have a conversation about standing on the shoulders of giants and standing on the shoulders of giants and standing on the shoulders of giants and what was a revolution what was a revolution what was a revolution >> is now just a fatal complete like I I >> is now just a fatal complete like I I >> is now just a fatal complete like I I got to sit next to got to sit next to got to sit next to >> I bought compilers like you probably >> I bought compilers like you probably >> I bought compilers like you probably bought compilers you know what I mean bought compilers you know what I mean bought compilers you know what I mean nowadays you can't sell a compiler for nowadays you can't sell a compiler for nowadays you can't sell a compiler for anything like it's not you know that's anything like it's not you know that's anything like it's not you know that's like that's just default standard like that's just default standard like that's just default standard language tooling is free to use language tooling is free to use language tooling is free to use >> I was in uh I was in Denmark and I got >> I was in uh I was in Denmark and I got >> I was in uh I was in Denmark and I got to sit next to like the guy who invented to sit next to like the guy who invented to sit next to like the guy who invented model view controller you know and like model view controller you know and like model view controller you know and like he didn't think about ruby on rails he he didn't think about ruby on rails he he didn't think about ruby on rails he didn't think about espec He just made didn't think about espec He just made didn't think about espec He just made it. So, and he's like Danish and super it. So, and he's like Danish and super it. So, and he's like Danish and super chill. So, he was like, "Yeah, it's chill. So, he was like, "Yeah, it's chill. So, he was like, "Yeah, it's cool. I'm glad everyone's enjoying this cool. I'm glad everyone's enjoying this cool. I'm glad everyone's enjoying this this this idea that I had on a weekend this this idea that I had on a weekend this this idea that I had on a weekend or whatever, or whatever, or whatever, >> but if he were running around smacking >> but if he were running around smacking >> but if he were running around smacking everyone with lawsuits every time they everyone with lawsuits every time they everyone with lawsuits every time they thought about making a triangle uh and, thought about making a triangle uh and, thought about making a triangle uh and, you know, separating responsibilities, you know, separating responsibilities, you know, separating responsibilities, we would all be sad." we would all be sad." we would all be sad." >> I had dinner uh with many people, but >> I had dinner uh with many people, but >> I had dinner uh with many people, but among one of them was Steve Bourne was among one of them was Steve Bourne was among one of them was Steve Bourne was sitting directly to my left. And I sitting directly to my left. And I sitting directly to my left. And I didn't know that until after the dinner didn't know that until after the dinner didn't know that until after the dinner happened. And I was like to my friend happened. And I was like to my friend happened. And I was like to my friend that told me, he's like, "Do you know that told me, he's like, "Do you know that told me, he's like, "Do you know who that guy was?" was like, "Oh, that's who that guy was?" was like, "Oh, that's who that guy was?" was like, "Oh, that's Steve Bourne from Bash, you know, Born Steve Bourne from Bash, you know, Born Steve Bourne from Bash, you know, Born Again Shell." I was like, "No, I had no Again Shell." I was like, "No, I had no Again Shell." I was like, "No, I had no idea." And I was like, "I'm I'm glad I idea." And I was like, "I'm I'm glad I idea." And I was like, "I'm I'm glad I acted so normal and chill instead of acted so normal and chill instead of acted so normal and chill instead of weird and fanboy. If I had known that's weird and fanboy. If I had known that's weird and fanboy. If I had known that's who he was, I might have been a little who he was, I might have been a little who he was, I might have been a little straight, you know, weirder about it."

straight, you know, weirder about it." straight, you know, weirder about it." So, I'm glad that I was able to just be So, I'm glad that I was able to just be So, I'm glad that I was able to just be a regular person. You You never know a regular person. You You never know a regular person. You You never know when you're like standing next to a when you're like standing next to a when you're like standing next to a person that did that. One time I was person that did that. One time I was person that did that. One time I was talking crap in the in the hallway in talking crap in the in the hallway in talking crap in the in the hallway in the Microsoft office on a visit. I was the Microsoft office on a visit. I was the Microsoft office on a visit. I was talking bad about HTTP talking bad about HTTP talking bad about HTTP and I was literally doing it to a guy and I was literally doing it to a guy and I was literally doing it to a guy whose name is on the HTTP spec. whose name is on the HTTP spec. whose name is on the HTTP spec. >> Like he was Tim Berners Lee's intern. >> Like he was Tim Berners Lee's intern. >> Like he was Tim Berners Lee's intern. >> Uhhuh. >> Uhhuh. >> Uhhuh. >> So like that moment is like where I >> So like that moment is like where I >> So like that moment is like where I learned just not to talk crap about learned just not to talk crap about learned just not to talk crap about anybody because they might have well anybody because they might have well anybody because they might have well written the spec written the spec written the spec >> on the thing. >> on the thing. >> on the thing. >> So So when you're writing code, if we >> So So when you're writing code, if we >> So So when you're writing code, if we think about standing on the shoulders of think about standing on the shoulders of think about standing on the shoulders of giants, giants, giants, >> I feel like at 30 plus years into my >> I feel like at 30 plus years into my >> I feel like at 30 plus years into my career, I get four loops. So if anyone career, I get four loops. So if anyone career, I get four loops. So if anyone can write a for loop for me, I don't can write a for loop for me, I don't can write a for loop for me, I don't feel bad about it. I don't need to like feel bad about it. I don't need to like feel bad about it. I don't need to like do that part. do that part. do that part. >> But where does the um I accept that >> But where does the um I accept that >> But where does the um I accept that these are building blocks like the Lego these are building blocks like the Lego these are building blocks like the Lego pieces that I accept exist and I'm not pieces that I accept exist and I'm not pieces that I accept exist and I'm not worried about it. And then where does worried about it. And then where does worried about it. And then where does uniqueness uniqueness uniqueness happen? Recently, let me know what you happen? Recently, let me know what you happen? Recently, let me know what you think about this and then you tell me think about this and then you tell me think about this and then you tell me about one of your times that you about one of your times that you about one of your times that you generated something. I got to sit at generated something. I got to sit at generated something. I got to sit at this at a C++ conference in Canada. get this at a C++ conference in Canada. get this at a C++ conference in Canada. get to sit with a gentleman who is working to sit with a gentleman who is working to sit with a gentleman who is working on carbon which is like a future version on carbon which is like a future version on carbon which is like a future version of C++ and I'm really excited about of C++ and I'm really excited about of C++ and I'm really excited about Commodore 64s right now. So I ran back Commodore 64s right now. So I ran back Commodore 64s right now. So I ran back to the hotel and I vibecoded a carbon to the hotel and I vibecoded a carbon to the hotel and I vibecoded a carbon 26502 26502 26502 uh compiler by piecing a bunch of Lego uh compiler by piecing a bunch of Lego uh compiler by piecing a bunch of Lego pieces together. So there's not a lot of pieces together. So there's not a lot of pieces together. So there's not a lot of uniqueness there.

uniqueness there. uniqueness there. >> Yeah. >> Yeah. >> Yeah. >> But I was, you know, I was first to do >> But I was, you know, I was first to do >> But I was, you know, I was first to do it and 90% of the work was messing it and 90% of the work was messing it and 90% of the work was messing around with make files. So I could have around with make files. So I could have around with make files. So I could have been a two week long googling and stack been a two week long googling and stack been a two week long googling and stack overflowing for make files, but I feel overflowing for make files, but I feel overflowing for make files, but I feel like a new thing got made because I like a new thing got made because I like a new thing got made because I didn't have to worry about worry about didn't have to worry about worry about didn't have to worry about worry about reminding myself pulling make files out reminding myself pulling make files out reminding myself pulling make files out of the archives. of the archives. of the archives. Did I do the work or did the AI do the Did I do the work or did the AI do the Did I do the work or did the AI do the work? It was kind of collaborative, you work? It was kind of collaborative, you work? It was kind of collaborative, you know what I mean? And it took it took know what I mean? And it took it took know what I mean? And it took it took some hours. some hours. some hours. >> Absolutely. I have interesting kind of >> Absolutely. I have interesting kind of >> Absolutely. I have interesting kind of feelings about this, too. I I started feelings about this, too. I I started feelings about this, too. I I started programing when I was seven. I'm 39 now programing when I was seven. I'm 39 now programing when I was seven. I'm 39 now and so you I also been doing this for a and so you I also been doing this for a and so you I also been doing this for a while. I also am pretty sure I while. I also am pretty sure I while. I also am pretty sure I understand for loops but like pretty understand for loops but like pretty understand for loops but like pretty sure sure sure >> uh mostly working in open source like >> uh mostly working in open source like >> uh mostly working in open source like the way that I've been thinking about the way that I've been thinking about the way that I've been thinking about working with claude is like it's kind of working with claude is like it's kind of working with claude is like it's kind of like I'm an open-source project of one. like I'm an open-source project of one. like I'm an open-source project of one. I know I've talked to a lot of people I know I've talked to a lot of people I know I've talked to a lot of people and I've seen a lot of comments online, and I've seen a lot of comments online, and I've seen a lot of comments online, some people that still find like the the some people that still find like the the some people that still find like the the puzzle aspect of writing the code to be puzzle aspect of writing the code to be puzzle aspect of writing the code to be their intrinsic motivator. And the their intrinsic motivator. And the their intrinsic motivator. And the longer I've been in my career, the less longer I've been in my career, the less longer I've been in my career, the less I have found like I just want to I want I have found like I just want to I want I have found like I just want to I want to figure out this bug and I want to to figure out this bug and I want to to figure out this bug and I want to debug this thing and I you know it's debug this thing and I you know it's debug this thing and I you know it's going to take me all Saturday and that's going to take me all Saturday and that's going to take me all Saturday and that's going to be awesome and you know really going to be awesome and you know really going to be awesome and you know really like motivated by doing that. Like that like motivated by doing that. Like that like motivated by doing that. Like that used to be the case, but now, you know, used to be the case, but now, you know, used to be the case, but now, you know, I'm busy and I've spent a lot of I'm busy and I've spent a lot of I'm busy and I've spent a lot of Saturdays dealing with bugs and like I Saturdays dealing with bugs and like I Saturdays dealing with bugs and like I just want my project to work. And so for just want my project to work. And so for just want my project to work. And so for me, like it's not at this point, I me, like it's not at this point, I me, like it's not at this point, I probably have mostly had Claude write my probably have mostly had Claude write my probably have mostly had Claude write my own code for the last like two months.

