Where is AI taking us? - with The Pragmatic Programmer Gergely Orosz

Like, I would never write that app. That Like, I would never write that app. That would be ridiculous. Would take me like would be ridiculous. Would take me like would be ridiculous. Would take me like 20 20 20 >> Ridiculous. Why why would you? No. >> Ridiculous. Why why would you? No. >> Ridiculous. Why why would you? No. Right. But now suddenly the Lego pieces, Right. But now suddenly the Lego pieces, Right. But now suddenly the Lego pieces, we've got OAuth, we've got personal we've got OAuth, we've got personal we've got OAuth, we've got personal access tokens, we've got nice clean REST access tokens, we've got nice clean REST access tokens, we've got nice clean REST APIs, a pattern to do it. We've got APIs, a pattern to do it. We've got APIs, a pattern to do it. We've got Python and .NET and uh JavaScript all Python and .NET and uh JavaScript all Python and .NET and uh JavaScript all very well understood to go and do these very well understood to go and do these very well understood to go and do these things. And I just said, "Go and tell me things. And I just said, "Go and tell me things. And I just said, "Go and tell me if any meetings are stressing me out." if any meetings are stressing me out." if any meetings are stressing me out." And it turns out that I'm going low And it turns out that I'm going low And it turns out that I'm going low blood sugar on Mondays because I don't blood sugar on Mondays because I don't blood sugar on Mondays because I don't eat lunch on Mondays. I never put it eat lunch on Mondays. I never put it eat lunch on Mondays. I never put it together together together until I combined effectively a join until I combined effectively a join until I combined effectively a join across Outlook calendar and my blood across Outlook calendar and my blood across Outlook calendar and my blood sugar. And it it took 20 minutes. And sugar. And it it took 20 minutes. And sugar. And it it took 20 minutes. And then I wrote a whole then I wrote a whole then I wrote a whole a report. And then I said, "Make it a a report. And then I said, "Make it a a report. And then I said, "Make it a scale and put it in GitHub." And now scale and put it in GitHub." And now scale and put it in GitHub." And now other people are using it. That's other people are using it. That's other people are using it. That's insane. Hi friends, I'm Scott Hanselman insane. Hi friends, I'm Scott Hanselman insane. Hi friends, I'm Scott Hanselman and this is another episode of and this is another episode of and this is another episode of Hanselminutes. Today I have the extreme Hanselminutes. Today I have the extreme Hanselminutes. Today I have the extreme pleasure of chatting with Gergely Orosz, pleasure of chatting with Gergely Orosz, pleasure of chatting with Gergely Orosz, the author of the Pragmatic Engineer the author of the Pragmatic Engineer the author of the Pragmatic Engineer Newsletter, number one technology Newsletter, number one technology Newsletter, number one technology newsletter on Substack, and just a newsletter on Substack, and just a newsletter on Substack, and just a lovely gentleman. How are you, sir? lovely gentleman. How are you, sir? lovely gentleman. How are you, sir? Doing great, Scott. It's It's really Doing great, Scott. It's It's really Doing great, Scott. It's It's really nice to to be here and catch up this nice to to be here and catch up this nice to to be here and catch up this time over video. Last time it was in time over video. Last time it was in time over video. Last time it was in person. Yeah, yeah. We hung out in person. Yeah, yeah. We hung out in person. Yeah, yeah. We hung out in person for a little while and now we're person for a little while and now we're person for a little while and now we're on we're on video, we're on audio on the on we're on video, we're on audio on the on we're on video, we're on audio on the podcast. You've got the Dune ornithopter podcast. You've got the Dune ornithopter podcast. You've got the Dune ornithopter Lego on your credibility bookshelf with Lego on your credibility bookshelf with Lego on your credibility bookshelf with uh all of the great books. I see Code uh all of the great books. I see Code uh all of the great books. I see Code Complete by Steve McConnell there in the Complete by Steve McConnell there in the Complete by Steve McConnell there in the background. I can immediately say this background. I can immediately say this background. I can immediately say this is a serious person right now. Yeah, and is a serious person right now. Yeah, and is a serious person right now. Yeah, and I I had the extreme joy and and I I had the extreme joy and and I I had the extreme joy and and privilege to interview Steve McConnell privilege to interview Steve McConnell privilege to interview Steve McConnell Did he sign it? Did he sign it? about a

Did he sign it? Did he sign it? about a Did he sign it? Did he sign it? about a year ago. He did sign year ago. He did sign year ago. He did sign Wait. Yes, he did. Wait. Yes, he did. Wait. Yes, he did. >> A signed I I have a signed book. I'm >> A signed I I have a signed book. I'm >> A signed I I have a signed book. I'm showing it to the camera. Oh my god, showing it to the camera. Oh my god, showing it to the camera. Oh my god, with everything with everything with everything >> was a big deal because Steve McConnell, >> was a big deal because Steve McConnell, >> was a big deal because Steve McConnell, he actually left tech as a whole about 3 he actually left tech as a whole about 3 he actually left tech as a whole about 3 years ago. He had an amazing run and now years ago. He had an amazing run and now years ago. He had an amazing run and now he's just reinventing himself, but he is he's just reinventing himself, but he is he's just reinventing himself, but he is just as thoughtful as as ever. And the just as thoughtful as as ever. And the just as thoughtful as as ever. And the the crazy thing about this book Code the crazy thing about this book Code the crazy thing about this book Code Complete that was so inspiring for me, Complete that was so inspiring for me, Complete that was so inspiring for me, Steve McConnell wrote this when he had Steve McConnell wrote this when he had Steve McConnell wrote this when he had five years of experience or so. He wrote five years of experience or so. He wrote five years of experience or so. He wrote 900 pages which has been the Bible for 900 pages which has been the Bible for 900 pages which has been the Bible for about 20 years for so many people. And about 20 years for so many people. And about 20 years for so many people. And one thing that it reminded me is is you one thing that it reminded me is is you one thing that it reminded me is is you don't need to wait to you know have 20 don't need to wait to you know have 20 don't need to wait to you know have 20 or 30 or 40 years of experience do or 30 or 40 years of experience do or 30 or 40 years of experience do something that can be industry defining something that can be industry defining something that can be industry defining or helping just so many people. You can or helping just so many people. You can or helping just so many people. You can start when you have one year, two years, start when you have one year, two years, start when you have one year, two years, three years of experience. You don't three years of experience. You don't three years of experience. You don't need to wait for longer. You know, need to wait for longer. You know, need to wait for longer. You know, that's a really great thing that you've that's a really great thing that you've that's a really great thing that you've said because I've always tried to said because I've always tried to said because I've always tried to express to people that I'll read your express to people that I'll read your express to people that I'll read your blog. I don't care how many years you've blog. I don't care how many years you've blog. I don't care how many years you've been doing this because no one has your been doing this because no one has your been doing this because no one has your perspective. No one has perspective. No one has perspective. No one has your I like oh, I don't know. Everyone's your I like oh, I don't know. Everyone's your I like oh, I don't know. Everyone's already written everything there is to already written everything there is to already written everything there is to write about Python. I don't know your write about Python. I don't know your write about Python. I don't know your perspective. I don't know how you got perspective. I don't know how you got perspective. I don't know how you got into it. I think that's great. That book into it. I think that's great. That book into it. I think that's great. That book uh Code Complete, that's of course is uh Code Complete, that's of course is uh Code Complete, that's of course is the new uh version two, that book came the new uh version two, that book came the new uh version two, that book came out 1993.

out 1993. out 1993. I started coding for money in '92. So, I started coding for money in '92. So, I started coding for money in '92. So, Code Complete was literally my entree Code Complete was literally my entree Code Complete was literally my entree into software engineering. Like I I into software engineering. Like I I into software engineering. Like I I landed in software around April of 2000 landed in software around April of 2000 landed in software around April of 2000 uh April of 1992 rather and then Code uh April of 1992 rather and then Code uh April of 1992 rather and then Code Complete like just Complete like just Complete like just people understand it was the biggest people understand it was the biggest people understand it was the biggest thing. thing. thing. It was a it was a word-of-mouth book. I It was a it was a word-of-mouth book. I It was a it was a word-of-mouth book. I did not realize that he only had five did not realize that he only had five did not realize that he only had five years experience at the time. years experience at the time. years experience at the time. Yep. Wow. Yep. Wow. Yep. Wow. >> And in fact fun fact just on like how >> And in fact fun fact just on like how >> And in fact fun fact just on like how funny things are, he told me and we and funny things are, he told me and we and funny things are, he told me and we and I I have a podcast episode on on on my I I have a podcast episode on on on my I I have a podcast episode on on on my podcast with him for where we talked podcast with him for where we talked podcast with him for where we talked about an hour and a half about these about an hour and a half about these about an hour and a half about these topics. But when he published apparently topics. But when he published apparently topics. But when he published apparently the publisher did not expect this book the publisher did not expect this book the publisher did not expect this book would sell. They just wanted a so-called would sell. They just wanted a so-called would sell. They just wanted a so-called backfiller in their catalog just to have backfiller in their catalog just to have backfiller in their catalog just to have something there and apparently the something there and apparently the something there and apparently the publisher was the most surprised at how publisher was the most surprised at how publisher was the most surprised at how many people started to buy. So, again many people started to buy. So, again many people started to buy. So, again just another uh thing that even even the just another uh thing that even even the just another uh thing that even even the publisher, even the person who read this publisher, even the person who read this publisher, even the person who read this 900 pages did not expect this to be big. 900 pages did not expect this to be big. 900 pages did not expect this to be big. So, sometimes you just got to do things So, sometimes you just got to do things So, sometimes you just got to do things and even if you don't think it's a big and even if you don't think it's a big and even if you don't think it's a big deal. Steve told me that he didn't think deal. Steve told me that he didn't think deal. Steve told me that he didn't think this was that revolutionary. I mean, who this was that revolutionary. I mean, who this was that revolutionary. I mean, who was he? He had like everyone probably was he? He had like everyone probably was he? He had like everyone probably should have known this thing. So, just should have known this thing. So, just should have known this thing. So, just one more thing, just do stuff, put it one more thing, just do stuff, put it one more thing, just do stuff, put it out there. Worst case is, you know, you out there. Worst case is, you know, you out there. Worst case is, you know, you might have one help one person, even might have one help one person, even might have one help one person, even that's an amazing feeling, I can tell that's an amazing feeling, I can tell that's an amazing feeling, I can tell you.

you. you. You know, that's a great that's a great You know, that's a great that's a great You know, that's a great that's a great way to start the conversation because way to start the conversation because way to start the conversation because there's this funny there's this lovely there's this funny there's this lovely there's this funny there's this lovely comedian that I'm mutuals with on TikTok comedian that I'm mutuals with on TikTok comedian that I'm mutuals with on TikTok named Rodney Norman Rodney Norman. He named Rodney Norman Rodney Norman. He named Rodney Norman Rodney Norman. He looks like a crazy mad scientist like looks like a crazy mad scientist like looks like a crazy mad scientist like from Back to the Future and he's got a from Back to the Future and he's got a from Back to the Future and he's got a wonderful long ZZ Top beard and he kind wonderful long ZZ Top beard and he kind wonderful long ZZ Top beard and he kind of pops up on your screen and he says, of pops up on your screen and he says, of pops up on your screen and he says, "You know, you can just do stuff. "You know, you can just do stuff. "You know, you can just do stuff. You can just You don't have to ask You can just You don't have to ask You can just You don't have to ask permission. permission. permission. You just make things. You just make things. You just make things. Okay, have a great day." And it just, Okay, have a great day." And it just, Okay, have a great day." And it just, you know, you're just doing your thing you know, you're just doing your thing you know, you're just doing your thing and he's just there to tell you that you and he's just there to tell you that you and he's just there to tell you that you can just do stuff. can just do stuff. can just do stuff. And man, I'm just doing so much stuff And man, I'm just doing so much stuff And man, I'm just doing so much stuff right now. I have gotten more done since right now. I have gotten more done since right now. I have gotten more done since Opus Opus Opus uh than probably in the previous 2 uh than probably in the previous 2 uh than probably in the previous 2 years. And by doing stuff, I mean years. And by doing stuff, I mean years. And by doing stuff, I mean shipping interesting stuff. I feel like shipping interesting stuff. I feel like shipping interesting stuff. I feel like I got a rocket ship strapped to my back. I got a rocket ship strapped to my back. I got a rocket ship strapped to my back. Are you having as much fun as I am? Are you having as much fun as I am? Are you having as much fun as I am? Yeah, I I've been very surprised on on Yeah, I I've been very surprised on on Yeah, I I've been very surprised on on how how how just really good these agents have just really good these agents have just really good these agents have gotten. And I I'm someone who's gotten. And I I'm someone who's gotten. And I I'm someone who's skeptical with any any any hype, any skeptical with any any any hype, any skeptical with any any any hype, any claim. I've been skeptical about crypto. claim. I've been skeptical about crypto. claim. I've been skeptical about crypto. Not not for the sake of crypto, but just Not not for the sake of crypto, but just Not not for the sake of crypto, but just the hyperbolic claims. I've been the hyperbolic claims. I've been the hyperbolic claims. I've been skeptical about AI. Mhm.

skeptical about AI. Mhm. skeptical about AI. Mhm. >> Cuz early on about a year and a half >> Cuz early on about a year and a half >> Cuz early on about a year and a half ago, we had people saying, "Oh, here's ago, we had people saying, "Oh, here's ago, we had people saying, "Oh, here's this AI that's going to replace software this AI that's going to replace software this AI that's going to replace software engineers." And again, it sounded very engineers." And again, it sounded very engineers." And again, it sounded very hyperbolic and also a little bit hyperbolic and also a little bit hyperbolic and also a little bit depressing to be fair. 100% agree. But depressing to be fair. 100% agree. But depressing to be fair. 100% agree. But then I always like to look at stuff. I then I always like to look at stuff. I then I always like to look at stuff. I like to try out firsthand what can it like to try out firsthand what can it like to try out firsthand what can it do? And again, it was it was pretty do? And again, it was it was pretty do? And again, it was it was pretty good. It was decent auto complete good. It was decent auto complete good. It was decent auto complete initially. It then started to do some initially. It then started to do some initially. It then started to do some stuff, but it started it hallucinated stuff, but it started it hallucinated stuff, but it started it hallucinated when I used ChatGPT or or I tried to use when I used ChatGPT or or I tried to use when I used ChatGPT or or I tried to use it for anything more complex, you know, it for anything more complex, you know, it for anything more complex, you know, like cursor. Early on, the suggestions like cursor. Early on, the suggestions like cursor. Early on, the suggestions were maybe not exactly what I was were maybe not exactly what I was were maybe not exactly what I was thinking of. But I'll also like over thinking of. But I'll also like over thinking of. But I'll also like over over the the winter break over the the winter break over the the winter break I I can still code pretty well I I can still code pretty well I I can still code pretty well if I put myself to it, but I just don't if I put myself to it, but I just don't if I put myself to it, but I just don't really do it because it's a lot of time really do it because it's a lot of time really do it because it's a lot of time to get in the zone. to get in the zone. to get in the zone. My my side projects are are I have a lot My my side projects are are I have a lot My my side projects are are I have a lot of side projects and and also I have of side projects and and also I have of side projects and and also I have some of my my business runs on my own some of my my business runs on my own some of my my business runs on my own APIs. I try to build whenever I can. For APIs. I try to build whenever I can. For APIs. I try to build whenever I can. For example, for a newsletter group example, for a newsletter group example, for a newsletter group subscriptions, there's like a subscriptions, there's like a subscriptions, there's like a self-service API. Companies can sign up self-service API. Companies can sign up self-service API. Companies can sign up and their whole domain can go on there and their whole domain can go on there and their whole domain can go on there and they get reporting and all that and they get reporting and all that and they get reporting and all that stuff. I I built that on a a tech stack stuff. I I built that on a a tech stack stuff. I I built that on a a tech stack that I wasn't that familiar at the time.

that I wasn't that familiar at the time. that I wasn't that familiar at the time. I wanted to play with Express.js and I wanted to play with Express.js and I wanted to play with Express.js and Node.js and and TypeScript. And every Node.js and and TypeScript. And every Node.js and and TypeScript. And every now and then I go back to it, but it now and then I go back to it, but it now and then I go back to it, but it always took me about 30 minutes to like always took me about 30 minutes to like always took me about 30 minutes to like get back, you know, remember the get back, you know, remember the get back, you know, remember the structure, think But I have tests, so structure, think But I have tests, so structure, think But I have tests, so whenever I make a change, I I can whenever I make a change, I I can whenever I make a change, I I can actually tell if I broke something. actually tell if I broke something. actually tell if I broke something. And this winter break, I just went there And this winter break, I just went there And this winter break, I just went there again. Like I have so many ideas and you again. Like I have so many ideas and you again. Like I have so many ideas and you know, like this time I heard Claude code know, like this time I heard Claude code know, like this time I heard Claude code is great. Uh so I just told Claude code is great. Uh so I just told Claude code is great. Uh so I just told Claude code that, you know, build this endpoint and that, you know, build this endpoint and that, you know, build this endpoint and and build me this this feature. And it and build me this this feature. And it and build me this this feature. And it did it. And then I looked at it and I did it. And then I looked at it and I did it. And then I looked at it and I said, "Run the tests." And it did. And said, "Run the tests." And it did. And said, "Run the tests." And it did. And the tests And then I looked at it and the tests And then I looked at it and the tests And then I looked at it and like one of the tests was not great, so like one of the tests was not great, so like one of the tests was not great, so I I had to fix it. But then it did it. I I had to fix it. But then it did it. I I had to fix it. But then it did it. And I found myself that I had spent And I found myself that I had spent And I found myself that I had spent about about about 5 minutes on this thing and it's already 5 minutes on this thing and it's already 5 minutes on this thing and it's already added the thing that I thought would added the thing that I thought would added the thing that I thought would take me 2 hours. 30 minutes to get in take me 2 hours. 30 minutes to get in take me 2 hours. 30 minutes to get in the zone. It's an hour to be in there. the zone. It's an hour to be in there. the zone. It's an hour to be in there. And then my wife said like, "Hey, how And then my wife said like, "Hey, how And then my wife said like, "Hey, how long are you going to be?" And usually long are you going to be?" And usually long are you going to be?" And usually whenever I'm coding or writing for that, whenever I'm coding or writing for that, whenever I'm coding or writing for that, like being in the zone, my time estimate like being in the zone, my time estimate like being in the zone, my time estimate is terribly off and this is a lot of is terribly off and this is a lot of is terribly off and this is a lot of source of conflict. But for this one, I source of conflict. But for this one, I source of conflict. But for this one, I was like, uh just just one more minute. was like, uh just just one more minute. was like, uh just just one more minute. And I literally just put another prompt And I literally just put another prompt And I literally just put another prompt and then I stood up and I went for and then I stood up and I went for and then I stood up and I went for dinner. And my wife was like, "Oh, what dinner. And my wife was like, "Oh, what dinner. And my wife was like, "Oh, what happened? Like you're early. Like were happened? Like you're early. Like were happened? Like you're early. Like were you not working?" I'm like, "I was you not working?" I'm like, "I was you not working?" I'm like, "I was working, but I'm using this thing, this working, but I'm using this thing, this working, but I'm using this thing, this agent." And it's just I'm just having agent." And it's just I'm just having agent." And it's just I'm just having this wild moment again and again and this wild moment again and again and this wild moment again and again and again. Another story was where again, I again. Another story was where again, I again. Another story was where again, I had this like massive wild moment. On my had this like massive wild moment. On my had this like massive wild moment. On my website, I have testimonials of like you website, I have testimonials of like you website, I have testimonials of like you know, people saying nice thing about the know, people saying nice thing about the know, people saying nice thing about the newsletter or or or podcast on Twitter, newsletter or or or podcast on Twitter, newsletter or or or podcast on Twitter, real people. And I I paid about $100 a real people. And I I paid about $100 a real people. And I I paid about $100 a month for this software. The servers month for this software. The servers month for this software. The servers were I can just have a nice or not a were I can just have a nice or not a were I can just have a nice or not a nice, a very simple app and interface

nice, a very simple app and interface nice, a very simple app and interface where I can post a Twitter link, it where I can post a Twitter link, it where I can post a Twitter link, it generates a kind of UI and I can embed generates a kind of UI and I can embed generates a kind of UI and I can embed it with an iframe and I pay for the it with an iframe and I pay for the it with an iframe and I pay for the service. service. service. And I got a bit pissed because I didn't And I got a bit pissed because I didn't And I got a bit pissed because I didn't get an invoice from them. Turns out this get an invoice from them. Turns out this get an invoice from them. Turns out this service has been like sold twice over. service has been like sold twice over. service has been like sold twice over. Their invoice system is a mess. I have a Their invoice system is a mess. I have a Their invoice system is a mess. I have a new invoice coming up. I don't know how new invoice coming up. I don't know how new invoice coming up. I don't know how much I'm going to pay. And I was much I'm going to pay. And I was much I'm going to pay. And I was thinking to myself like hang on. Like thinking to myself like hang on. Like thinking to myself like hang on. Like can I not have an agent can I not have an agent can I not have an agent to replace this cuz I know I like I'm to replace this cuz I know I like I'm to replace this cuz I know I like I'm paying paying paying and so I just don't want to maintain an and so I just don't want to maintain an and so I just don't want to maintain an HTML file that has all these nicely HTML file that has all these nicely HTML file that has all these nicely formatted things. So I told the agent, formatted things. So I told the agent, formatted things. So I told the agent, hey, go there, collect all these hey, go there, collect all these hey, go there, collect all these testimonials, put it in a structure that testimonials, put it in a structure that testimonials, put it in a structure that is easy to maintain cuz I'm thinking is easy to maintain cuz I'm thinking is easy to maintain cuz I'm thinking about that already. Put it in a JSON about that already. Put it in a JSON about that already. Put it in a JSON format. And you know, like like put it format. And you know, like like put it format. And you know, like like put it separately and then build time generate separately and then build time generate separately and then build time generate this HTML and then show me the results. this HTML and then show me the results. this HTML and then show me the results. And in about I I actually measured it And in about I I actually measured it And in about I I actually measured it end to end 20 minutes. I went from I end to end 20 minutes. I went from I end to end 20 minutes. I went from I have the third party that I'm depending have the third party that I'm depending have the third party that I'm depending on to I have no third party. The build on to I have no third party. The build on to I have no third party. The build is passing. It's now pushed out to is passing. It's now pushed out to is passing. It's now pushed out to production and I did two tweaks to it production and I did two tweaks to it production and I did two tweaks to it and I'm done. and I'm done. and I'm done. And to me this is mind-blowing like the And to me this is mind-blowing like the And to me this is mind-blowing like the implications. So like until now again, implications. So like until now again, implications. So like until now again, as a software professional, as someone as a software professional, as someone as a software professional, as someone who knows how to code, knows how to who knows how to code, knows how to who knows how to code, knows how to deploy, I was willing to pick like my deploy, I was willing to pick like my deploy, I was willing to pick like my time is pretty valuable. I kind of like time is pretty valuable. I kind of like time is pretty valuable. I kind of like value my time roughly as like I don't value my time roughly as like I don't value my time roughly as like I don't know, something like $300 an hour or know, something like $300 an hour or know, something like $300 an hour or $200 an hour when I work for kind of $200 an hour when I work for kind of $200 an hour when I work for kind of myself cuz I want to put a value on that myself cuz I want to put a value on that myself cuz I want to put a value on that time. So for me, if it takes an hour, time. So for me, if it takes an hour, time. So for me, if it takes an hour, it's worth paying for me $100 a month.

it's worth paying for me $100 a month. it's worth paying for me $100 a month. And you know, you can agree or disagree And you know, you can agree or disagree And you know, you can agree or disagree with this. But now it took me 20 minutes with this. But now it took me 20 minutes with this. But now it took me 20 minutes to replace it for good. Why would I pay to replace it for good. Why would I pay to replace it for good. Why would I pay $100? So yeah, just like you, I've been $100? So yeah, just like you, I've been $100? So yeah, just like you, I've been mind-blown with how many things I can mind-blown with how many things I can mind-blown with how many things I can do. Not mention like personal expenses, do. Not mention like personal expenses, do. Not mention like personal expenses, some of these things. It's just opening some of these things. It's just opening some of these things. It's just opening a whole new world. And it's not just me a whole new world. And it's not just me a whole new world. And it's not just me or you. I'm talking to a lot of people, or you. I'm talking to a lot of people, or you. I'm talking to a lot of people, uh folks working at startups, at as uh folks working at startups, at as uh folks working at startups, at as engineers. And everyone is having this engineers. And everyone is having this engineers. And everyone is having this like this winter break was the weirdest like this winter break was the weirdest like this winter break was the weirdest winter break. People are coming back and winter break. People are coming back and winter break. People are coming back and say say say damn. Like so many things work and damn. Like so many things work and damn. Like so many things work and everyone's changing like how they work, everyone's changing like how they work, everyone's changing like how they work, experimenting, and just getting a lot experimenting, and just getting a lot experimenting, and just getting a lot more stuff done. more stuff done. more stuff done. Yeah, I've got I'll give you two quick Yeah, I've got I'll give you two quick Yeah, I've got I'll give you two quick stories. So the back end for stories. So the back end for stories. So the back end for Hanselminutes, which has been this way Hanselminutes, which has been this way Hanselminutes, which has been this way for for for probably 15 years, maybe longer. The The probably 15 years, maybe longer. The The probably 15 years, maybe longer. The The podcast is over 20 years old, is podcast is over 20 years old, is podcast is over 20 years old, is JavaScript files in Azure storage. JavaScript files in Azure storage. JavaScript files in Azure storage. And I once a week I would take 10 or 15 And I once a week I would take 10 or 15 And I once a week I would take 10 or 15 minutes. I'd open it in Visual Studio minutes. I'd open it in Visual Studio minutes. I'd open it in Visual Studio Code. I'd edit the JavaScript files, Code. I'd edit the JavaScript files, Code. I'd edit the JavaScript files, which would express a new show has come which would express a new show has come which would express a new show has come out and then there's a linkage to some out and then there's a linkage to some out and then there's a linkage to some advertising. And every single week I was advertising. And every single week I was advertising. And every single week I was like, "I One of these days I'm going to like, "I One of these days I'm going to like, "I One of these days I'm going to take a weekend. I'm going to write an take a weekend. I'm going to write an take a weekend. I'm going to write an admin."