own code for the last like two months. own code for the last like two months. Like I've written very small amount of Like I've written very small amount of Like I've written very small amount of it overall and that's because like it overall and that's because like it overall and that's because like >> the software engineering parts are what >> the software engineering parts are what >> the software engineering parts are what is interesting to me right now. Um I'm is interesting to me right now. Um I'm is interesting to me right now. Um I'm also working on a compiler that also working on a compiler that also working on a compiler that effectively claude is completely uh effectively claude is completely uh effectively claude is completely uh written and like I'm doing that because written and like I'm doing that because written and like I'm doing that because I I wanted to build a compiler because I I I wanted to build a compiler because I I I wanted to build a compiler because I haven't done it in a really long time. haven't done it in a really long time. haven't done it in a really long time. When I worked on Rust I was not working When I worked on Rust I was not working When I worked on Rust I was not working on the compiler. I love compilers. on the compiler. I love compilers. on the compiler. I love compilers. Actually structured my college courses Actually structured my college courses Actually structured my college courses to get to compilers as quickly as to get to compilers as quickly as to get to compilers as quickly as possible. But like the like debugging my possible. But like the like debugging my possible. But like the like debugging my small bug where my register allocator small bug where my register allocator small bug where my register allocator was kind of stupid is not what's fun to was kind of stupid is not what's fun to was kind of stupid is not what's fun to me about compilers. It's like okay you me about compilers. It's like okay you me about compilers. It's like okay you know what what IRS do I want to have? know what what IRS do I want to have? know what what IRS do I want to have? what optimization passes do I want? what optimization passes do I want? what optimization passes do I want? What's some language semantic ideas, I What's some language semantic ideas, I What's some language semantic ideas, I want to be able to try those out and see want to be able to try those out and see want to be able to try those out and see if it's a good idea or not? And like if it's a good idea or not? And like if it's a good idea or not? And like this the low sort of almost like popping this the low sort of almost like popping this the low sort of almost like popping up one more layer of abstraction is kind up one more layer of abstraction is kind up one more layer of abstraction is kind of the way that I feel about it. And so of the way that I feel about it. And so of the way that I feel about it. And so the design aspect and like the the way the design aspect and like the the way the design aspect and like the the way the big pictures fit together like I'm the big pictures fit together like I'm the big pictures fit together like I'm interested in the architecture of my interested in the architecture of my interested in the architecture of my project. I am less interested in project. I am less interested in project. I am less interested in handwriting every single bit. I'm not a handwriting every single bit. I'm not a handwriting every single bit. I'm not a full-on complete vibe coder. Like I do full-on complete vibe coder. Like I do full-on complete vibe coder. Like I do review every PR that I merge. I think review every PR that I merge. I think review every PR that I merge. I think it's like professionally responsible, it's like professionally responsible, it's like professionally responsible, especially like for work stuff. For for especially like for work stuff. For for especially like for work stuff. For for fun stuff, there's been a couple small fun stuff, there's been a couple small fun stuff, there's been a couple small projects that I've just not bothered projects that I've just not bothered projects that I've just not bothered reading the code of. And that's mostly reading the code of. And that's mostly reading the code of. And that's mostly because I read enough JavaScript and I because I read enough JavaScript and I because I read enough JavaScript and I don't really care to like like projects don't really care to like like projects don't really care to like like projects that are very low stakes that just work that are very low stakes that just work that are very low stakes that just work because I'm trying them out and it's because I'm trying them out and it's because I'm trying them out and it's like fine and it's, you know, for me like fine and it's, you know, for me like fine and it's, you know, for me only like that's fine. I don't care only like that's fine. I don't care only like that's fine. I don't care about that really. But like for for

about that really. But like for for about that really. But like for for professional projects, I still think professional projects, I still think professional projects, I still think it's important to review everything and it's important to review everything and it's important to review everything and so I do. But like so I do. But like so I do. But like I'm, you know, like the very very I'm, you know, like the very very I'm, you know, like the very very specifics. It's, it reminds me of when I specifics. It's, it reminds me of when I specifics. It's, it reminds me of when I used to care a lot about code formatting used to care a lot about code formatting used to care a lot about code formatting and then like auto formatterers are now and then like auto formatterers are now and then like auto formatterers are now the rage and now I just like don't care the rage and now I just like don't care the rage and now I just like don't care about that anymore. It's kind of like about that anymore. It's kind of like about that anymore. It's kind of like one level up again where it's like I one level up again where it's like I one level up again where it's like I really care about the architecture. I really care about the architecture. I really care about the architecture. I care about the way things fit together. care about the way things fit together. care about the way things fit together. Care about if there's tests, but like if Care about if there's tests, but like if Care about if there's tests, but like if this function is like 20 lines and this this function is like 20 lines and this this function is like 20 lines and this one and should be two 10 line ones or one and should be two 10 line ones or one and should be two 10 line ones or what like I I don't actually care about what like I I don't actually care about what like I I don't actually care about that anymore basically. And so for me, I that anymore basically. And so for me, I that anymore basically. And so for me, I like reading code and I like like reading code and I like like reading code and I like understanding code that somebody else understanding code that somebody else understanding code that somebody else has written and I like those kinds of has written and I like those kinds of has written and I like those kinds of things. And so I think that the sort of things. And so I think that the sort of things. And so I think that the sort of like vibe of working with Claude really like vibe of working with Claude really like vibe of working with Claude really works for the things that I enjoy about works for the things that I enjoy about works for the things that I enjoy about professional software development professional software development professional software development basically. basically. basically. >> So it's upleveled it to the ideal point >> So it's upleveled it to the ideal point >> So it's upleveled it to the ideal point of this is the part of my brain that of this is the part of my brain that of this is the part of my brain that wants to be creative and you're still wants to be creative and you're still wants to be creative and you're still like you're feeling creative. like you're feeling creative. like you're feeling creative. >> Yeah. Now, but you're someone who was a >> Yeah. Now, but you're someone who was a >> Yeah. Now, but you're someone who was a low-level programmer, but also a high low-level programmer, but also a high low-level programmer, but also a high level programmer because like Rust isn't level programmer because like Rust isn't level programmer because like Rust isn't exactly Java, but Rails and Ruby are exactly Java, but Rails and Ruby are exactly Java, but Rails and Ruby are somewhat high level comparatively to the somewhat high level comparatively to the somewhat high level comparatively to the C and the curly brace languages. So, I C and the curly brace languages. So, I C and the curly brace languages. So, I have known you as someone who changes have known you as someone who changes have known you as someone who changes altitude quite comfortably. Here's the altitude quite comfortably. Here's the altitude quite comfortably. Here's the question though.