admin." admin." I wrote an admin. It I used GitHub I wrote an admin. It I used GitHub I wrote an admin. It I used GitHub Copilot CLI. I used Opus 45. It was 42 Copilot CLI. I used Opus 45. It was 42 Copilot CLI. I used Opus 45. It was 42 minutes. It took longer to figure out minutes. It took longer to figure out minutes. It took longer to figure out how to deploy it to the cloud than it how to deploy it to the cloud than it how to deploy it to the cloud than it did to write the thing. And I think the did to write the thing. And I think the did to write the thing. And I think the that's that's idea number thing number that's that's idea number thing number that's that's idea number thing number one. And then one. And then one. And then a couple weeks ago, a couple weeks ago, a couple weeks ago, I use a blood sugar management system I use a blood sugar management system I use a blood sugar management system called Nightscout, which is an called Nightscout, which is an called Nightscout, which is an open-source software. And I have a REST open-source software. And I have a REST open-source software. And I have a REST API, which is my blood sugar. So when API, which is my blood sugar. So when API, which is my blood sugar. So when I'm overseas or I'm traveling, my wife I'm overseas or I'm traveling, my wife I'm overseas or I'm traveling, my wife can see my blood sugar on like screens can see my blood sugar on like screens can see my blood sugar on like screens around the house around the house around the house and things like that. And there's a and things like that. And there's a and things like that. And there's a notification if my blood sugar goes high notification if my blood sugar goes high notification if my blood sugar goes high or goes low. or goes low. or goes low. It's It's very specific. It's very It's It's very specific. It's very It's It's very specific. It's very grounded and it's a number. I don't want grounded and it's a number. I don't want grounded and it's a number. I don't want to hallucinate that. to hallucinate that. to hallucinate that. >> [snorts] >> [snorts] >> [snorts] >> But I now want to have joins with other >> But I now want to have joins with other >> But I now want to have joins with other data. Like how does my blood sugar data. Like how does my blood sugar data. Like how does my blood sugar interact when I walk, when I travel, interact when I walk, when I travel, interact when I walk, when I travel, when I eat certain foods, when I'm in when I eat certain foods, when I'm in when I eat certain foods, when I'm in certain meetings. So now there's certain meetings. So now there's certain meetings. So now there's ambiguity. ambiguity. ambiguity. The agent loop, the agentic loop is an The agent loop, the agentic loop is an The agent loop, the agentic loop is an ambiguity loop. ambiguity loop. ambiguity loop. And that ambiguity loop then now allows And that ambiguity loop then now allows And that ambiguity loop then now allows me to join two things. So I used two me to join two things. So I used two me to join two things. So I used two pieces of data. One, my blood sugar pieces of data. One, my blood sugar pieces of data. One, my blood sugar system.

system. system. And the other one is a thing called Work And the other one is a thing called Work And the other one is a thing called Work IQ, which is effectively like talking to IQ, which is effectively like talking to IQ, which is effectively like talking to the Microsoft Graph. So it's like, you the Microsoft Graph. So it's like, you the Microsoft Graph. So it's like, you know, using Google Calendar API. And I know, using Google Calendar API. And I know, using Google Calendar API. And I just said, "Are any meetings correlating just said, "Are any meetings correlating just said, "Are any meetings correlating with my blood sugar?" with my blood sugar?" with my blood sugar?" Like I would never write that app. That Like I would never write that app. That Like I would never write that app. That would be ridiculous. It would take would be ridiculous. It would take would be ridiculous. It would take ridiculous. ridiculous. ridiculous. >> Why would you? No. Right. But now >> Why would you? No. Right. But now >> Why would you? No. Right. But now suddenly the LEGO pieces, we've got suddenly the LEGO pieces, we've got suddenly the LEGO pieces, we've got OAuth, we've got personal access tokens, OAuth, we've got personal access tokens, OAuth, we've got personal access tokens, we've got nice clean REST APIs, a we've got nice clean REST APIs, a we've got nice clean REST APIs, a pattern to do it. We've got Python and pattern to do it. We've got Python and pattern to do it. We've got Python and .NET and JavaScript all very well .NET and JavaScript all very well .NET and JavaScript all very well understood to go and do these things. understood to go and do these things. understood to go and do these things. And I just said, "Go and tell me if any And I just said, "Go and tell me if any And I just said, "Go and tell me if any meetings are stressing me out." And it meetings are stressing me out." And it meetings are stressing me out." And it turns out that I'm going low blood sugar turns out that I'm going low blood sugar turns out that I'm going low blood sugar on Mondays because I don't eat lunch on on Mondays because I don't eat lunch on on Mondays because I don't eat lunch on Mondays. I never put it together Mondays. I never put it together Mondays. I never put it together until I combined effectively a join until I combined effectively a join until I combined effectively a join across Outlook calendar and my blood across Outlook calendar and my blood across Outlook calendar and my blood sugar. And it it took 20 minutes. And sugar. And it it took 20 minutes. And sugar. And it it took 20 minutes. And then I wrote a whole then I wrote a whole then I wrote a whole a report. And then I said, "Make it a a report. And then I said, "Make it a a report. And then I said, "Make it a scale and put it in GitHub." And now scale and put it in GitHub." And now scale and put it in GitHub." And now other people are using it. That's other people are using it. That's other people are using it. That's insane. insane. insane. Yeah, and Yeah, and Yeah, and I I was always skeptical when I heard I I was always skeptical when I heard I I was always skeptical when I heard the return of personal software cuz I've the return of personal software cuz I've the return of personal software cuz I've been hearing it 10 plus years. The been hearing it 10 plus years. The been hearing it 10 plus years. The personal software personal software personal software here. But I was I was skeptical just here. But I was I was skeptical just here. But I was I was skeptical just personally because I I personally did personally because I I personally did personally because I I personally did not see it. And again, you might have not see it. And again, you might have not see it. And again, you might have seen more than I have. But I'm starting seen more than I have. But I'm starting seen more than I have. But I'm starting to become a believer in the sense that I to become a believer in the sense that I to become a believer in the sense that I I mean, what you told me and also what I mean, what you told me and also what I mean, what you told me and also what I'm doing, it's kind of personal I'm doing, it's kind of personal I'm doing, it's kind of personal software, software that I wanted for software, software that I wanted for software, software that I wanted for myself or for a very small business. And myself or for a very small business. And myself or for a very small business. And for example, for my own business, The for example, for my own business, The for example, for my own business, The Pragmatic Engineer, Pragmatic Engineer, Pragmatic Engineer, it would not make sense it would have it would not make sense it would have it would not make sense it would have never made sense to hire anyone. So, I

never made sense to hire anyone. So, I never made sense to hire anyone. So, I was buying SaaS services even though I'm was buying SaaS services even though I'm was buying SaaS services even though I'm a software engineer. And now with AI, a software engineer. And now with AI, a software engineer. And now with AI, I'm again I I I would have not hired I'm again I I I would have not hired I'm again I I I would have not hired anyone at all. It just would have not anyone at all. It just would have not anyone at all. It just would have not been built. And now I'm building stuff. been built. And now I'm building stuff. been built. And now I'm building stuff. And also often times, as you say, you're And also often times, as you say, you're And also often times, as you say, you're building stuff that just would have not building stuff that just would have not building stuff that just would have not made sense at all to build. made sense at all to build. made sense at all to build. >> a great point. I'm not going to buy a >> a great point. I'm not going to buy a >> a great point. I'm not going to buy a back end for my bespoke podcast any more back end for my bespoke podcast any more back end for my bespoke podcast any more than you're going to buy you know, than you're going to buy you know, than you're going to buy you know, well, you did pay for this this embedded well, you did pay for this this embedded well, you did pay for this this embedded thing. But now you're probably thing. But now you're probably thing. But now you're probably wondering, why is that a business? wondering, why is that a business? wondering, why is that a business? And now the question is, should you spin And now the question is, should you spin And now the question is, should you spin off the thing you wrote as its own off the thing you wrote as its own off the thing you wrote as its own business? This is the other thing I'm business? This is the other thing I'm business? This is the other thing I'm watching people do, spin off 30, 40 watching people do, spin off 30, 40 watching people do, spin off 30, 40 little tiny micro SaaSes little tiny micro SaaSes little tiny micro SaaSes for other people. for other people. for other people. Yeah, that's a good question what will Yeah, that's a good question what will Yeah, that's a good question what will happen with micro SaaS. But when you happen with micro SaaS. But when you happen with micro SaaS. But when you said you're open sourcing thing, one said you're open sourcing thing, one said you're open sourcing thing, one thing that I'm also hearing my my thing that I'm also hearing my my thing that I'm also hearing my my brother startup, they just open source brother startup, they just open source brother startup, they just open source kind of a visual representation of of kind of a visual representation of of kind of a visual representation of of Claude code that they built for Claude code that they built for Claude code that they built for themselves and other people can use it themselves and other people can use it themselves and other people can use it and he's seeing a lot of remixing going and he's seeing a lot of remixing going and he's seeing a lot of remixing going in open source where for example in that in open source where for example in that in open source where for example in that open source project he does not want to open source project he does not want to open source project he does not want to merge other people's pull requests merge other people's pull requests merge other people's pull requests because he wants to keep direction like because he wants to keep direction like because he wants to keep direction like he he wants to keep it consistent. So he he he wants to keep it consistent. So he he he wants to keep it consistent. So he looks at the whatever comes in a pull looks at the whatever comes in a pull looks at the whatever comes in a pull request and he looks at the idea and if request and he looks at the idea and if request and he looks at the idea and if he likes it, he will then use the agent he likes it, he will then use the agent he likes it, he will then use the agent actually build it the way he thinks it actually build it the way he thinks it actually build it the way he thinks it should be done. So strong control. But should be done. So strong control. But should be done. So strong control. But what he's seeing here is a lot of people what he's seeing here is a lot of people what he's seeing here is a lot of people are forking off their open source are forking off their open source are forking off their open source project and remixing it because with an project and remixing it because with an project and remixing it because with an agent again, you can you can tell an agent again, you can you can tell an agent again, you can you can tell an agent like hey generate a pull request agent like hey generate a pull request agent like hey generate a pull request and hope someone merges it or you can and hope someone merges it or you can and hope someone merges it or you can just say like hey make this change in just say like hey make this change in just say like hey make this change in the software in this fork especially

the software in this fork especially the software in this fork especially when it's open source and a lot of when it's open source and a lot of when it's open source and a lot of people are putting it on on GitHub as people are putting it on on GitHub as people are putting it on on GitHub as open source cuz again it's easy. Open open source cuz again it's easy. Open open source cuz again it's easy. Open source product projects are are are source product projects are are are source product projects are are are things for free or maybe it's free things for free or maybe it's free things for free or maybe it's free otherwise, but we might see an explosion otherwise, but we might see an explosion otherwise, but we might see an explosion in open source because of this remixing in open source because of this remixing in open source because of this remixing nature. It's it's very interesting. nature. It's it's very interesting. nature. It's it's very interesting. >> So this is the thing though. We're >> So this is the thing though. We're >> So this is the thing though. We're hearing this term slop and AI slop and hearing this term slop and AI slop and hearing this term slop and AI slop and some people are saying well this is just some people are saying well this is just some people are saying well this is just slop, but if it works well and it's slop, but if it works well and it's slop, but if it works well and it's personal and it's only on your machine personal and it's only on your machine personal and it's only on your machine and it does the thing you want it to do, and it does the thing you want it to do, and it does the thing you want it to do, maybe it's not slop at all. Two things maybe it's not slop at all. Two things maybe it's not slop at all. Two things that I remixed recently, the Mac has that I remixed recently, the Mac has that I remixed recently, the Mac has that ring light that is a feature. I that ring light that is a feature. I that ring light that is a feature. I made a Windows ring light, had a lot of made a Windows ring light, had a lot of made a Windows ring light, had a lot of fun with it. So it's basically an fun with it. So it's basically an fun with it. So it's basically an artificial drawn ring light. And then artificial drawn ring light. And then artificial drawn ring light. And then just literally two days ago on on Hacker just literally two days ago on on Hacker just literally two days ago on on Hacker News I saw the most clever thing called News I saw the most clever thing called News I saw the most clever thing called posture for Mac where if you slouch posture for Mac where if you slouch posture for Mac where if you slouch it detects that you slouched it detects that you slouched it detects that you slouched >> Amazing. >> Amazing. >> Amazing. >> your screen so that it causes you to >> your screen so that it causes you to >> your screen so that it causes you to have to sit up straight in order to you have to sit up straight in order to you have to sit up straight in order to you know make your screen clear again. So I know make your screen clear again. So I know make your screen clear again. So I told Copilot CLI to go and make me a told Copilot CLI to go and make me a told Copilot CLI to go and make me a Windows version. So now I have an Windows version. So now I have an Windows version. So now I have an application that literally dims the application that literally dims the application that literally dims the screen if my posture is bad to force me screen if my posture is bad to force me screen if my posture is bad to force me to like think about it. That's just to like think about it. That's just to like think about it. That's just silly personal software. And now we've silly personal software. And now we've silly personal software. And now we've got Claude bot um I just spun up in WSL, got Claude bot um I just spun up in WSL, got Claude bot um I just spun up in WSL, Windows Subsystem for Linux, and I'm Windows Subsystem for Linux, and I'm Windows Subsystem for Linux, and I'm debating if I should run it in my debating if I should run it in my debating if I should run it in my Synology, Synology, Synology, which would be my my NAS, my network which would be my my NAS, my network which would be my my NAS, my network attached storage. So, like attached storage. So, like attached storage. So, like why shouldn't I have a little server in why shouldn't I have a little server in why shouldn't I have a little server in my own house doing my own thing? Plus, my own house doing my own thing? Plus, my own house doing my own thing? Plus, something like Home Assistant. I'm