question though. question though. >> Are you and does your generation >> Are you and does your generation >> Are you and does your generation represent the last full stack developer? represent the last full stack developer? represent the last full stack developer? >> Maybe. That's it's a really interesting >> Maybe. That's it's a really interesting >> Maybe. That's it's a really interesting question. I I started with GW Basic and question. I I started with GW Basic and question. I I started with GW Basic and then I learned C probably when I was then I learned C probably when I was then I learned C probably when I was like 12 and then Java and C++ when I was like 12 and then Java and C++ when I was like 12 and then Java and C++ when I was like 14. And so it's really funny too like 14. And so it's really funny too like 14. And so it's really funny too that like people that knew me from Ruby that like people that knew me from Ruby that like people that knew me from Ruby world saw me go to Rust and there was a world saw me go to Rust and there was a world saw me go to Rust and there was a lot of people used to say things about lot of people used to say things about lot of people used to say things about Rust like oh those are just high level Rust like oh those are just high level Rust like oh those are just high level programmers that don't know what they're programmers that don't know what they're programmers that don't know what they're doing doing low-level stuff and I was doing doing low-level stuff and I was doing doing low-level stuff and I was like me and my friends were working on like me and my friends were working on like me and my friends were working on an operating system in college man like an operating system in college man like an operating system in college man like people can know multiple things like you people can know multiple things like you people can know multiple things like you know one of my friends in college used know one of my friends in college used know one of my friends in college used to say like I can't believe you're doing to say like I can't believe you're doing to say like I can't believe you're doing web development because assembly is so web development because assembly is so web development because assembly is so much easier like the instructions the much easier like the instructions the much easier like the instructions the CPU does what I tell it to do exactly CPU does what I tell it to do exactly CPU does what I tell it to do exactly but you like put a scripting language but you like put a scripting language but you like put a scripting language inside a markup language and ship it to inside a markup language and ship it to inside a markup language and ship it to a computer on the other side of the a computer on the other side of the a computer on the other side of the planet is maybe not even running the planet is maybe not even running the planet is maybe not even running the same operating system and you like same operating system and you like same operating system and you like expect that to work like that seems expect that to work like that seems expect that to work like that seems insanely complicated to me. I will stick insanely complicated to me. I will stick insanely complicated to me. I will stick with my assembly language. You know what with my assembly language. You know what with my assembly language. You know what I So there's different perspectives on I So there's different perspectives on I So there's different perspectives on all these kinds of things and and yeah, all these kinds of things and and yeah, all these kinds of things and and yeah, like I think that, you know, people my like I think that, you know, people my like I think that, you know, people my age, like I was lucky enough to sort of age, like I was lucky enough to sort of age, like I was lucky enough to sort of grow up with like a text adventure was grow up with like a text adventure was grow up with like a text adventure was the first thing I ever did on a the first thing I ever did on a the first thing I ever did on a computer, you know, and so like I computer, you know, and so like I computer, you know, and so like I remember DOSs and pre-windows, just remember DOSs and pre-windows, just remember DOSs and pre-windows, just barely, but like I was kind of there.

barely, but like I was kind of there. barely, but like I was kind of there. And so that's usually what I thought of And so that's usually what I thought of And so that's usually what I thought of is like my generation was the last one is like my generation was the last one is like my generation was the last one to like, you know, pre-w web know what to like, you know, pre-w web know what to like, you know, pre-w web know what computers were like and frankly just computers were like and frankly just computers were like and frankly just remember what life was like before the remember what life was like before the remember what life was like before the web existed or cell phone. I can't web existed or cell phone. I can't web existed or cell phone. I can't believe I got a cell phone in like believe I got a cell phone in like believe I got a cell phone in like college. You know what I mean? Like college. You know what I mean? Like college. You know what I mean? Like think about kids having to deal with think about kids having to deal with think about kids having to deal with cell phones at schools and stuff. Now cell phones at schools and stuff. Now cell phones at schools and stuff. Now I'm just like oh my god. I'm just like oh my god. I'm just like oh my god. >> My my kid's school just uh banned cell >> My my kid's school just uh banned cell >> My my kid's school just uh banned cell phones. So this this now just when he's phones. So this this now just when he's phones. So this this now just when he's a senior like you know this would have a senior like you know this would have a senior like you know this would have been helpful four years ago. been helpful four years ago. been helpful four years ago. >> Yeah. they got to put it in a Faraday >> Yeah. they got to put it in a Faraday >> Yeah. they got to put it in a Faraday bag bag or something when they come into bag bag or something when they come into bag bag or something when they come into work come to school in a couple of work come to school in a couple of work come to school in a couple of weeks. weeks. weeks. >> Yeah. So, I mean it's possible, but I >> Yeah. So, I mean it's possible, but I >> Yeah. So, I mean it's possible, but I think the other thing too is that like think the other thing too is that like think the other thing too is that like nothing is forcing you to use Claude for nothing is forcing you to use Claude for nothing is forcing you to use Claude for everything. You know what I mean? Like everything. You know what I mean? Like everything. You know what I mean? Like >> when you say Claude, you mean literally >> when you say Claude, you mean literally >> when you say Claude, you mean literally Claude? Do you mean the Sonet thing or Claude? Do you mean the Sonet thing or Claude? Do you mean the Sonet thing or do you use do you use do you use >> I think I use Claude code and basically >> I think I use Claude code and basically >> I think I use Claude code and basically it's like the tool that has worked the it's like the tool that has worked the it's like the tool that has worked the best for me. I've actually had terrible best for me. I've actually had terrible best for me. I've actually had terrible time with cursor. I know a lot of people time with cursor. I know a lot of people time with cursor. I know a lot of people really liked it, but I not really really liked it, but I not really really liked it, but I not really personally find it very effective. personally find it very effective. personally find it very effective. People seem to be very um like everyone People seem to be very um like everyone People seem to be very um like everyone was like Cursor. Oh my god, Cursor is was like Cursor. Oh my god, Cursor is was like Cursor. Oh my god, Cursor is the best. And then like a week later the best. And then like a week later the best. And then like a week later they're like Cursor is dead to me. I they're like Cursor is dead to me. I they're like Cursor is dead to me. I like only use so like Honda, Toyota, like only use so like Honda, Toyota, like only use so like Honda, Toyota, Audi, you know, find your car. If it Audi, you know, find your car. If it Audi, you know, find your car. If it makes you happy, drive the car.

makes you happy, drive the car. makes you happy, drive the car. >> Yeah. And I think it also represents >> Yeah. And I think it also represents >> Yeah. And I think it also represents like interface expectations. Like I like interface expectations. Like I like interface expectations. Like I think the reason that I don't like think the reason that I don't like think the reason that I don't like cursor as much is because I really like cursor as much is because I really like cursor as much is because I really like the agentic style of using these tools the agentic style of using these tools the agentic style of using these tools and cursor is very focused on the fancy and cursor is very focused on the fancy and cursor is very focused on the fancy autocomplete style of these tools. And autocomplete style of these tools. And autocomplete style of these tools. And so I think that like and they've added so I think that like and they've added so I think that like and they've added agentic stuff, but like I think that you agentic stuff, but like I think that you agentic stuff, but like I think that you know they're called cursor for a reason. know they're called cursor for a reason. know they're called cursor for a reason. Like it's supposed to be about looking Like it's supposed to be about looking Like it's supposed to be about looking at where you put the cursor and helping at where you put the cursor and helping at where you put the cursor and helping you. And so they kind of have like you. And so they kind of have like you. And so they kind of have like bought into that vision of what these bought into that vision of what these bought into that vision of what these tools are supposed to be. I think that's tools are supposed to be. I think that's tools are supposed to be. I think that's what doesn't gel with me personally what doesn't gel with me personally what doesn't gel with me personally because like then I'm still typing the because like then I'm still typing the because like then I'm still typing the code and looking at it. You know, I'm code and looking at it. You know, I'm code and looking at it. You know, I'm not, you know, not, you know, not, you know, >> I kind of look at it the same way as >> I kind of look at it the same way as >> I kind of look at it the same way as when the cloud happened because like my when the cloud happened because like my when the cloud happened because like my websites plural and there's like 12 of websites plural and there's like 12 of websites plural and there's like 12 of them, but it's it's a long tale, but them, but it's it's a long tale, but them, but it's it's a long tale, but there's like, you know, the Hansselman there's like, you know, the Hansselman there's like, you know, the Hansselman International super business that International super business that International super business that consists of me alone. uh you know it was consists of me alone. uh you know it was consists of me alone. uh you know it was running on a freaking server under my running on a freaking server under my running on a freaking server under my desk and then it was running under a desk and then it was running under a desk and then it was running under a server that was colllocated in someone server that was colllocated in someone server that was colllocated in someone else's desk and then one day someone else's desk and then one day someone else's desk and then one day someone kicked it and said oh I should probably kicked it and said oh I should probably kicked it and said oh I should probably move that to a VM and then that moved move that to a VM and then that moved move that to a VM and then that moved into a a node and now it's in you know into a a node and now it's in you know into a a node and now it's in you know now it's globally whatever you know like now it's globally whatever you know like now it's globally whatever you know like I I tell this story about how we used to I I tell this story about how we used to I I tell this story about how we used to fly consultants in to configure load fly consultants in to configure load fly consultants in to configure load balancers balancers balancers >> and now it's a checkbox >> and now it's a checkbox >> and now it's a checkbox >> in Azure and it's like >> in Azure and it's like >> in Azure and it's like >> I can be mad about that or I can just >> I can be mad about that or I can just >> I can be mad about that or I can just pull that page of my resume out and just pull that page of my resume out and just pull that page of my resume out and just go, "All right, I guess I have a shorter go, "All right, I guess I have a shorter go, "All right, I guess I have a shorter resume now." But now I'm finding as a as resume now." But now I'm finding as a as resume now." But now I'm finding as a as a small business of one guy. Until the a small business of one guy. Until the a small business of one guy. Until the last week or the week before last, I