something like Home Assistant. I'm something like Home Assistant. I'm curious, are you a Home Assistant curious, are you a Home Assistant curious, are you a Home Assistant person? Not as much. I use it a a little person? Not as much. I use it a a little person? Not as much. I use it a a little bit, but I I've I've just not I I think bit, but I I've I've just not I I think bit, but I I've I've just not I I think I don't have the integrations for it, I don't have the integrations for it, I don't have the integrations for it, but I I could see myself using it, but I but I I could see myself using it, but I but I I could see myself using it, but I I totally agree with you. Like the the I totally agree with you. Like the the I totally agree with you. Like the the idea of like a you know, personal idea of like a you know, personal idea of like a you know, personal assistant. Like I feel we're back into assistant. Like I feel we're back into assistant. Like I feel we're back into the the the the good old days of when PCs were the good old days of when PCs were the good old days of when PCs were starting to become mainstream, where starting to become mainstream, where starting to become mainstream, where like you we just had like you know, home like you we just had like you know, home like you we just had like you know, home homemade software. Like it was just read homemade software. Like it was just read homemade software. Like it was just read on the internet and and you know, you on the internet and and you know, you on the internet and and you know, you controlled your own hardware and and you controlled your own hardware and and you controlled your own hardware and and you had your own software. Like again, for had your own software. Like again, for had your own software. Like again, for personal assistant, why why could I not personal assistant, why why could I not personal assistant, why why could I not have it run on my stuff and and me have it run on my stuff and and me have it run on my stuff and and me choosing my subscriptions and me choosing my subscriptions and me choosing my subscriptions and me choosing what it has access to? Like I I choosing what it has access to? Like I I choosing what it has access to? Like I I feel like the hacker mentality is back, feel like the hacker mentality is back, feel like the hacker mentality is back, like Yeah, there was a time for hackers like Yeah, there was a time for hackers like Yeah, there was a time for hackers in the '90s and in the '90s and in the '90s and pop fiction everywhere, but it was pop fiction everywhere, but it was pop fiction everywhere, but it was happening. I remember. And then it kind happening. I remember. And then it kind happening. I remember. And then it kind of went away the last like few years, of went away the last like few years, of went away the last like few years, decades. decades. decades. Yeah, I feel like there's a other than Yeah, I feel like there's a other than Yeah, I feel like there's a other than the part where the LLM runs in the the part where the LLM runs in the the part where the LLM runs in the cloud, a lot of this stuff can be done cloud, a lot of this stuff can be done cloud, a lot of this stuff can be done internally. internally. internally. And I always try to think about would my And I always try to think about would my And I always try to think about would my software work in airplane mode?

software work in airplane mode? software work in airplane mode? Right? I just feel like that's Right? I just feel like that's Right? I just feel like that's important. And my house needs to work in important. And my house needs to work in important. And my house needs to work in airplane mode. airplane mode. airplane mode. >> And also don't forget like I personally >> And also don't forget like I personally >> And also don't forget like I personally think it's just a matter of time, matter think it's just a matter of time, matter think it's just a matter of time, matter of years where LLM will run on your of years where LLM will run on your of years where LLM will run on your machine. I mean, there's a lot of a lot machine. I mean, there's a lot of a lot machine. I mean, there's a lot of a lot of work being done. I know the Windows of work being done. I know the Windows of work being done. I know the Windows 11 team is is doing a bunch of stuff 11 team is is doing a bunch of stuff 11 team is is doing a bunch of stuff around around around infrastructure pieces to make that one infrastructure pieces to make that one infrastructure pieces to make that one day happen. LLMs are getting day happen. LLMs are getting day happen. LLMs are getting smaller and and actually some of them smaller and and actually some of them smaller and and actually some of them run on your laptop. They're just not run on your laptop. They're just not run on your laptop. They're just not nearly as good as state of the art. But nearly as good as state of the art. But nearly as good as state of the art. But again, again, again, I I I'm hoping this will be the case cuz I I I'm hoping this will be the case cuz I I I'm hoping this will be the case cuz uh I mean 100% agree. I've got you know, uh I mean 100% agree. I've got you know, uh I mean 100% agree. I've got you know, LM Studio is a fantastic Everyone talks LM Studio is a fantastic Everyone talks LM Studio is a fantastic Everyone talks about Ollama, but they're sleeping on LM about Ollama, but they're sleeping on LM about Ollama, but they're sleeping on LM Studio, lmstudio.ai. Studio, lmstudio.ai. Studio, lmstudio.ai. Um running that, Um running that, Um running that, it then presents an OpenAI endpoint it then presents an OpenAI endpoint it then presents an OpenAI endpoint that's available inside your house. that's available inside your house. that's available inside your house. Totally works locally. If you do that Totally works locally. If you do that Totally works locally. If you do that plus like a GPT 20 billion OSS, plus like a GPT 20 billion OSS, plus like a GPT 20 billion OSS, you've got a perfectly good model that you've got a perfectly good model that you've got a perfectly good model that will run inside your house. It makes me will run inside your house. It makes me will run inside your house. It makes me wonder, will it run on your laptop? Will wonder, will it run on your laptop? Will wonder, will it run on your laptop? Will it run on your desktop? Or again, I it run on your desktop? Or again, I it run on your desktop? Or again, I bring up this idea of the NAS. If you bring up this idea of the NAS. If you bring up this idea of the NAS. If you remember things like Windows Home remember things like Windows Home remember things like Windows Home Server, the Synologies, TrueNAS, Server, the Synologies, TrueNAS, Server, the Synologies, TrueNAS, FreeNAS, why wouldn't I have a tiny FreeNAS, why wouldn't I have a tiny FreeNAS, why wouldn't I have a tiny machine that would sit in a closet that machine that would sit in a closet that machine that would sit in a closet that would provide a totally private LLM for would provide a totally private LLM for would provide a totally private LLM for the family?

the family? the family? 100% agree. I I have NASes running 100% agree. I I have NASes running 100% agree. I I have NASes running backing them by Dropbox already and it's backing them by Dropbox already and it's backing them by Dropbox already and it's it's already on. I wouldn't mind like, it's already on. I wouldn't mind like, it's already on. I wouldn't mind like, you know, doing a little inference when you know, doing a little inference when you know, doing a little inference when we need it. Yeah, yeah. I don't know if we need it. Yeah, yeah. I don't know if we need it. Yeah, yeah. I don't know if you can see over here. People who are you can see over here. People who are you can see over here. People who are listening won't be able to see it, but listening won't be able to see it, but listening won't be able to see it, but this is a Reachy mini robot that is a this is a Reachy mini robot that is a this is a Reachy mini robot that is a from Hugging Face. And this is a little from Hugging Face. And this is a little from Hugging Face. And this is a little robot that you buy from Hugging Face and robot that you buy from Hugging Face and robot that you buy from Hugging Face and then you can It's got a Raspberry Pi in then you can It's got a Raspberry Pi in then you can It's got a Raspberry Pi in it and then you can have it do stuff. Um it and then you can have it do stuff. Um it and then you can have it do stuff. Um it took me about 15 minutes to create a it took me about 15 minutes to create a it took me about 15 minutes to create a skill. So when when uh skill. So when when uh skill. So when when uh Copilot CLI is done with something, Copilot CLI is done with something, Copilot CLI is done with something, he'll celebrate. he'll celebrate. he'll celebrate. Like it's it's so much more interesting Like it's it's so much more interesting Like it's it's so much more interesting and personal to hack and build your own and personal to hack and build your own and personal to hack and build your own robot than to like yap at Alexa who's robot than to like yap at Alexa who's robot than to like yap at Alexa who's just going to remind you that like to just going to remind you that like to just going to remind you that like to buy more crap. Like I built that guy and buy more crap. Like I built that guy and buy more crap. Like I built that guy and he can talk to me and he'll order food he can talk to me and he'll order food he can talk to me and he'll order food and he'll put things on my grocery list and he'll put things on my grocery list and he'll put things on my grocery list and he'll dance when my when my my build and he'll dance when my when my my build and he'll dance when my when my my build is done. is done. is done. I That's you know, make the web weird I That's you know, make the web weird I That's you know, make the web weird again is kind of where my where I'm at. again is kind of where my where I'm at. again is kind of where my where I'm at. Yep.

Yep. Yep. Yeah. So do you Have you looked at Yeah. So do you Have you looked at Yeah. So do you Have you looked at Claude bot? Have you been spending time Claude bot? Have you been spending time Claude bot? Have you been spending time with that? Because there's a lot of with that? Because there's a lot of with that? Because there's a lot of controversy about the security aspect of controversy about the security aspect of controversy about the security aspect of it and I think it and I think it and I think it's people should just relax a little it's people should just relax a little it's people should just relax a little bit because everything starts insecure bit because everything starts insecure bit because everything starts insecure to start with. to start with. to start with. So interesting you would say because I I So interesting you would say because I I So interesting you would say because I I I talked with Peter Steinberger. I met I talked with Peter Steinberger. I met I talked with Peter Steinberger. I met him in London 2 weeks ago and I have a him in London 2 weeks ago and I have a him in London 2 weeks ago and I have a podcast episode coming out. Oh, great. podcast episode coming out. Oh, great. podcast episode coming out. Oh, great. It it it will have been out by by the It it it will have been out by by the It it it will have been out by by the time time time we we talked. So, we we talked. So, we we talked. So, I knew a little bit of Claude about I knew a little bit of Claude about I knew a little bit of Claude about before, but he showed me on his phone. before, but he showed me on his phone. before, but he showed me on his phone. And he showed me what he had it had it And he showed me what he had it had it And he showed me what he had it had it hooked up and it was wild. Like again, hooked up and it was wild. Like again, hooked up and it was wild. Like again, he gave it full access to all these he gave it full access to all these he gave it full access to all these things. You know, he he is living on the things. You know, he he is living on the things. You know, he he is living on the edge and he's very clear, by the way, edge and he's very clear, by the way, edge and he's very clear, by the way, that you should probably not do this. He that you should probably not do this. He that you should probably not do this. He is YOLO-ing it. I mean, he's not giving is YOLO-ing it. I mean, he's not giving is YOLO-ing it. I mean, he's not giving access to the bank accounts and some access to the bank accounts and some access to the bank accounts and some other things, but he's giving way wider other things, but he's giving way wider other things, but he's giving way wider access than I would be comfortable with. access than I would be comfortable with. access than I would be comfortable with. But then he showed me how he uses it But then he showed me how he uses it But then he showed me how he uses it day-to-day. He showed it He kind of day-to-day. He showed it He kind of day-to-day. He showed it He kind of wasn't demoing it. He was just like wasn't demoing it. He was just like wasn't demoing it. He was just like using it. And after 5 minutes, my using it. And after 5 minutes, my using it. And after 5 minutes, my thinking was like, "Oh my gosh, this is thinking was like, "Oh my gosh, this is thinking was like, "Oh my gosh, this is what Siri would be like in 10 years, but what Siri would be like in 10 years, but what Siri would be like in 10 years, but he has it working here." I mean, it's he has it working here." I mean, it's he has it working here." I mean, it's got a lot of shortcuts, clearly like a got a lot of shortcuts, clearly like a got a lot of shortcuts, clearly like a lot of things that that you you need lot of things that that you you need lot of things that that you you need What's an example of something that blew What's an example of something that blew What's an example of something that blew your mind? Cuz I use Siri all and I I your mind? Cuz I use Siri all and I I your mind? Cuz I use Siri all and I I want to preface this by saying, "I'll want to preface this by saying, "I'll want to preface this by saying, "I'll use Siri very often for things like uh use Siri very often for things like uh use Siri very often for things like uh geo geo-fencing." So, I'll say, "Remind geo geo-fencing." So, I'll say, "Remind geo geo-fencing." So, I'll say, "Remind me when I get home to do this." And I me when I get home to do this." And I me when I get home to do this." And I find that magical. I could say, "Hey, find that magical. I could say, "Hey, find that magical. I could say, "Hey, you know, make me an appointment with you know, make me an appointment with you know, make me an appointment with Gergely tomorrow at this location." That Gergely tomorrow at this location." That Gergely tomorrow at this location." That those things are nice, but it's the

those things are nice, but it's the those things are nice, but it's the giving it arms and legs part. giving it arms and legs part. giving it arms and legs part. That's interesting. So, like That's interesting. So, like That's interesting. So, like he showed me how he uses this. He just he showed me how he uses this. He just he showed me how he uses this. He just tells it to book me an appointment, for tells it to book me an appointment, for tells it to book me an appointment, for example, his barber. example, his barber. example, his barber. And And And it goes off and and the the wild thing it goes off and and the the wild thing it goes off and and the the wild thing about that was that it tried to go about that was that it tried to go about that was that it tried to go online, but it struggled or something online, but it struggled or something online, but it struggled or something crashed for some reason or it had an crashed for some reason or it had an crashed for some reason or it had an issue with the the browser. And it issue with the the browser. And it issue with the the browser. And it created itself a voice skill using 11 created itself a voice skill using 11 created itself a voice skill using 11 Labs, which it had access to because I Labs, which it had access to because I Labs, which it had access to because I like he he has Oh, no. Like like he has like he he has Oh, no. Like like he has like he he has Oh, no. Like like he has a subscription and actually made the a subscription and actually made the a subscription and actually made the call without asking him. So, and it then call without asking him. So, and it then call without asking him. So, and it then added this skill to the functionality. added this skill to the functionality. added this skill to the functionality. It's all in the logs though, so you but It's all in the logs though, so you but It's all in the logs though, so you but the fact that it's an agent that can the fact that it's an agent that can the fact that it's an agent that can that can improve itself already this is that can improve itself already this is that can improve itself already this is wild and it got the stuff done that he wild and it got the stuff done that he wild and it got the stuff done that he wanted which was a bit of a scary thing wanted which was a bit of a scary thing wanted which was a bit of a scary thing for me like okay I just want dolphin for me like okay I just want dolphin for me like okay I just want dolphin like actually made this call with with like actually made this call with with like actually made this call with with 11 that was wild. But which is funny cuz 11 that was wild. But which is funny cuz 11 that was wild. But which is funny cuz that's what Google did and everyone that's what Google did and everyone that's what Google did and everyone thought that was creepy. Yeah and you thought that was creepy. Yeah and you thought that was creepy. Yeah and you can decide where you're but again this can decide where you're but again this can decide where you're but again this this is the fact that it can this is the fact that it can this is the fact that it can and and it can do a lot of things where and and it can do a lot of things where and and it can do a lot of things where it can figure stuff out and it can it can figure stuff out and it can it can figure stuff out and it can browse and it can create a new skill for browse and it can create a new skill for browse and it can create a new skill for itself which is very very surprising. I itself which is very very surprising. I itself which is very very surprising. I think this has so many like fascinating think this has so many like fascinating think this has so many like fascinating and slightly terrifying implications but and slightly terrifying implications but and slightly terrifying implications but I'm more on the fascinating side. Mhm.

I'm more on the fascinating side. Mhm. I'm more on the fascinating side. Mhm. And then the other side which was crazy And then the other side which was crazy And then the other side which was crazy he he took a photo of two of us and said he he took a photo of two of us and said he he took a photo of two of us and said like hey like who who who am I here like hey like who who who am I here like hey like who who who am I here with? with? with? And it looked at the the photo it it And it looked at the the photo it it And it looked at the the photo it it analyzed it it it ran a search and then analyzed it it it ran a search and then analyzed it it it ran a search and then it cross-referenced his calendar and it cross-referenced his calendar and it cross-referenced his calendar and said like oh yeah this is going to be said like oh yeah this is going to be said like oh yeah this is going to be like that was easy cuz I I just I just like that was easy cuz I I just I just like that was easy cuz I I just I just have you here. And but what really the have you here. And but what really the have you here. And but what really the biggest thing that fascinated me is how biggest thing that fascinated me is how biggest thing that fascinated me is how how hooked Peter was with his how hooked Peter was with his how hooked Peter was with his agent and how much it was tuned on his agent and how much it was tuned on his agent and how much it was tuned on his personality it knew what he was doing personality it knew what he was doing personality it knew what he was doing and it [clears throat] it was I'll be and it [clears throat] it was I'll be and it [clears throat] it was I'll be honest it felt a bit weird on how honest it felt a bit weird on how honest it felt a bit weird on how clearly addicted to it it it was. clearly addicted to it it it was. clearly addicted to it it it was. And I'm kind of thinking there's going And I'm kind of thinking there's going And I'm kind of thinking there's going to be a danger and and I mean you look to be a danger and and I mean you look to be a danger and and I mean you look at a danger opportunity like you know I at a danger opportunity like you know I at a danger opportunity like you know I know people are addicted to chat GPT but know people are addicted to chat GPT but know people are addicted to chat GPT but this is going to be way more addictive this is going to be way more addictive this is going to be way more addictive and it might it might not be Claude bot and it might it might not be Claude bot and it might it might not be Claude bot but it it might be the next version but it it might be the next version but it it might be the next version that's out. that's out. that's out. >> No but there's the concept of immediacy >> No but there's the concept of immediacy >> No but there's the concept of immediacy like we we we are a certain we are men like we we we are a certain we are men like we we we are a certain we are men of a certain age but the idea that like of a certain age but the idea that like of a certain age but the idea that like you used to wait six to eight weeks for you used to wait six to eight weeks for you used to wait six to eight weeks for the thing to come in the mail the thing to come in the mail the thing to come in the mail and now if it's not there by the and now if it's not there by the and now if it's not there by the afternoon you're upset. Or you used to afternoon you're upset. Or you used to afternoon you're upset. Or you used to wait two to four weeks to get your wait two to four weeks to get your wait two to four weeks to get your passport renewed if you can't renew it passport renewed if you can't renew it passport renewed if you can't renew it overnight you're mad.

overnight you're mad. overnight you're mad. The idea that you can have food The idea that you can have food The idea that you can have food delivered to you by a stranger or a delivered to you by a stranger or a delivered to you by a stranger or a stranger can bring their car to you and stranger can bring their car to you and stranger can bring their car to you and then take you anywhere then take you anywhere then take you anywhere is is amazing and if that breaks down we is is amazing and if that breaks down we is is amazing and if that breaks down we will have a group of helpless people who will have a group of helpless people who will have a group of helpless people who are unable to do anything for themselves are unable to do anything for themselves are unable to do anything for themselves much less do their own laundry. Yeah. much less do their own laundry. Yeah. much less do their own laundry. Yeah. But but to your question on the security But but to your question on the security But but to your question on the security like I kind of view it like I'm also a like I kind of view it like I'm also a like I kind of view it like I'm also a bit more chill about it. Like I view it bit more chill about it. Like I view it bit more chill about it. Like I view it I remember the times where Windows was I remember the times where Windows was I remember the times where Windows was just starting to become big in the 90s just starting to become big in the 90s just starting to become big in the 90s where I was getting my first machines where I was getting my first machines where I was getting my first machines and you know the way you got software is and you know the way you got software is and you know the way you got software is you you kind of pass it on a floppy you you kind of pass it on a floppy you you kind of pass it on a floppy disks and later there were websites that disks and later there were websites that disks and later there were websites that you could download it and of course you could download it and of course you could download it and of course later there were ways to get the you later there were ways to get the you later there were ways to get the you know like the so-called cracks for the know like the so-called cracks for the know like the so-called cracks for the for the a lot of the games had for the a lot of the games had for the a lot of the games had protections with like you had numbers to protections with like you had numbers to protections with like you had numbers to fill in from manual and all that and fill in from manual and all that and fill in from manual and all that and there were cracks that would that would there were cracks that would that would there were cracks that would that would crack this or make a modification and crack this or make a modification and crack this or make a modification and people were downloading that and a lot people were downloading that and a lot people were downloading that and a lot of it was viruses and a lot of people of it was viruses and a lot of people of it was viruses and a lot of people got nasty viruses and their computers got nasty viruses and their computers got nasty viruses and their computers did all sorts of stuff and over time did all sorts of stuff and over time did all sorts of stuff and over time people learned well A this is bad B like people learned well A this is bad B like people learned well A this is bad B like okay we will have like okay we will have like okay we will have like protection like like antivirus or turn protection like like antivirus or turn protection like like antivirus or turn to a professional in your family on what to a professional in your family on what to a professional in your family on what to do and I think we're going to we're to do and I think we're going to we're to do and I think we're going to we're going to have exactly the same age where going to have exactly the same age where going to have exactly the same age where these AI agents can do a lot of stuff if these AI agents can do a lot of stuff if these AI agents can do a lot of stuff if you give access to sensitive stuff they you give access to sensitive stuff they you give access to sensitive stuff they will be both more powerful but also they will be both more powerful but also they will be both more powerful but also they can be a lot more vulnerable and they can be a lot more vulnerable and they can be a lot more vulnerable and they can do like crazy stuff. So I think can do like crazy stuff. So I think can do like crazy stuff. So I think we'll have a whole learning except it'll we'll have a whole learning except it'll we'll have a whole learning except it'll happen a lot faster cuz now the whole happen a lot faster cuz now the whole happen a lot faster cuz now the whole world has access and it'll be a lot a world has access and it'll be a lot a world has access and it'll be a lot a lot bigger storm. Did you have lot bigger storm. Did you have lot bigger storm. Did you have we are a little bit different in age.

we are a little bit different in age. we are a little bit different in age. Did you come up putting like your your Did you come up putting like your your Did you come up putting like your your your homework on a floppy disk like a your homework on a floppy disk like a your homework on a floppy disk like a thesis thesis thesis or were you a little beyond that? I I I or were you a little beyond that? I I I or were you a little beyond that? I I I was a little beyond that. It was already was a little beyond that. It was already was a little beyond that. It was already email for me. So there was a saying back email for me. So there was a saying back email for me. So there was a saying back when we used to carry our homework when we used to carry our homework when we used to carry our homework around on a 3 and 1/2 inch floppy that around on a 3 and 1/2 inch floppy that around on a 3 and 1/2 inch floppy that like everyone has to lose their thesis like everyone has to lose their thesis like everyone has to lose their thesis once. once. once. It's like a rite of passage. Like you're It's like a rite of passage. Like you're It's like a rite of passage. Like you're you're walking around with your entire you're walking around with your entire you're walking around with your entire PhD thesis on a 3 and 1/2 floppy and it PhD thesis on a 3 and 1/2 floppy and it PhD thesis on a 3 and 1/2 floppy and it you leave it out in the sun or whatever you leave it out in the sun or whatever you leave it out in the sun or whatever and then you call a friend with Norton and then you call a friend with Norton and then you call a friend with Norton Disk Doctor. So like that happens one Disk Doctor. So like that happens one Disk Doctor. So like that happens one time. time. time. Right? You you get your your Twitter Right? You you get your your Twitter Right? You you get your your Twitter hacked or you lose your Dropbox key or hacked or you lose your Dropbox key or hacked or you lose your Dropbox key or you lose your Bitcoin in in a dump you lose your Bitcoin in in a dump you lose your Bitcoin in in a dump somewhere. somewhere. somewhere. Somebody's going to get absolutely Somebody's going to get absolutely Somebody's going to get absolutely destroyed destroyed destroyed at some point. But in doing that, we at some point. But in doing that, we at some point. But in doing that, we will all learn. So, when I say I'm less will all learn. So, when I say I'm less will all learn. So, when I say I'm less chill about it, the idea that you have chill about it, the idea that you have chill about it, the idea that you have to ship it sloppy and wide open first in to ship it sloppy and wide open first in to ship it sloppy and wide open first in order to get order to get order to get what the what what is the limit here? what the what what is the limit here? what the what what is the limit here? And he's obviously on the on the limit. And he's obviously on the on the limit. And he's obviously on the on the limit. I had a delightful moment with a Claude I had a delightful moment with a Claude I had a delightful moment with a Claude Bot recently. I I stalled it in So, I'm Bot recently. I I stalled it in So, I'm Bot recently. I I stalled it in So, I'm on Windows, I installed it in WSL, which on Windows, I installed it in WSL, which on Windows, I installed it in WSL, which is the subsystem within Windows cuz I is the subsystem within Windows cuz I is the subsystem within Windows cuz I want it sandboxed.

want it sandboxed. want it sandboxed. It's not a legitimate sandbox in the It's not a legitimate sandbox in the It's not a legitimate sandbox in the sense of there's no auditing, but it's sense of there's no auditing, but it's sense of there's no auditing, but it's extremely transparent that it stores extremely transparent that it stores extremely transparent that it stores everything in memories. everything in memories. everything in memories. And I I talk a lot about this, and I'm And I I talk a lot about this, and I'm And I I talk a lot about this, and I'm curious what you think. curious what you think. curious what you think. I call it AI's uncanny valley, right? I call it AI's uncanny valley, right? I call it AI's uncanny valley, right? The uncanny valley in like 3D animation The uncanny valley in like 3D animation The uncanny valley in like 3D animation is like, "Ooh, what's wrong with that is like, "Ooh, what's wrong with that is like, "Ooh, what's wrong with that what's wrong with their face?" Like the what's wrong with their face?" Like the what's wrong with their face?" Like the Rock in the Scorpion King. It's like Rock in the Scorpion King. It's like Rock in the Scorpion King. It's like it's clearly bad CG. it's clearly bad CG. it's clearly bad CG. If an AI If an AI If an AI breaks into the uncanny valley and calls breaks into the uncanny valley and calls breaks into the uncanny valley and calls your barber on your behalf, that would your barber on your behalf, that would your barber on your behalf, that would break deeply into the uncanny valley for break deeply into the uncanny valley for break deeply into the uncanny valley for me. But I gave it access to my But that me. But I gave it access to my But that me. But I gave it access to my But that was a task to to book an appointment. was a task to to book an appointment. was a task to to book an appointment. >> it did it by any means necessary. And I >> it did it by any means necessary. And I >> it did it by any means necessary. And I would need to say, "Don't don't down you would need to say, "Don't don't down you would need to say, "Don't don't down you know don't that's too far." Like it know don't that's too far." Like it know don't that's too far." Like it would have to have a sense of taste. would have to have a sense of taste. would have to have a sense of taste. Yep. But I do like the idea of Yep. But I do like the idea of Yep. But I do like the idea of proactivity cuz a good a good assistant proactivity cuz a good a good assistant proactivity cuz a good a good assistant Oh, I took the I took it upon myself to Oh, I took the I took it upon myself to Oh, I took the I took it upon myself to put you in the aisle seat cuz I know you put you in the aisle seat cuz I know you put you in the aisle seat cuz I know you love the aisle. That's cool. love the aisle. That's cool. love the aisle. That's cool. You know what I mean? Oh, I put you in You know what I mean? Oh, I put you in You know what I mean? Oh, I put you in first class because I love you and I first class because I love you and I first class because I love you and I charged it and I opened a credit card charged it and I opened a credit card charged it and I opened a credit card for you. I didn't think you'd mind.