last week or the week before last, I last week or the week before last, I never had a backend for the website. I never had a backend for the website. I never had a backend for the website. I literally every week in doing this literally every week in doing this literally every week in doing this podcast edit a JSON file and upload it podcast edit a JSON file and upload it podcast edit a JSON file and upload it to a bucket. And then I was like, you to a bucket. And then I was like, you to a bucket. And then I was like, you know, why haven't I ever written a know, why haven't I ever written a know, why haven't I ever written a backend for this? Well, it's because it backend for this? Well, it's because it backend for this? Well, it's because it takes two seconds to do the JavaScript takes two seconds to do the JavaScript takes two seconds to do the JavaScript update. And then I don't have the 3 days update. And then I don't have the 3 days update. And then I don't have the 3 days that it would take. that it would take. that it would take. >> Yeah. >> Yeah. >> Yeah. >> So, I wrote it and I wrote it and it >> So, I wrote it and I wrote it and it >> So, I wrote it and I wrote it and it took 42 minutes. It took longer to get took 42 minutes. It took longer to get took 42 minutes. It took longer to get it into the cloud than it did to write it into the cloud than it did to write it into the cloud than it did to write the tool. And now I've been improving the tool. And now I've been improving the tool. And now I've been improving the tool and improving the tool and the tool and improving the tool and the tool and improving the tool and improving the tool. It's a freaking improving the tool. It's a freaking improving the tool. It's a freaking delight. But I never would have invested delight. But I never would have invested delight. But I never would have invested 3 weeks or hired a vendor. So then did I 3 weeks or hired a vendor. So then did I 3 weeks or hired a vendor. So then did I just cheapen things? Did I just cheapen just cheapen things? Did I just cheapen just cheapen things? Did I just cheapen the value of all software? I don't know. the value of all software? I don't know. the value of all software? I don't know. Like am I self-hating software engineer? Like am I self-hating software engineer? Like am I self-hating software engineer? >> Yeah. on the 12 websites thing. I I was >> Yeah. on the 12 websites thing. I I was >> Yeah. on the 12 websites thing. I I was at Walgreens before and I've always at Walgreens before and I've always at Walgreens before and I've always resisted signing up for a Walgreens resisted signing up for a Walgreens resisted signing up for a Walgreens account for some reason. And then account for some reason. And then account for some reason. And then finally this guy's like, "Do you want finally this guy's like, "Do you want finally this guy's like, "Do you want the Walgreens points?" I was, "Sure, the Walgreens points?" I was, "Sure, the Walgreens points?" I was, "Sure, I'll go to Walgreens points." He's like, I'll go to Walgreens points." He's like, I'll go to Walgreens points." He's like, "What's your email?" And I was like, "What's your email?" And I was like, "What's your email?" And I was like, "Steve attecladic.com." And he goes, "Steve attecladic.com." And he goes, "Steve attecladic.com." And he goes, "Oh, you have your own domain. That's "Oh, you have your own domain. That's "Oh, you have your own domain. That's really cool." And I was like, you know, really cool." And I was like, you know, really cool." And I was like, you know, it's kind of cool, but the problem is is it's kind of cool, but the problem is is it's kind of cool, but the problem is is then you find yourself having ideas and then you find yourself having ideas and then you find yourself having ideas and then you're buying more domains and they then you're buying more domains and they then you're buying more domains and they cost like, you know, 10 bucks a year and cost like, you know, 10 bucks a year and cost like, you know, 10 bucks a year and next thing you know, you have like a next thing you know, you have like a next thing you know, you have like a zillion domains and now you're spending zillion domains and now you're spending zillion domains and now you're spending all this money on projects you're not all this money on projects you're not all this money on projects you're not even doing. So, and he goes, "Yeah, even doing. So, and he goes, "Yeah, even doing. So, and he goes, "Yeah, you're right. Maybe it's not as cool as you're right. Maybe it's not as cool as you're right. Maybe it's not as cool as it sounds. Well, good luck." And I was it sounds. Well, good luck." And I was it sounds. Well, good luck." And I was like, like, like, >> I had uh one of my buddies, I had >> I had uh one of my buddies, I had >> I had uh one of my buddies, I had Anthony Eden who started DNS simple or Anthony Eden who started DNS simple or Anthony Eden who started DNS simple or DNS simple DNS simple DNS simple >> and uh you know, I've got a >> and uh you know, I've got a >> and uh you know, I've got a grandfathered in plan, but it it it gets grandfathered in plan, but it it it gets grandfathered in plan, but it it it gets expensive after 51 domains.

expensive after 51 domains. expensive after 51 domains. >> So, he is personally keeping me at 49 >> So, he is personally keeping me at 49 >> So, he is personally keeping me at 49 domains and each one of them is a domains and each one of them is a domains and each one of them is a declaration of my failure to launch a declaration of my failure to launch a declaration of my failure to launch a proper startup. proper startup. proper startup. >> Absolutely. But I think that that >> Absolutely. But I think that that >> Absolutely. But I think that that exactly like activation energy of like, exactly like activation energy of like, exactly like activation energy of like, okay, this would take me a couple days. okay, this would take me a couple days. okay, this would take me a couple days. Like it also may have only taken you two Like it also may have only taken you two Like it also may have only taken you two hours if you wrote it by hand. But like hours if you wrote it by hand. But like hours if you wrote it by hand. But like when you estimate, you know, in your when you estimate, you know, in your when you estimate, you know, in your head, okay, this project's going to take head, okay, this project's going to take head, okay, this project's going to take me a while. I I didn't start this me a while. I I didn't start this me a while. I I didn't start this compiler project until I started using compiler project until I started using compiler project until I started using these tools because I was like, you know these tools because I was like, you know these tools because I was like, you know what, a compiler is a lot of work. Uh what, a compiler is a lot of work. Uh what, a compiler is a lot of work. Uh what I want to do with it is a lot of what I want to do with it is a lot of what I want to do with it is a lot of work. I don't have time. I'm too busy. work. I don't have time. I'm too busy. work. I don't have time. I'm too busy. But you know what? Like Cloud's over But you know what? Like Cloud's over But you know what? Like Cloud's over here in this other window just churning here in this other window just churning here in this other window just churning away at it while we're talking. And away at it while we're talking. And away at it while we're talking. And like, you know, I can do like, you know, I can do like, you know, I can do >> it right now. So the comp doing it right >> it right now. So the comp doing it right >> it right now. So the comp doing it right now right over there. now right over there. now right over there. >> Okay. Did you give it a long task? Like >> Okay. Did you give it a long task? Like >> Okay. Did you give it a long task? Like give me a sense of the size of the task give me a sense of the size of the task give me a sense of the size of the task because you said you're having fun, but because you said you're having fun, but because you said you're having fun, but I don't want people who've never done I don't want people who've never done I don't want people who've never done this to think that claude in a oneshot this to think that claude in a oneshot this to think that claude in a oneshot prompt can make a compiler. prompt can make a compiler. prompt can make a compiler. >> Yeah, absolutely not. So this language >> Yeah, absolutely not. So this language >> Yeah, absolutely not. So this language currently is like it's got 32-bit and currently is like it's got 32-bit and currently is like it's got 32-bit and 64-bit integers, true and false, empty 64-bit integers, true and false, empty 64-bit integers, true and false, empty tupils, if while, and function calls, tupils, if while, and function calls, tupils, if while, and function calls, and that's like it. Like it's a very and that's like it. Like it's a very and that's like it. Like it's a very very minimal. So last night like I was very minimal. So last night like I was very minimal. So last night like I was adding initial support for like arrays adding initial support for like arrays adding initial support for like arrays and strrus which is a big step up in and strrus which is a big step up in and strrus which is a big step up in complexity because you're going from complexity because you're going from complexity because you're going from single values to like aggregates or like single values to like aggregates or like single values to like aggregates or like multiple values right multiple values right multiple values right >> and now you have to think about like how >> and now you have to think about like how >> and now you have to think about like how they um how they sit on memory they um how they sit on memory they um how they sit on memory boundaries and boundaries and boundaries and >> whether you pack the strrus or like >> whether you pack the strrus or like >> whether you pack the strrus or like buffer like there's a lot buffer like there's a lot buffer like there's a lot >> exactly and like alignment and >> exactly and like alignment and >> exactly and like alignment and calculating these things and then calculating these things and then calculating these things and then there's also like IR design questions there's also like IR design questions there's also like IR design questions that are like you know like LVM has that are like you know like LVM has that are like you know like LVM has aggregates in its IR directly and so