for you. I didn't think you'd mind. for you. I didn't think you'd mind. That's not okay, Yep. That's not okay, Yep. That's not okay, Yep. But I told it about my blood sugar, But I told it about my blood sugar, But I told it about my blood sugar, right? And I said, "Remind me if my right? And I said, "Remind me if my right? And I said, "Remind me if my blood sugar goes too high." blood sugar goes too high." blood sugar goes too high." Cuz it has cron jobs. And I'm looking at Cuz it has cron jobs. And I'm looking at Cuz it has cron jobs. And I'm looking at it right here. It said, "I also added a it right here. It said, "I also added a it right here. It said, "I also added a low because you're diabetic and lows are low because you're diabetic and lows are low because you're diabetic and lows are more dangerous. I'd rather be more more dangerous. I'd rather be more more dangerous. I'd rather be more annoying than let a low blood sugar annoying than let a low blood sugar annoying than let a low blood sugar slide. I hope you don't mind." slide. I hope you don't mind." slide. I hope you don't mind." Yeah. Yeah. Yeah. That's that's That's that's That's that's very like very like very like I don't know. I don't know. I don't know. It's it's enthusiasm. It's it's it's It's it's enthusiasm. It's it's it's It's it's enthusiasm. It's it's it's easily solved. It's all in a markdown easily solved. It's all in a markdown easily solved. It's all in a markdown file. I think that the there's the file. I think that the there's the file. I think that the there's the novelty of it, but there's also the idea novelty of it, but there's also the idea novelty of it, but there's also the idea that I know why it's happening. that I know why it's happening. that I know why it's happening. Like if you compare it to Siri, Like if you compare it to Siri, Like if you compare it to Siri, I don't know why it thinks these things. I don't know why it thinks these things. I don't know why it thinks these things. I don't know what weird stuff it knows I don't know what weird stuff it knows I don't know what weird stuff it knows about me. It's in or Alexa, it's in the about me. It's in or Alexa, it's in the about me. It's in or Alexa, it's in the cloud somewhere. cloud somewhere. cloud somewhere. But with this, it's in a file called But with this, it's in a file called But with this, it's in a file called it's literally called soul.md. it's literally called soul.md. it's literally called soul.md. Yeah. Yeah. Yeah. And I think that Windows and I think And I think that Windows and I think And I think that Windows and I think that you know, everyone Mac would all that you know, everyone Mac would all that you know, everyone Mac would all the big players can learn about it. Just the big players can learn about it. Just the big players can learn about it. Just put it in a text file in a folder put it in a text file in a folder put it in a text file in a folder and I will trust it more. But if you and I will trust it more. But if you and I will trust it more. But if you hold it in the cloud, hold it in the cloud, hold it in the cloud, I don't trust I don't trust you if I I don't trust I don't trust you if I I don't trust I don't trust you if I can't see the file. I'm curious what you can't see the file. I'm curious what you can't see the file. I'm curious what you think about that.

think about that. think about that. I I I like it. I mean, I I I like it. I mean, I I I like it. I mean, I think it's it's it's worth looking at I think it's it's it's worth looking at I think it's it's it's worth looking at why Claude has become so popular so why Claude has become so popular so why Claude has become so popular so quickly quickly quickly to the point that it it is to the point that it it is to the point that it it is and how it's pulling in so many and how it's pulling in so many and how it's pulling in so many different people. Not just software different people. Not just software different people. Not just software engineers, but non-software engineers as engineers, but non-software engineers as engineers, but non-software engineers as well. And all all built what by one well. And all all built what by one well. And all all built what by one person who is scratching their itch to person who is scratching their itch to person who is scratching their itch to have this like, you know, like this have this like, you know, like this have this like, you know, like this imaginary future assistant that can do imaginary future assistant that can do imaginary future assistant that can do all of these things. So like I I I'm all of these things. So like I I I'm all of these things. So like I I I'm just mostly fascinated by like First of just mostly fascinated by like First of just mostly fascinated by like First of all, like all, like all, like it gives me a little bit of hope into it gives me a little bit of hope into it gives me a little bit of hope into software engineering as a whole. So software engineering as a whole. So software engineering as a whole. So Peter is had Peter is had Peter is had was an amazing software engineer before was an amazing software engineer before was an amazing software engineer before he he built PSPDFKit. And then he just he he built PSPDFKit. And then he just he he built PSPDFKit. And then he just took a very long break and he came back took a very long break and he came back took a very long break and he came back and he started to obsessively, you know, and he started to obsessively, you know, and he started to obsessively, you know, create stuff. He built a lot of create stuff. He built a lot of create stuff. He built a lot of different projects. And different projects. And different projects. And there was was one where you could there was was one where you could there was was one where you could remotely run your agent from your phone remotely run your agent from your phone remotely run your agent from your phone on your server, this kind of stuff. on your server, this kind of stuff. on your server, this kind of stuff. And if I look at Claude Bot, he And if I look at Claude Bot, he And if I look at Claude Bot, he you know, we talk a lot there's a lot of you know, we talk a lot there's a lot of you know, we talk a lot there's a lot of talk about vibe coding, what happens talk about vibe coding, what happens talk about vibe coding, what happens with software engineering now that the with software engineering now that the with software engineering now that the AI can write all the code, which which AI can write all the code, which which AI can write all the code, which which he is letting AI write all the code. He he is letting AI write all the code. He he is letting AI write all the code. He uses Codex, I believe, because he likes uses Codex, I believe, because he likes uses Codex, I believe, because he likes the long long running tasks.

the long long running tasks. the long long running tasks. And he And he And he but when I talk with him, the crazy but when I talk with him, the crazy but when I talk with him, the crazy thing about is he keeps the architecture thing about is he keeps the architecture thing about is he keeps the architecture so much in his head. He is so so much in his head. He is so so much in his head. He is so opinionated about how to build it. He opinionated about how to build it. He opinionated about how to build it. He refactors all the time. refactors all the time. refactors all the time. And when I talk with him, I felt like And when I talk with him, I felt like And when I talk with him, I felt like this is a software engineer and this is a software engineer and this is a software engineer and architect who is this is this is his architect who is this is this is his architect who is this is this is his baby. Like he's still he's the one baby. Like he's still he's the one baby. Like he's still he's the one merging all of the pull requests merging all of the pull requests merging all of the pull requests single-handedly. Really? single-handedly. Really? single-handedly. Really? >> That's also what Yeah. Well, I think he >> That's also what Yeah. Well, I think he >> That's also what Yeah. Well, I think he might have like one or two people might have like one or two people might have like one or two people helping, but for the most part is just helping, but for the most part is just helping, but for the most part is just him with him with him with >> See, if you juxtapose that with the >> See, if you juxtapose that with the >> See, if you juxtapose that with the enthusiasm around Ralph Loops and enthusiasm around Ralph Loops and enthusiasm around Ralph Loops and autonomy and agents that do the merging autonomy and agents that do the merging autonomy and agents that do the merging itself, it's interesting that here's a itself, it's interesting that here's a itself, it's interesting that here's a person who's obsessive about what he person who's obsessive about what he person who's obsessive about what he wants ClaudeBot to do. wants ClaudeBot to do. wants ClaudeBot to do. He's obsessive about its tasks. He's He's obsessive about its tasks. He's He's obsessive about its tasks. He's vibe coding all of it, but then he's vibe coding all of it, but then he's vibe coding all of it, but then he's also curating each pull request also curating each pull request also curating each pull request manually. manually. manually. And not going in and just saying And not going in and just saying And not going in and just saying >> says he doesn't believe in the Ralph >> says he doesn't believe in the Ralph >> says he doesn't believe in the Ralph idea. He's he thinks that's just like idea. He's he thinks that's just like idea. He's he thinks that's just like you you've not given the prompts. He you you've not given the prompts. He you you've not given the prompts. He spends a lot of time a lot So, he runs spends a lot of time a lot So, he runs spends a lot of time a lot So, he runs about five or six or seven parallel about five or six or seven parallel about five or six or seven parallel agents. He spends a lot of time with agents. He spends a lot of time with agents. He spends a lot of time with each of them planning. He asks them each of them planning. He asks them each of them planning. He asks them about this, what about that? And when about this, what about that? And when about this, what about that? And when he's happy with the plan, it's a bit he's happy with the plan, it's a bit he's happy with the plan, it's a bit like a tech lead. He says, "Okay, go and like a tech lead. He says, "Okay, go and like a tech lead. He says, "Okay, go and do it." And then he likes Codex because do it." And then he likes Codex because do it." And then he likes Codex because Codex will go and it will work away up Codex will go and it will work away up Codex will go and it will work away up to like an hour or even longer to like an hour or even longer to like an hour or even longer sometimes.

sometimes. sometimes. And so, like and if if I look at the And so, like and if if I look at the And so, like and if if I look at the success, I I think I think this is where success, I I think I think this is where success, I I think I think this is where like let's look at the output. Claude is like let's look at the output. Claude is like let's look at the output. Claude is clearly popular. It's hitting a nerve clearly popular. It's hitting a nerve clearly popular. It's hitting a nerve and it's evolving with people and it and it's evolving with people and it and it's evolving with people and it does have a personality and a taste and does have a personality and a taste and does have a personality and a taste and it's consistent. You know, I I I love to it's consistent. You know, I I I love to it's consistent. You know, I I I love to see see see >> talking Claude Opus or ClaudeBot? >> talking Claude Opus or ClaudeBot? >> talking Claude Opus or ClaudeBot? >> Uh so, ClaudeBot. Yeah, and now now it's >> Uh so, ClaudeBot. Yeah, and now now it's >> Uh so, ClaudeBot. Yeah, and now now it's called MoldBot. He just renamed it called MoldBot. He just renamed it called MoldBot. He just renamed it because like it was getting confusing in because like it was getting confusing in because like it was getting confusing in Anthropic. Anthropic. Anthropic. >> Oh, wow. He renamed it. Yeah, that was >> Oh, wow. He renamed it. Yeah, that was >> Oh, wow. He renamed it. Yeah, that was today. today. today. It's called Mold It's called Mold It's called Mold MoldBot. So, it's still the crab the MoldBot. So, it's still the crab the MoldBot. So, it's still the crab the crab bot the Mold MoldBot. So, like he crab bot the Mold MoldBot. So, like he crab bot the Mold MoldBot. So, like he built a product this way where he is in built a product this way where he is in built a product this way where he is in one person is in charge. One person is one person is in charge. One person is one person is in charge. One person is kind of the architect. And kind of the architect. And kind of the architect. And I I would just love to see a successful I I would just love to see a successful I I would just love to see a successful Ralph project which is also successful. Ralph project which is also successful. Ralph project which is also successful. People like it where the AI went off and People like it where the AI went off and People like it where the AI went off and did it. I I don't have an example yet did it. I I don't have an example yet did it. I I don't have an example yet which does not mean it does not exist, which does not mean it does not exist, which does not mean it does not exist, but but but I I love to see if you know, like, we're I I love to see if you know, like, we're I I love to see if you know, like, we're in an age where I'm sure eventually in an age where I'm sure eventually in an age where I'm sure eventually something will pop up. But to me Ralph something will pop up. But to me Ralph something will pop up. But to me Ralph seems a little bit like I'm kind of seems a little bit like I'm kind of seems a little bit like I'm kind of lazy. Let me see if the AI can do and lazy. Let me see if the AI can do and lazy. Let me see if the AI can do and make all the decisions. And as a make all the decisions. And as a make all the decisions. And as a professional, I I would like to think professional, I I would like to think professional, I I would like to think that it makes a difference that it makes a difference that it makes a difference who is sitting behind the drive the the who is sitting behind the drive the the who is sitting behind the drive the the the wheel the wheel the wheel and you know, like and like and you know, like and like and you know, like and like doing this and we'll see if if this will doing this and we'll see if if this will doing this and we'll see if if this will be more of a self-driving thing where, be more of a self-driving thing where, be more of a self-driving thing where, you know, like after a while when the you know, like after a while when the you know, like after a while when the car is doing good enough job, it doesn't car is doing good enough job, it doesn't car is doing good enough job, it doesn't really matter that you're behind it or really matter that you're behind it or really matter that you're behind it or but but it but if because of the roads but but it but if because of the roads but but it but if because of the roads are so well mapped and and the streets are so well mapped and and the streets are so well mapped and and the streets are so well known. But if it's rough are so well known. But if it's rough are so well known. But if it's rough terrain, terrain, terrain, I remember I was in Mongolia where the I remember I was in Mongolia where the I remember I was in Mongolia where the roads are very very rough and we were roads are very very rough and we were roads are very very rough and we were going on on rough terrain. And this going on on rough terrain. And this going on on rough terrain. And this driver was insane on how they drove. It