aggregates in its IR directly and so aggregates in its IR directly and so that's got some pros but it also some that's got some pros but it also some that's got some pros but it also some cons because if you're a compiler author cons because if you're a compiler author cons because if you're a compiler author and you want your aggregates to have and you want your aggregates to have and you want your aggregates to have different semantics than theirs do, different semantics than theirs do, different semantics than theirs do, you're kind of out of luck. you're kind of out of luck. you're kind of out of luck. >> LL LLM LLVM is the LLVM rather. Um that >> LL LLM LLVM is the LLVM rather. Um that >> LL LLM LLVM is the LLVM rather. Um that way I was talking to Chandler uh way I was talking to Chandler uh way I was talking to Chandler uh Chandler last week. Chandler last week. Chandler last week. >> Um that's the only game in town now like >> Um that's the only game in town now like >> Um that's the only game in town now like cuz I'm old. I'm like Lex and Yak like cuz I'm old. I'm like Lex and Yak like cuz I'm old. I'm like Lex and Yak like there's other ways to do compilers. there's other ways to do compilers. there's other ways to do compilers. >> So I'm doing it all by hand actually. >> So I'm doing it all by hand actually. >> So I'm doing it all by hand actually. I'm not using LVM. Um, and so, uh, I'm not using LVM. Um, and so, uh, I'm not using LVM. Um, and so, uh, >> because it's you're like playing on hard >> because it's you're like playing on hard >> because it's you're like playing on hard mode. mode. mode. >> Yeah. Like I'm Well, it's also like I >> Yeah. Like I'm Well, it's also like I >> Yeah. Like I'm Well, it's also like I wanted to build a compiler and so having wanted to build a compiler and so having wanted to build a compiler and so having the whole second half of your compiler the whole second half of your compiler the whole second half of your compiler written by somebody else is like kind of written by somebody else is like kind of written by somebody else is like kind of cheating for my goals. cheating for my goals. cheating for my goals. >> Um, plus LVM is wonderful. I don't think >> Um, plus LVM is wonderful. I don't think >> Um, plus LVM is wonderful. I don't think it's bad at all, but I am very inspired it's bad at all, but I am very inspired it's bad at all, but I am very inspired by Zigg recently um, effectively uh, by Zigg recently um, effectively uh, by Zigg recently um, effectively uh, making LVM optional. And there's some making LVM optional. And there's some making LVM optional. And there's some really interesting kind of like good uh really interesting kind of like good uh really interesting kind of like good uh you know things about that too. Although you know things about that too. Although you know things about that too. Although I also won't say Chandler's wrong, I also won't say Chandler's wrong, I also won't say Chandler's wrong, especially for carbon because he needs especially for carbon because he needs especially for carbon because he needs actual C++ interop to make carbon work actual C++ interop to make carbon work actual C++ interop to make carbon work and there's like all of Clang just not and there's like all of Clang just not and there's like all of Clang just not even just LVM but all of Clang is like even just LVM but all of Clang is like even just LVM but all of Clang is like effectively the only way to do that in effectively the only way to do that in effectively the only way to do that in the way that he's trying to make carbon the way that he's trying to make carbon the way that he's trying to make carbon work which work which work which >> which is ironic because separate from AI >> which is ironic because separate from AI >> which is ironic because separate from AI and separate from coding the idea that and separate from coding the idea that and separate from coding the idea that like clang and LVM and all the things like clang and LVM and all the things like clang and LVM and all the things like they're all raising the water level like they're all raising the water level like they're all raising the water level to the point where it's like well if you to the point where it's like well if you to the point where it's like well if you want to make a compiler are you really want to make a compiler are you really want to make a compiler are you really making a compiler or are you just a a making a compiler or are you just a a making a compiler or are you just a a designer designer designer >> right you're just an LVM front end so >> right you're just an LVM front end so >> right you're just an LVM front end so then it's I'm just a uh a language then it's I'm just a uh a language then it's I'm just a uh a language designer which is different but you're

designer which is different but you're designer which is different but you're choosing to basically drive stick shift choosing to basically drive stick shift choosing to basically drive stick shift >> essentially you know there's I'm still >> essentially you know there's I'm still >> essentially you know there's I'm still using a couple libraries for some things using a couple libraries for some things using a couple libraries for some things like and uh you know it's not like I'm like and uh you know it's not like I'm like and uh you know it's not like I'm going zero dependencies on this thing going zero dependencies on this thing going zero dependencies on this thing but you're asking I got a little off but you're asking I got a little off but you're asking I got a little off track like what it's what it's working track like what it's what it's working track like what it's what it's working on so I introduced aggregates and I got on so I introduced aggregates and I got on so I introduced aggregates and I got basic support in but there are some basic support in but there are some basic support in but there are some pretty serious bugs and so I effectively pretty serious bugs and so I effectively pretty serious bugs and so I effectively earlier asked it like you know hey can earlier asked it like you know hey can earlier asked it like you know hey can you investigate this test that's failing you investigate this test that's failing you investigate this test that's failing and it was like sure I think it's for and it was like sure I think it's for and it was like sure I think it's for these reasons. And I was like, okay, you these reasons. And I was like, okay, you these reasons. And I was like, okay, you know, that definitely seems possible. know, that definitely seems possible. know, that definitely seems possible. >> Go do the work to make that test pass. >> Go do the work to make that test pass. >> Go do the work to make that test pass. And so it is currently like looking at, And so it is currently like looking at, And so it is currently like looking at, you know, all of the things of where it you know, all of the things of where it you know, all of the things of where it needs to fix things. And so it's like needs to fix things. And so it's like needs to fix things. And so it's like examine the current error handling and examine the current error handling and examine the current error handling and check array literal. Uh, check array literal. Uh, check array literal. Uh, >> does it feel smart or do you feel like a >> does it feel smart or do you feel like a >> does it feel smart or do you feel like a million monkeys are slapping a million million monkeys are slapping a million million monkeys are slapping a million typewriters until a test passes? typewriters until a test passes? typewriters until a test passes? >> It is. It is a dice roll of which one it >> It is. It is a dice roll of which one it >> It is. It is a dice roll of which one it is. is. is. So the very the very first when when So the very the very first when when So the very the very first when when this language was nothing other than this language was nothing other than this language was nothing other than like integers and I didn't have a print like integers and I didn't have a print like integers and I didn't have a print function. It was just return code. You function. It was just return code. You function. It was just return code. You could like examine the exit code to see could like examine the exit code to see could like examine the exit code to see what integer would come out of the what integer would come out of the what integer would come out of the thing. I asked Claude just like I did thing. I asked Claude just like I did thing. I asked Claude just like I did try to do the oneshot thing. Not that I try to do the oneshot thing. Not that I try to do the oneshot thing. Not that I was expecting anything good, but I said was expecting anything good, but I said was expecting anything good, but I said like hey I need to I need to compile like hey I need to I need to compile like hey I need to I need to compile this to an x8664 Linux executable. Can this to an x8664 Linux executable. Can this to an x8664 Linux executable. Can you do that please? And it generated you do that please? And it generated you do that please? And it generated something. And I uh a friend happened to something. And I uh a friend happened to something. And I uh a friend happened to get on Discord at the same time that was get on Discord at the same time that was get on Discord at the same time that was uh kind of interested in a lot of these uh kind of interested in a lot of these uh kind of interested in a lot of these similar topics and is also pretty AI similar topics and is also pretty AI similar topics and is also pretty AI skeptical. And I was like, "Hey, uh skeptical. And I was like, "Hey, uh skeptical. And I was like, "Hey, uh Claude just generated me a codegen back Claude just generated me a codegen back Claude just generated me a codegen back end. Do you want to take a look at it?"