driver was insane on how they drove. It driver was insane on how they drove. It to me it all looked the same, but to me it all looked the same, but to me it all looked the same, but sometimes we're doing crazy turns and sometimes we're doing crazy turns and sometimes we're doing crazy turns and then you realize that he saw the like he then you realize that he saw the like he then you realize that he saw the like he saw the land that that would have could saw the land that that would have could saw the land that that would have could would have mushy. He saw the riverbeds would have mushy. He saw the riverbeds would have mushy. He saw the riverbeds that that would have go around. that that would have go around. that that would have go around. >> mode. This is an expert. And and it's an >> mode. This is an expert. And and it's an >> mode. This is an expert. And and it's an expert and I'm I'm sure that expert can expert and I'm I'm sure that expert can expert and I'm I'm sure that expert can also use like some sometimes hold like also use like some sometimes hold like also use like some sometimes hold like turn on or or use assists as well. But I turn on or or use assists as well. But I turn on or or use assists as well. But I you know, you know, you know, I love creating software. I used to say I love creating software. I used to say I love creating software. I used to say that I I I loved coding and that I I I loved coding and that I I I loved coding and I'm not sure that's true that ever was I'm not sure that's true that ever was I'm not sure that's true that ever was true. I think I I learned to to like it true. I think I I learned to to like it true. I think I I learned to to like it and I I loved being good at it. and I I loved being good at it. and I I loved being good at it. I I love that few people could do it. I I I love that few people could do it. I I I love that few people could do it. I I I still kind of love when I do stuff I I still kind of love when I do stuff I I still kind of love when I do stuff with code that no one can do. I When we with code that no one can do. I When we with code that no one can do. I When we go to the movie theater, go to the movie theater, go to the movie theater, the website does not allow you to book a the website does not allow you to book a the website does not allow you to book a ticket that is that has one seat in ticket that is that has one seat in ticket that is that has one seat in between. Well, guess what? It's a between. Well, guess what? It's a between. Well, guess what? It's a JavaScript only side trick and I I JavaScript only side trick and I I JavaScript only side trick and I I figured out pretty early. figured out pretty early. figured out pretty early. >> I literally hit that yesterday where I >> I literally hit that yesterday where I >> I literally hit that yesterday where I did not want to sit next to random did not want to sit next to random did not want to sit next to random people. people. people. >> [laughter] >> [laughter] >> [laughter] >> Yeah, so it's it's it's a client-side >> Yeah, so it's it's it's a client-side >> Yeah, so it's it's it's a client-side thing and I can go around it and thing and I can go around it and thing and I can go around it and everyone in in my friend group knows me everyone in in my friend group knows me everyone in in my friend group knows me and sometimes people ask me to do it for and sometimes people ask me to do it for and sometimes people ask me to do it for them. It makes me feel special. Like them. It makes me feel special. Like them. It makes me feel special. Like it's it's it's like out of the, you know, 10 or 20 like out of the, you know, 10 or 20 like out of the, you know, 10 or 20 immediate people I know, no one else can immediate people I know, no one else can immediate people I know, no one else can do it and it's not a big deal. You open do it and it's not a big deal. You open do it and it's not a big deal. You open dev tools, you figure out which class it dev tools, you figure out which class it dev tools, you figure out which class it is, you place a breakpoint, and then you is, you place a breakpoint, and then you is, you place a breakpoint, and then you override the variable, right? Like, but override the variable, right? Like, but override the variable, right? Like, but but you know what I mean? Like, and and but you know what I mean? Like, and and but you know what I mean? Like, and and that's what I mean, like, I that's what I mean, like, I that's what I mean, like, I I would like to think that I would like to think that I would like to think that I think we'll have an identity crisis, I think we'll have an identity crisis, I think we'll have an identity crisis, or we already are software engineers, or we already are software engineers, or we already are software engineers, figuring out, okay, if AI can write all figuring out, okay, if AI can write all figuring out, okay, if AI can write all these things, what else makes us uh these things, what else makes us uh these things, what else makes us uh special? But I think there is something special? But I think there is something special? But I think there is something much more than coding that makes us

much more than coding that makes us much more than coding that makes us special, and I think we should cultivate special, and I think we should cultivate special, and I think we should cultivate that. And that's why I love what Peter that. And that's why I love what Peter that. And that's why I love what Peter is doing, which is like, he is in is doing, which is like, he is in is doing, which is like, he is in charge, he is the architect, he has a charge, he is the architect, he has a charge, he is the architect, he has a taste. And that's why I'm not a huge fan taste. And that's why I'm not a huge fan taste. And that's why I'm not a huge fan of like Let's give it to Ralph. You just of like Let's give it to Ralph. You just of like Let's give it to Ralph. You just nailed it, though, and I love that you nailed it, though, and I love that you nailed it, though, and I love that you said it without me having to say it, said it without me having to say it, said it without me having to say it, because you The word is taste. because you The word is taste. because you The word is taste. Yep. Yep. Yep. >> The word is taste. He has a perspective. >> The word is taste. He has a perspective. >> The word is taste. He has a perspective. I would love to chat with him sometime, I would love to chat with him sometime, I would love to chat with him sometime, because I appreciate when someone has a because I appreciate when someone has a because I appreciate when someone has a perspective, whether it be perspective, whether it be perspective, whether it be uh DHH on Rails, it was opinionated. If uh DHH on Rails, it was opinionated. If uh DHH on Rails, it was opinionated. If it's David Fowler on Aspire, he's got an it's David Fowler on Aspire, he's got an it's David Fowler on Aspire, he's got an opinion. opinion. opinion. I disagree on the Ralph thing, though, I disagree on the Ralph thing, though, I disagree on the Ralph thing, though, because it's not all or nothing. because it's not all or nothing. because it's not all or nothing. Because David Fowler, distinguished Because David Fowler, distinguished Because David Fowler, distinguished engineer in .NET, and architect of engineer in .NET, and architect of engineer in .NET, and architect of Aspire, is a great example. He would Aspire, is a great example. He would Aspire, is a great example. He would never never never architect the Aspire orchestrator with a architect the Aspire orchestrator with a architect the Aspire orchestrator with a Ralph loop. However, they had four or Ralph loop. However, they had four or Ralph loop. However, they had four or 500 bugs that were all reported, and 500 bugs that were all reported, and 500 bugs that were all reported, and they couldn't confirm that they were they couldn't confirm that they were they couldn't confirm that they were real bugs. Mhm. So, he [clears throat] real bugs. Mhm. So, he [clears throat] real bugs. Mhm. So, he [clears throat] ran a Ralph loop, which I just think of ran a Ralph loop, which I just think of ran a Ralph loop, which I just think of being a really tenacious loop. It's just being a really tenacious loop. It's just being a really tenacious loop. It's just an infinitely patient junior engineer. I an infinitely patient junior engineer. I an infinitely patient junior engineer. I would never put an infinitely patient would never put an infinitely patient would never put an infinitely patient junior engineer on an architecture junior engineer on an architecture junior engineer on an architecture problem.

problem. problem. But if I But he went and he said, "Hey, But if I But he went and he said, "Hey, But if I But he went and he said, "Hey, go and look at these 400 bugs, and go and look at these 400 bugs, and go and look at these 400 bugs, and reproduce them." And I think he reproduce them." And I think he reproduce them." And I think he reproduced like 368 of them, and then reproduced like 368 of them, and then reproduced like 368 of them, and then added context. It was literally the very added context. It was literally the very added context. It was literally the very definition of toil. definition of toil. definition of toil. That's what a Ralph loop is for. But I That's what a Ralph loop is for. But I That's what a Ralph loop is for. But I don't think a million monkeys and a don't think a million monkeys and a don't think a million monkeys and a million keyboards could create million keyboards could create million keyboards could create something ama- amazing. Like, they something ama- amazing. Like, they something ama- amazing. Like, they always say that an infinite number of always say that an infinite number of always say that an infinite number of monkeys and an infinite They could They monkeys and an infinite They could They monkeys and an infinite They could They could make Shakespeare. But they need could make Shakespeare. But they need could make Shakespeare. But they need good taste. I I I I I think you're right good taste. I I I I I think you're right good taste. I I I I I think you're right in the sense that I you know where in the sense that I you know where in the sense that I you know where everything is so new like I feel as a everything is so new like I feel as a everything is so new like I feel as a professional as an engineer the professional as an engineer the professional as an engineer the engineering mindset is like look we've engineering mindset is like look we've engineering mindset is like look we've got this new thing like you know like got this new thing like you know like got this new thing like you know like the the kind of the the kind of the the kind of Well we have we have a new hammer right? Well we have we have a new hammer right? Well we have we have a new hammer right? Is everything a nail? a new hammer but Is everything a nail? a new hammer but Is everything a nail? a new hammer but like I'm like the kind of the amateur like I'm like the kind of the amateur like I'm like the kind of the amateur approach is like you're kind of wow this approach is like you're kind of wow this approach is like you're kind of wow this is so cool oh my gosh or or the novice is so cool oh my gosh or or the novice is so cool oh my gosh or or the novice is like it's magic it can do all these is like it's magic it can do all these is like it's magic it can do all these things and the engineering mindset is things and the engineering mindset is things and the engineering mindset is cool what are the limits? How well does cool what are the limits? How well does cool what are the limits? How well does this work? What are the limits? How far this work? What are the limits? How far this work? What are the limits? How far can I go? And I think that's that's what can I go? And I think that's that's what can I go? And I think that's that's what we need to figure out like it's like we need to figure out like it's like we need to figure out like it's like okay well how can we use it how well okay well how can we use it how well okay well how can we use it how well does it work? Ralph has an interesting does it work? Ralph has an interesting does it work? Ralph has an interesting technique which is what you said like technique which is what you said like technique which is what you said like when when is it a great use when has it when when is it a great use when has it when when is it a great use when has it been and you just add it to your your been and you just add it to your your been and you just add it to your your tool set and then you figure out which tool set and then you figure out which tool set and then you figure out which ones to use based on the problem based ones to use based on the problem based ones to use based on the problem based on honestly your mood and your energy on honestly your mood and your energy on honestly your mood and your energy levels and what you want to get out of levels and what you want to get out of levels and what you want to get out of it there's also this thing like you know it there's also this thing like you know it there's also this thing like you know when you use AI you get do you actually when you use AI you get do you actually when you use AI you get do you actually want to learn about a problem? Cloud want to learn about a problem? Cloud want to learn about a problem? Cloud code has has a mode where it can code has has a mode where it can code has has a mode where it can actually challenge you and it gives you actually challenge you and it gives you actually challenge you and it gives you task I I tried to use it and it looked task I I tried to use it and it looked task I I tried to use it and it looked like a good idea but it didn't really like a good idea but it didn't really like a good idea but it didn't really work but it's like how much do I want to

work but it's like how much do I want to work but it's like how much do I want to learn about a topic because then I will learn about a topic because then I will learn about a topic because then I will be more involved versus if it's routine be more involved versus if it's routine be more involved versus if it's routine and toil and yeah I I I feel like as as and toil and yeah I I I feel like as as and toil and yeah I I I feel like as as professionals like the best thing anyone professionals like the best thing anyone professionals like the best thing anyone can do is use all these things learn can do is use all these things learn can do is use all these things learn them have first hand experience do not them have first hand experience do not them have first hand experience do not believe what you read on the internet or believe what you read on the internet or believe what you read on the internet or or validate it cuz you want to have or validate it cuz you want to have or validate it cuz you want to have those strong opinions and then you know those strong opinions and then you know those strong opinions and then you know you have this like your tool set has you have this like your tool set has you have this like your tool set has gotten bigger if if you have a bunch of gotten bigger if if you have a bunch of gotten bigger if if you have a bunch of you 20 plus years of experience you you you 20 plus years of experience you you you 20 plus years of experience you you already have long tool set add some more already have long tool set add some more already have long tool set add some more tools if you if you have less tools if you if you have less tools if you if you have less [clears throat] experience add these [clears throat] experience add these [clears throat] experience add these tools and get really good at them and tools and get really good at them and tools and get really good at them and you're going to add a lot more as you you're going to add a lot more as you you're going to add a lot more as you go. Well and that's going to be a go. Well and that's going to be a go. Well and that's going to be a problem because people who are incurious problem because people who are incurious problem because people who are incurious are going to become not just incurious are going to become not just incurious are going to become not just incurious but ultimately just quite lazy. but ultimately just quite lazy. but ultimately just quite lazy. If if you don't want to learn more if If if you don't want to learn more if If if you don't want to learn more if you just want to get it done you just want to get it done you just want to get it done then it's then it's then it's no disrespect to the Swedes it's kind of no disrespect to the Swedes it's kind of no disrespect to the Swedes it's kind of IKEA furniture. IKEA furniture. IKEA furniture. uh versus bespoke furniture like what uh versus bespoke furniture like what uh versus bespoke furniture like what kind of a craftsperson do you want to kind of a craftsperson do you want to kind of a craftsperson do you want to be? be? be? And that's going to be challenging. Do And that's going to be challenging. Do And that's going to be challenging. Do you want to just get from point A to you want to just get from point A to you want to just get from point A to point B, or do you want to learn how the point B, or do you want to learn how the point B, or do you want to learn how the engine operates? Now, what book have you engine operates? Now, what book have you engine operates? Now, what book have you grabbed off of the off of the Gergely uh grabbed off of the off of the Gergely uh grabbed off of the off of the Gergely uh bookshelf? And I this was like when when bookshelf? And I this was like when when bookshelf? And I this was like when when you say like you know, like if if you're you say like you know, like if if you're you say like you know, like if if you're not learning, the best example of this not learning, the best example of this not learning, the best example of this is Chip Huyen uh from who wrote the book is Chip Huyen uh from who wrote the book is Chip Huyen uh from who wrote the book AI engineering. Okay.