end. Do you want to take a look at it?" end. Do you want to take a look at it?" And they said, "Sure." And so while we And they said, "Sure." And so while we And they said, "Sure." And so while we were looking at it, I went in the were looking at it, I went in the were looking at it, I went in the background. I said, "Hey Claude, it's background. I said, "Hey Claude, it's background. I said, "Hey Claude, it's seg faulting. Like, can you fix that?" seg faulting. Like, can you fix that?" seg faulting. Like, can you fix that?" And then put the window away. And we're And then put the window away. And we're And then put the window away. And we're looking at the code and my friend goes, looking at the code and my friend goes, looking at the code and my friend goes, "Yeah, that's definitely wrong and "Yeah, that's definitely wrong and "Yeah, that's definitely wrong and that's definitely wrong. like this kind that's definitely wrong. like this kind that's definitely wrong. like this kind of looks okay for a very first draft of of looks okay for a very first draft of of looks okay for a very first draft of like a very basic you know this doesn't like a very basic you know this doesn't like a very basic you know this doesn't do nearly anything but like you know do nearly anything but like you know do nearly anything but like you know it's doing something and so but that's it's doing something and so but that's it's doing something and so but that's definitely a problem. Um, and we like definitely a problem. Um, and we like definitely a problem. Um, and we like used GDB and we were looking at the used GDB and we were looking at the used GDB and we were looking at the stuff and we're looking at back traces stuff and we're looking at back traces stuff and we're looking at back traces and we're using obje to like look at the and we're using obje to like look at the and we're using obje to like look at the actual like output assembly and I was actual like output assembly and I was actual like output assembly and I was like, yeah, okay, this is what's messed like, yeah, okay, this is what's messed like, yeah, okay, this is what's messed up. Cool. And then I tab back over and up. Cool. And then I tab back over and up. Cool. And then I tab back over and look up the window and Claude was like, look up the window and Claude was like, look up the window and Claude was like, I fixed the bug. And so I tried running I fixed the bug. And so I tried running I fixed the bug. And so I tried running it and the program ran and it spit out a it and the program ran and it spit out a it and the program ran and it spit out a number as the exit code and I was like, number as the exit code and I was like, number as the exit code and I was like, that's cool. And I scrolled back through that's cool. And I scrolled back through that's cool. And I scrolled back through the history and Claude had invoked GDB the history and Claude had invoked GDB the history and Claude had invoked GDB to examine the binary. He had like to examine the binary. He had like to examine the binary. He had like looked at obj dump to like figure out looked at obj dump to like figure out looked at obj dump to like figure out what was actually wrong. So it basically what was actually wrong. So it basically what was actually wrong. So it basically did the exact same steps that we did to did the exact same steps that we did to did the exact same steps that we did to like you know and it it found the thing like you know and it it found the thing like you know and it it found the thing that we found and also something we that we found and also something we that we found and also something we didn't find and that made it work. And didn't find and that made it work. And didn't find and that made it work. And so like that was impressive but like so like that was impressive but like so like that was impressive but like also I've asked it to do very simple also I've asked it to do very simple also I've asked it to do very simple things like I recently found in in this things like I recently found in in this things like I recently found in in this sort of feature range I'm working on. It sort of feature range I'm working on. It sort of feature range I'm working on. It had decided that instead of calculating had decided that instead of calculating had decided that instead of calculating like offsets for strrus like you know like offsets for strrus like you know like offsets for strrus like you know struck.x and strr.y by it was it had struck.x and strr.y by it was it had struck.x and strr.y by it was it had just set up a calculate size function just set up a calculate size function just set up a calculate size function that had basically done a pattern match that had basically done a pattern match that had basically done a pattern match on the name of the strruct field for all on the name of the strruct field for all on the name of the strruct field for all the examples and just was calculating the examples and just was calculating the examples and just was calculating offset based on like the name not not offset based on like the name not not offset based on like the name not not not doing any introspection whatsoever not doing any introspection whatsoever not doing any introspection whatsoever and it was just like you know x is a and it was just like you know x is a and it was just like you know x is a 64-bit integer so we'll you know offset 64-bit integer so we'll you know offset 64-bit integer so we'll you know offset by this much and value is used in this

by this much and value is used in this by this much and value is used in this one test and it's like you know 64 bytes one test and it's like you know 64 bytes one test and it's like you know 64 bytes long and so we'll use that or whatever long and so we'll use that or whatever long and so we'll use that or whatever and so I was like that's really dumb and and so I was like that's really dumb and and so I was like that's really dumb and Claude, like you got to actually Claude, like you got to actually Claude, like you got to actually calculate the real thing instead of just calculate the real thing instead of just calculate the real thing instead of just doing that. And it was like, you're doing that. And it was like, you're doing that. And it was like, you're right. And then it started like it right. And then it started like it right. And then it started like it started to be like, okay, you know, like started to be like, okay, you know, like started to be like, okay, you know, like um I'm going to like, you know, fix this um I'm going to like, you know, fix this um I'm going to like, you know, fix this for real. And it started going down the for real. And it started going down the for real. And it started going down the path of fixing it for real. And then it path of fixing it for real. And then it path of fixing it for real. And then it was like, wait, I think there's a was like, wait, I think there's a was like, wait, I think there's a simpler thing. What if we could just simpler thing. What if we could just simpler thing. What if we could just estimate it based off the name? I'm estimate it based off the name? I'm estimate it based off the name? I'm going to undo my patches and try to do going to undo my patches and try to do going to undo my patches and try to do that instead. And I'd be like, Claude, that instead. And I'd be like, Claude, that instead. And I'd be like, Claude, we were just trying to fix you doing we were just trying to fix you doing we were just trying to fix you doing this by doing it the right way. this by doing it the right way. this by doing it the right way. >> Squirrel. >> Squirrel. >> Squirrel. >> Yeah. Exactly. So, it's like it's it's >> Yeah. Exactly. So, it's like it's it's >> Yeah. Exactly. So, it's like it's it's one or the other. And I think one or the other. And I think one or the other. And I think >> but it's a it's a like I've described it >> but it's a it's a like I've described it >> but it's a it's a like I've described it in when I try to teach this stuff is in when I try to teach this stuff is in when I try to teach this stuff is like a pachinko machine or plinko where like a pachinko machine or plinko where like a pachinko machine or plinko where you drop the thing and it starts you drop the thing and it starts you drop the thing and it starts bouncing around and every once in a bouncing around and every once in a bouncing around and every once in a while it rolls a d20 and it go like ah while it rolls a d20 and it go like ah while it rolls a d20 and it go like ah and it runs over that direction because and it runs over that direction because and it runs over that direction because it's not smart. Like we it's it's it's not smart. Like we it's it's it's not smart. Like we it's it's amazing. It's a miracle. It is not amazing. It's a miracle. It is not amazing. It's a miracle. It is not smart. smart. smart. >> Yeah. It's it's definitely I think >> Yeah. It's it's definitely I think >> Yeah. It's it's definitely I think sometimes it can be very smart. And I sometimes it can be very smart. And I sometimes it can be very smart. And I think I've been trying to I'm trying to think I've been trying to I'm trying to think I've been trying to I'm trying to think a lot about what I what do I think think a lot about what I what do I think think a lot about what I what do I think smart even means? Like I'm I'm in a smart even means? Like I'm I'm in a smart even means? Like I'm I'm in a space I'm like what does thinking even space I'm like what does thinking even space I'm like what does thinking even mean? I'm not actually mean? I'm not actually mean? I'm not actually >> I guess what I'm saying it's like not >> I guess what I'm saying it's like not >> I guess what I'm saying it's like not intrinsically smart. Like I don't know intrinsically smart. Like I don't know intrinsically smart. Like I don't know like I've joked that maybe I'm just like I've joked that maybe I'm just like I've joked that maybe I'm just people listen to the show and they're people listen to the show and they're people listen to the show and they're like oh there's another handsomemanism.

like oh there's another handsomemanism. like oh there's another handsomemanism. It's like I'm just a stat statistical It's like I'm just a stat statistical It's like I'm just a stat statistical model. Like there's the same five things model. Like there's the same five things model. Like there's the same five things that Hanselman says. Like we're all we that Hanselman says. Like we're all we that Hanselman says. Like we're all we all have our our things that we say that all have our our things that we say that all have our our things that we say that get stuck in our mouths. I have spent a get stuck in our mouths. I have spent a get stuck in our mouths. I have spent a lot of time around a two-year-old lot of time around a two-year-old lot of time around a two-year-old recently, and at the same time, I'm recently, and at the same time, I'm recently, and at the same time, I'm getting angry replies on Blue Sky that getting angry replies on Blue Sky that getting angry replies on Blue Sky that are like, "LMs aren't intelligent. They are like, "LMs aren't intelligent. They are like, "LMs aren't intelligent. They can't think. All they do is repeat what can't think. All they do is repeat what can't think. All they do is repeat what they've heard before and then she just they've heard before and then she just they've heard before and then she just repeats every every single thing she repeats every every single thing she repeats every every single thing she hears comes out of her mouth." hears comes out of her mouth." hears comes out of her mouth." >> So, here you are building a statistical >> So, here you are building a statistical >> So, here you are building a statistical model of a human. model of a human. model of a human. >> Yeah, exactly. And I'm like, and that >> Yeah, exactly. And I'm like, and that >> Yeah, exactly. And I'm like, and that doesn't mean I think that an LM is a doesn't mean I think that an LM is a doesn't mean I think that an LM is a tool is a is a child or that a child is tool is a is a child or that a child is tool is a is a child or that a child is like, you know, not more than the like, you know, not more than the like, you know, not more than the parallels are crazy because it's like parallels are crazy because it's like parallels are crazy because it's like it's a stochcastic parrot. Well, that's it's a stochcastic parrot. Well, that's it's a stochcastic parrot. Well, that's a pretty good analogy. a pretty good analogy. a pretty good analogy. >> I don't Now, I don't want to call you >> I don't Now, I don't want to call you >> I don't Now, I don't want to call you out, but I have to say I am looking at out, but I have to say I am looking at out, but I have to say I am looking at your GitHub graph here your GitHub graph here your GitHub graph here >> and it was dark green and then around >> and it was dark green and then around >> and it was dark green and then around June, early June, late May, it started June, early June, late May, it started June, early June, late May, it started to get lighter green. to get lighter green. to get lighter green. >> Does that correlate to your enthusiasm >> Does that correlate to your enthusiasm >> Does that correlate to your enthusiasm for writing code with a assistant? for writing code with a assistant? for writing code with a assistant? >> The problem is that my current work >> The problem is that my current work >> The problem is that my current work product is entirely private and so it is product is entirely private and so it is product is entirely private and so it is not going to show up on my GitHub. Okay.

not going to show up on my GitHub. Okay. not going to show up on my GitHub. Okay. And And And >> so that green is not a direct >> so that green is not a direct >> so that green is not a direct correlation like you found coding with correlation like you found coding with correlation like you found coding with AI. AI. AI. >> Yeah. Yeah. Totally. Um my now I'm >> Yeah. Yeah. Totally. Um my now I'm >> Yeah. Yeah. Totally. Um my now I'm curious. I'm going to look at it since I curious. I'm going to look at it since I curious. I'm going to look at it since I can see my my private one like is that can see my my private one like is that can see my my private one like is that >> because there's a check box that says >> because there's a check box that says >> because there's a check box that says you know private GitHub repositories you know private GitHub repositories you know private GitHub repositories will show up as green but it looks like will show up as green but it looks like will show up as green but it looks like you got into the book and into Rust and you got into the book and into Rust and you got into the book and into Rust and into RU which rue rue is when into RU which rue rue is when into RU which rue rue is when >> that kind of got public. So I was just >> that kind of got public. So I was just >> that kind of got public. So I was just curious. see my bad compiler code, you curious. see my bad compiler code, you curious. see my bad compiler code, you can go check out my RU repository. Yeah, can go check out my RU repository. Yeah, can go check out my RU repository. Yeah, sounds like odd claims that it's fixed sounds like odd claims that it's fixed sounds like odd claims that it's fixed everything but three of my tests everything but three of my tests everything but three of my tests actually just now. So, that'll be a fun actually just now. So, that'll be a fun actually just now. So, that'll be a fun thing to review after the show. But, um thing to review after the show. But, um thing to review after the show. But, um >> but yeah, so it definitely definitely >> but yeah, so it definitely definitely >> but yeah, so it definitely definitely there's like June is a bunch and then there's like June is a bunch and then there's like June is a bunch and then there's sort of three weeks of much there's sort of three weeks of much there's sort of three weeks of much lighter things and then July gets like a lighter things and then July gets like a lighter things and then July gets like a lot heavier and so you I think just life lot heavier and so you I think just life lot heavier and so you I think just life kind of happens like I'm now I'm 39. kind of happens like I'm now I'm 39. kind of happens like I'm now I'm 39. I've been touching some grass sometimes. I've been touching some grass sometimes. I've been touching some grass sometimes. Uh, and so I'm not like putting in the Uh, and so I'm not like putting in the Uh, and so I'm not like putting in the hours. If you, you know, if you look at hours. If you, you know, if you look at hours. If you, you know, if you look at my like 2011 get our 20 even 2008 or my like 2011 get our 20 even 2008 or my like 2011 get our 20 even 2008 or 2010 or whatever, like I was going 2010 or whatever, like I was going 2010 or whatever, like I was going pretty hard for many years there. Uh, pretty hard for many years there. Uh, pretty hard for many years there. Uh, but like, you know, now it's like much but like, you know, now it's like much but like, you know, now it's like much much more kind of chilled out.

much more kind of chilled out. much more kind of chilled out. >> But are you having more fun? Cuz I feel >> But are you having more fun? Cuz I feel >> But are you having more fun? Cuz I feel like yes, I'm doing more with AI code like yes, I'm doing more with AI code like yes, I'm doing more with AI code generation, but I'm enjoying it more. It generation, but I'm enjoying it more. It generation, but I'm enjoying it more. It it is so far a kind of precision, right? it is so far a kind of precision, right? it is so far a kind of precision, right? Because like the the joke is well I'm Because like the the joke is well I'm Because like the the joke is well I'm going to use specd driven development going to use specd driven development going to use specd driven development and I'll write markdown files and then and I'll write markdown files and then and I'll write markdown files and then I'll feed those into cloud or like or I'll feed those into cloud or like or I'll feed those into cloud or like or I'll feed that into copilot and it's I'll feed that into copilot and it's I'll feed that into copilot and it's like maybe I should just use a really like maybe I should just use a really like maybe I should just use a really precise grammar you know and then the precise grammar you know and then the precise grammar you know and then the the slippery slope right back into the slippery slope right back into the slippery slope right back into compilers again. compilers again. compilers again. >> Totally. It's it's it's interesting. >> Totally. It's it's it's interesting. >> Totally. It's it's it's interesting. There was a paper I saw recently that uh There was a paper I saw recently that uh There was a paper I saw recently that uh like these tools will do better if you like these tools will do better if you like these tools will do better if you have good variable names. like they took have good variable names. like they took have good variable names. like they took the same codebase and they asked it to the same codebase and they asked it to the same codebase and they asked it to fix a bug and then they transformed the fix a bug and then they transformed the fix a bug and then they transformed the source code to have gibberish, you know, source code to have gibberish, you know, source code to have gibberish, you know, names and that didn't work. And it's names and that didn't work. And it's names and that didn't work. And it's because, you know, it's like doing because, you know, it's like doing because, you know, it's like doing correlations. And so if it, you know, correlations. And so if it, you know, correlations. And so if it, you know, sees something that's named a certain sees something that's named a certain sees something that's named a certain way, it's going to think that it works way, it's going to think that it works way, it's going to think that it works in a certain way because it's just the in a certain way because it's just the in a certain way because it's just the same way that we kind of like look at same way that we kind of like look at same way that we kind of like look at these things. And so I I'm definitely these things. And so I I'm definitely these things. And so I I'm definitely having fun. Uh I think that like the having fun. Uh I think that like the having fun. Uh I think that like the time I've had to be programming versus time I've had to be programming versus time I've had to be programming versus not has kind of changed uh you know, in not has kind of changed uh you know, in not has kind of changed uh you know, in my life a lot over the last couple years my life a lot over the last couple years my life a lot over the last couple years for sure and especially lately. But I'm for sure and especially lately. But I'm for sure and especially lately. But I'm definitely enjoying it. I think that definitely enjoying it. I think that definitely enjoying it. I think that it's brought me a lot of stress because it's brought me a lot of stress because it's brought me a lot of stress because of the many of the people I know that of the many of the people I know that of the many of the people I know that are super anti these tools are some of are super anti these tools are some of are super anti these tools are some of my best friends. And I've already lost a my best friends. And I've already lost a my best friends. And I've already lost a couple of friends or at least been let's couple of friends or at least been let's couple of friends or at least been let's say like had very strong words exchanged say like had very strong words exchanged say like had very strong words exchanged between people that uh you know I between people that uh you know I between people that uh you know I thought were friends or not um based on thought were friends or not um based on thought were friends or not um based on my like refusal to totally disavow these

my like refusal to totally disavow these my like refusal to totally disavow these tools entirely. And so I have several tools entirely. And so I have several tools entirely. And so I have several friends who are like working on projects friends who are like working on projects friends who are like working on projects that are pretty terrified to find out that are pretty terrified to find out that are pretty terrified to find out that you know who's going to get upset that you know who's going to get upset that you know who's going to get upset with them if they talk about their with them if they talk about their with them if they talk about their usage. And so that part has put a damper usage. And so that part has put a damper usage. And so that part has put a damper on it. But the actual like act of doing on it. But the actual like act of doing on it. But the actual like act of doing the thing it's definitely been a lot of the thing it's definitely been a lot of the thing it's definitely been a lot of fun. Even when I do the spectr stuff fun. Even when I do the spectr stuff fun. Even when I do the spectr stuff like I will absolutely do sometimes, you like I will absolutely do sometimes, you like I will absolutely do sometimes, you know, do the whole markdown thing and I know, do the whole markdown thing and I know, do the whole markdown thing and I think that's also like a good uh a good think that's also like a good uh a good think that's also like a good uh a good strategy. It's like kind of like a lot strategy. It's like kind of like a lot strategy. It's like kind of like a lot of things that are good for LM also seem of things that are good for LM also seem of things that are good for LM also seem to be good for humans in many ways and to be good for humans in many ways and to be good for humans in many ways and it's kind of it's kind of interesting. it's kind of it's kind of interesting. it's kind of it's kind of interesting. Um, I had uh I was on Richard Felman's Um, I had uh I was on Richard Felman's Um, I had uh I was on Richard Felman's podcast a month or two ago and he was podcast a month or two ago and he was podcast a month or two ago and he was talking about he had a comment and on a talking about he had a comment and on a talking about he had a comment and on a function and he'd asked Zed because he function and he'd asked Zed because he function and he'd asked Zed because he works at Zed and so he uses that as a works at Zed and so he uses that as a works at Zed and so he uses that as a thing to uh to refactor the body of some thing to uh to refactor the body of some thing to uh to refactor the body of some code and then it had made a change in code and then it had made a change in code and then it had made a change in the comment and at first he was mad the comment and at first he was mad the comment and at first he was mad because he's like I didn't tell you to because he's like I didn't tell you to because he's like I didn't tell you to touch the comments I told you to rewrite touch the comments I told you to rewrite touch the comments I told you to rewrite the code but then he realized that there the code but then he realized that there the code but then he realized that there was a side effect of the way the code was a side effect of the way the code was a side effect of the way the code was previously implemented that was was previously implemented that was was previously implemented that was described in the code comment and when described in the code comment and when described in the code comment and when he had made the refactoring it broke he had made the refactoring it broke he had made the refactoring it broke that thing and therefore the code that thing and therefore the code that thing and therefore the code comment comment was wrong. And so the comment comment was wrong. And so the comment comment was wrong. And so the tool editing the comment had drawn tool editing the comment had drawn tool editing the comment had drawn attention to like there's a behavior attention to like there's a behavior attention to like there's a behavior here that's like not expressed in the here that's like not expressed in the here that's like not expressed in the type signature that you know you need to type signature that you know you need to type signature that you know you need to care about. And he was like oh that's care about. And he was like oh that's care about. And he was like oh that's like really interesting because that like really interesting because that like really interesting because that gave me sort of like a point to be able gave me sort of like a point to be able gave me sort of like a point to be able to pay attention to that. And so I think to pay attention to that. And so I think to pay attention to that. And so I think like a lot of these kind of things are like a lot of these kind of things are like a lot of these kind of things are kind of interesting because like you kind of interesting because like you kind of interesting because like you know I'm even like the docs guy and you know I'm even like the docs guy and you know I'm even like the docs guy and you know it's not fun a lot of the times know it's not fun a lot of the times know it's not fun a lot of the times writing docs. And like are LM docs good?

writing docs. And like are LM docs good? writing docs. And like are LM docs good? Not necessarily. But like if you hate Not necessarily. But like if you hate Not necessarily. But like if you hate writing docs, you can get something and writing docs, you can get something and writing docs, you can get something and something is often better than nothing. something is often better than nothing. something is often better than nothing. And especially cuz like comments that go And especially cuz like comments that go And especially cuz like comments that go out of the way comments get really bad out of the way comments get really bad out of the way comments get really bad is when they get out of sync with the is when they get out of sync with the is when they get out of sync with the implementation. And so if you can like, implementation. And so if you can like, implementation. And so if you can like, you know, have a tool that is able to you know, have a tool that is able to you know, have a tool that is able to reasonably check that they're reasonably reasonably check that they're reasonably reasonably check that they're reasonably up todate. Like as much as I dislike a up todate. Like as much as I dislike a up todate. Like as much as I dislike a lot of LLM writing, I think that like lot of LLM writing, I think that like lot of LLM writing, I think that like LLM generated documentation is better LLM generated documentation is better LLM generated documentation is better than zero documentation. Would I prefer than zero documentation. Would I prefer than zero documentation. Would I prefer finely crafted docs? Absolutely. But finely crafted docs? Absolutely. But finely crafted docs? Absolutely. But like nobody's nobody's doing that on like nobody's nobody's doing that on like nobody's nobody's doing that on your Saturday projects. But like you can your Saturday projects. But like you can your Saturday projects. But like you can get a reasonable amount of docs at a get a reasonable amount of docs at a get a reasonable amount of docs at a better standard by using tools like better standard by using tools like better standard by using tools like this. this. this. >> Yeah. I've got a a a thing I'm open >> Yeah. I've got a a a thing I'm open >> Yeah. I've got a a a thing I'm open sourcing soon and I uh used an LLM to sourcing soon and I uh used an LLM to sourcing soon and I uh used an LLM to help generate the the readme and it's help generate the the readme and it's help generate the the readme and it's just it's it's a better readme than I just it's it's a better readme than I just it's it's a better readme than I would have written. Like I'm not going would have written. Like I'm not going would have written. Like I'm not going to ship it as is, but it's better. to ship it as is, but it's better. to ship it as is, but it's better. >> Yeah. And you definitely got to like >> Yeah. And you definitely got to like >> Yeah. And you definitely got to like rein it in a lot too. like the rein it in a lot too. like the rein it in a lot too. like the exuberance and the emojis and the the exuberance and the emojis and the the exuberance and the emojis and the the bulleted lists are like definitely get a bulleted lists are like definitely get a bulleted lists are like definitely get a lot uh lot uh lot uh >> M dash is an emoji. >> M dash is an emoji. >> M dash is an emoji. >> Yeah, I love using M dashes too. I'm so >> Yeah, I love using M dashes too. I'm so >> Yeah, I love using M dashes too. I'm so mad that mad that mad that >> I know what the M dashes I was an M dash >> I know what the M dashes I was an M dash >> I know what the M dashes I was an M dash person early on and now it's a sign of person early on and now it's a sign of person early on and now it's a sign of the uh the apocalypse.

the uh the apocalypse. the uh the apocalypse. >> When you have Brian on, he's also a big >> When you have Brian on, he's also a big >> When you have Brian on, he's also a big M dash guy. So that's good. Yeah. Yeah. M dash guy. So that's good. Yeah. Yeah. M dash guy. So that's good. Yeah. Yeah. >> I can feel the M dashes when I'm >> I can feel the M dashes when I'm >> I can feel the M dashes when I'm speaking. speaking. speaking. >> Yeah, that's exactly it's like that's >> Yeah, that's exactly it's like that's >> Yeah, that's exactly it's like that's not a that's not a semicolon, people. not a that's not a semicolon, people. not a that's not a semicolon, people. That's an M dash. That's an M dash. That's an M dash. >> Yeah. I've I've I've told like both >> Yeah. I've I've I've told like both >> Yeah. I've I've I've told like both Claude and Chhat GPT like, "Hey, this Claude and Chhat GPT like, "Hey, this Claude and Chhat GPT like, "Hey, this text you gave me is far too LMY. Can you text you gave me is far too LMY. Can you text you gave me is far too LMY. Can you like make it not please?" And it's like like make it not please?" And it's like like make it not please?" And it's like I understand, you know, and then it's so I understand, you know, and then it's so I understand, you know, and then it's so funny because the first thing they'll funny because the first thing they'll funny because the first thing they'll say back is like, "You're totally say back is like, "You're totally say back is like, "You're totally right." Which is also like a very right." Which is also like a very right." Which is also like a very >> I'm so sick of the you're totally right. >> I'm so sick of the you're totally right. >> I'm so sick of the you're totally right. I'm over the you're totally right. I'm over the you're totally right. I'm over the you're totally right. >> Yeah. And I'm starting to notice. And >> Yeah. And I'm starting to notice. And >> Yeah. And I'm starting to notice. And the other thing is that I feel like I the other thing is that I feel like I the other thing is that I feel like I pioneered emoji and business email and pioneered emoji and business email and pioneered emoji and business email and now it just makes me look like a now it just makes me look like a now it just makes me look like a schmuck. schmuck. schmuck. >> Should have gotten the patents on it >> Should have gotten the patents on it >> Should have gotten the patents on it and then Yeah. Yeah. Well, thank you so and then Yeah. Yeah. Well, thank you so and then Yeah. Yeah. Well, thank you so much, Steve Clavnik, for hanging out much, Steve Clavnik, for hanging out much, Steve Clavnik, for hanging out with me today. with me today. with me today. >> Yeah, it's always great to talk to you. >> Yeah, it's always great to talk to you. >> Yeah, it's always great to talk to you. >> We have accomplished nothing, but we >> We have accomplished nothing, but we >> We have accomplished nothing, but we have enjoyed ourselves, and that is what have enjoyed ourselves, and that is what have enjoyed ourselves, and that is what is important. And I'm glad that you're is important. And I'm glad that you're is important. And I'm glad that you're enjoying yourself uh writing some code enjoying yourself uh writing some code enjoying yourself uh writing some code with coding editors. You can learn more with coding editors. You can learn more with coding editors. You can learn more about Steve and his thoughts at about Steve and his thoughts at about Steve and his thoughts at steveclavnick.com. You can check out his steveclavnick.com. You can check out his steveclavnick.com. You can check out his book and follow him on Blue Sky. This book and follow him on Blue Sky. This book and follow him on Blue Sky. This has been another episode of Hansel has been another episode of Hansel has been another episode of Hansel Minutes and we'll see you again next Minutes and we'll see you again next Minutes and we'll see you again next week.