AI engineering. Okay. AI engineering. Okay. >> And uh I I had her on on on the podcast >> And uh I I had her on on on the podcast >> And uh I I had her on on on the podcast as well. And one of the most surprising as well. And one of the most surprising as well. And one of the most surprising things So, so she is one of the biggest things So, so she is one of the biggest things So, so she is one of the biggest experts on AI engineering and and how to experts on AI engineering and and how to experts on AI engineering and and how to like build these tools, how use rag, and like build these tools, how use rag, and like build these tools, how use rag, and and embeddings, and all these things. and embeddings, and all these things. and embeddings, and all these things. And this is amazing book. Like, if if if And this is amazing book. Like, if if if And this is amazing book. Like, if if if you're doing anything with LLMs or want you're doing anything with LLMs or want you're doing anything with LLMs or want to do, just read it, get it. It's such a to do, just read it, get it. It's such a to do, just read it, get it. It's such a great great investment. One of the great great investment. One of the great great investment. One of the surprising things I had is she had this surprising things I had is she had this surprising things I had is she had this really nice graph in the book that I'm really nice graph in the book that I'm really nice graph in the book that I'm showing that shows the cumulative GitHub showing that shows the cumulative GitHub showing that shows the cumulative GitHub repositories based on explosion. based repositories based on explosion. based repositories based on explosion. based on what types of if if they're on what types of if if they're on what types of if if they're applications, AI engineering, model, applications, AI engineering, model, applications, AI engineering, model, repo, infrastructure. And there's 900 repo, infrastructure. And there's 900 repo, infrastructure. And there's 900 repositories over a nice thing. And I repositories over a nice thing. And I repositories over a nice thing. And I over like years. And so, she's kind of over like years. And so, she's kind of over like years. And so, she's kind of seeing showing trends. And I asked her seeing showing trends. And I asked her seeing showing trends. And I asked her like, "Cool. Like, how what kind of AI like, "Cool. Like, how what kind of AI like, "Cool. Like, how what kind of AI did you use to like categorize these 900 did you use to like categorize these 900 did you use to like categorize these 900 repositories?" She said, "I didn't use repositories?" She said, "I didn't use repositories?" She said, "I didn't use an AI. I did it by hand." I was like, an AI. I did it by hand." I was like, an AI. I did it by hand." I was like, "Hold on. Hold on. Hold on. This is an "Hold on. Hold on. Hold on. This is an "Hold on. Hold on. Hold on. This is an AI engineering book. You are AI engineering book. You are AI engineering book. You are >> by hand or by for loop by hand? >> by hand or by for loop by hand? >> by hand or by for loop by hand? She said she manually categorized them She said she manually categorized them She said she manually categorized them for the most part. I said like, "Why for the most part. I said like, "Why for the most part. I said like, "Why would you do manual?" She said like, would you do manual?" She said like, would you do manual?" She said like, "One of the most underrated things in ML "One of the most underrated things in ML "One of the most underrated things in ML engineering is that you want to put engineering is that you want to put engineering is that you want to put manual work up front Mhm. because it manual work up front Mhm. because it manual work up front Mhm. because it gives you better results." And she said gives you better results." And she said gives you better results." And she said that manual work is underrated for a few that manual work is underrated for a few that manual work is underrated for a few reasons. You will have better quality reasons. You will have better quality reasons. You will have better quality data. You will also learn a bit more.

data. You will also learn a bit more. data. You will also learn a bit more. And then when you figure out the And then when you figure out the And then when you figure out the patterns, you do automate some things. patterns, you do automate some things. patterns, you do automate some things. But she said that people working in ML But she said that people working in ML But she said that people working in ML engineering do actually not shy away engineering do actually not shy away engineering do actually not shy away from from manual work because it makes from from manual work because it makes from from manual work because it makes the end result better. So, like to me, the end result better. So, like to me, the end result better. So, like to me, this is just a reminder. If you use AI this is just a reminder. If you use AI this is just a reminder. If you use AI for anything automation, it can do all for anything automation, it can do all for anything automation, it can do all all these things. Like, the people I all these things. Like, the people I all these things. Like, the people I think who will will a lot more think who will will a lot more think who will will a lot more successful professionally are the ones successful professionally are the ones successful professionally are the ones who do not shy away from doing to start who do not shy away from doing to start who do not shy away from doing to start by doing manual work at first and only by doing manual work at first and only by doing manual work at first and only then move to automating it when you're then move to automating it when you're then move to automating it when you're like sick and tired of it. Yes, that's a like sick and tired of it. Yes, that's a like sick and tired of it. Yes, that's a great point. Like you have to you have great point. Like you have to you have great point. Like you have to you have to do the thing and then say, "Okay, now to do the thing and then say, "Okay, now to do the thing and then say, "Okay, now I want to I I want to perfect the thing I want to I I want to perfect the thing I want to I I want to perfect the thing and now I want to package it up and do and now I want to package it up and do and now I want to package it up and do it at at scale." it at at scale." it at at scale." I do feel like this reminds me we were I do feel like this reminds me we were I do feel like this reminds me we were talking before we started recording talking before we started recording talking before we started recording about kind of like our sense of history about kind of like our sense of history about kind of like our sense of history and like you know, having done this for and like you know, having done this for and like you know, having done this for 10, 20, 30 years. 10, 20, 30 years. 10, 20, 30 years. There's inflection points and I've There's inflection points and I've There's inflection points and I've experienced four. experienced four. experienced four. And I'm curious what you think about And I'm curious what you think about And I'm curious what you think about this. this. this. When we when I started in assembler, When we when I started in assembler, When we when I started in assembler, I would have neckbeards, I would have neckbeards, I would have neckbeards, non-gender specific neckbeards, just non-gender specific neckbeards, just non-gender specific neckbeards, just people who are old programmers say, "You people who are old programmers say, "You people who are old programmers say, "You don't want to use C.

don't want to use C. don't want to use C. That's for the weak. You know, real That's for the weak. You know, real That's for the weak. You know, real programmers, you know, poke it directly programmers, you know, poke it directly programmers, you know, poke it directly into a register." And then there was into a register." And then there was into a register." And then there was IntelliSense. I literally had people IntelliSense. I literally had people IntelliSense. I literally had people tell me that, you know, syntax tell me that, you know, syntax tell me that, you know, syntax highlighting would rot your brain. And highlighting would rot your brain. And highlighting would rot your brain. And you know, don't let it auto complete. you know, don't let it auto complete. you know, don't let it auto complete. Yep. That was one. Then there was the Yep. That was one. Then there was the Yep. That was one. Then there was the Stack Overflow moment. Stack Overflow moment. Stack Overflow moment. Where we just started copy-pasting Where we just started copy-pasting Where we just started copy-pasting directly into production. directly into production. directly into production. >> And now we're experiencing the death of >> And now we're experiencing the death of >> And now we're experiencing the death of the death of coding. the death of coding. the death of coding. And people think that means it's the And people think that means it's the And people think that means it's the death of the craft because we suddenly death of the craft because we suddenly death of the craft because we suddenly got a power tool that knows how to like got a power tool that knows how to like got a power tool that knows how to like It's like when you see those TikToks It's like when you see those TikToks It's like when you see those TikToks where they can like rip up an entire where they can like rip up an entire where they can like rip up an entire tree and chop it up into boards instead tree and chop it up into boards instead tree and chop it up into boards instead of like cutting it down. In the In the of like cutting it down. In the In the of like cutting it down. In the In the US, we have this thing called the Yankee US, we have this thing called the Yankee US, we have this thing called the Yankee Workshop where it's like a man alone in Workshop where it's like a man alone in Workshop where it's like a man alone in his kind of like Amish barn with just his kind of like Amish barn with just his kind of like Amish barn with just like a planing tool and he just does it like a planing tool and he just does it like a planing tool and he just does it the old-fashioned way. And that's why I the old-fashioned way. And that's why I the old-fashioned way. And that's why I try to like build silly robots and make try to like build silly robots and make try to like build silly robots and make Commodore 64s and you know, I saw the Commodore 64s and you know, I saw the Commodore 64s and you know, I saw the primogen writing a VI for C64 like we're primogen writing a VI for C64 like we're primogen writing a VI for C64 like we're going to see a return to bespoke going to see a return to bespoke going to see a return to bespoke software for fun and interesting and software for fun and interesting and software for fun and interesting and unique and creative work.

unique and creative work. unique and creative work. But I don't want to make another React But I don't want to make another React But I don't want to make another React database like text boxes over data. So database like text boxes over data. So database like text boxes over data. So toil I am willing to give up if it frees toil I am willing to give up if it frees toil I am willing to give up if it frees up time up time up time to do interesting crafts person work. to do interesting crafts person work. to do interesting crafts person work. Yeah, I I think like these inflection Yeah, I I think like these inflection Yeah, I I think like these inflection points are real and I I I've seen all of points are real and I I I've seen all of points are real and I I I've seen all of them except for the assembly. I've only them except for the assembly. I've only them except for the assembly. I've only heard about that one. But when I joined heard about that one. But when I joined heard about that one. But when I joined the workforce, I was using ReSharper and the workforce, I was using ReSharper and the workforce, I was using ReSharper and highlighting and yeah. highlighting and yeah. highlighting and yeah. >> Oh, wow. All the old the old the old the >> Oh, wow. All the old the old the old the >> Oh, wow. All the old the old the old the old-timers were like this is going to old-timers were like this is going to old-timers were like this is going to like it's I remember when ReSharper came like it's I remember when ReSharper came like it's I remember when ReSharper came out. out. out. >> Like I I I was dissed at and then I I >> Like I I I was dissed at and then I I >> Like I I I was dissed at and then I I was the generation that was dissing was the generation that was dissing was the generation that was dissing people for using Stack Overflow cuz I'm people for using Stack Overflow cuz I'm people for using Stack Overflow cuz I'm like you don't need that and it's it's like you don't need that and it's it's like you don't need that and it's it's inaccurate and all that. So I was kind inaccurate and all that. So I was kind inaccurate and all that. So I was kind of already by you know I had a few years of already by you know I had a few years of already by you know I had a few years experience, but this is experience, but this is experience, but this is I you know like there's a few things I you know like there's a few things I you know like there's a few things like the industry in the industry like like the industry in the industry like like the industry in the industry like people surprisingly don't like change people surprisingly don't like change people surprisingly don't like change even though the industry has been about even though the industry has been about even though the industry has been about change, but after a few stable years change, but after a few stable years change, but after a few stable years people forget about it and they get good people forget about it and they get good people forget about it and they get good at it and they're very resistant to this at it and they're very resistant to this at it and they're very resistant to this and it's hard to get rid of. If you've and it's hard to get rid of. If you've and it's hard to get rid of. If you've gone through a few cycles, it's a bit gone through a few cycles, it's a bit gone through a few cycles, it's a bit easier. So you know anyone who's feeling easier. So you know anyone who's feeling easier. So you know anyone who's feeling bad about this change like don't worry, bad about this change like don't worry, bad about this change like don't worry, it's going to happen in like 5-10 years it's going to happen in like 5-10 years it's going to happen in like 5-10 years again. So might as well just get used to again. So might as well just get used to again. So might as well just get used to this.

this. this. >> [laughter] >> [laughter] >> [laughter] >> What Yeah, what is it they say? The only >> What Yeah, what is it they say? The only >> What Yeah, what is it they say? The only thing that is constant is change. Yeah. thing that is constant is change. Yeah. thing that is constant is change. Yeah. But I do think a big thing that will But I do think a big thing that will But I do think a big thing that will change and I have seen this play out as change and I have seen this play out as change and I have seen this play out as well with the inflection points. Your well with the inflection points. Your well with the inflection points. Your typical software engineer changes a lot. typical software engineer changes a lot. typical software engineer changes a lot. In the early 2000s when I entered the In the early 2000s when I entered the In the early 2000s when I entered the field, the top software engineers and field, the top software engineers and field, the top software engineers and top software developers were antisocial top software developers were antisocial top software developers were antisocial but brilliant. They were brilliant but brilliant. They were brilliant but brilliant. They were brilliant jerks. They're But they were jerks. They're But they were jerks. They're But they were highly respected at least in the highly respected at least in the highly respected at least in the companies that I worked at because they companies that I worked at because they companies that I worked at because they were the ones who could wrangle all this were the ones who could wrangle all this were the ones who could wrangle all this code and they they could they could fix code and they they could they could fix code and they they could they could fix the bugs and they wouldn't you know the bugs and they wouldn't you know the bugs and they wouldn't you know hoard knowledge, but they were highly hoard knowledge, but they were highly hoard knowledge, but they were highly paid, highly respected. As time paid, highly respected. As time paid, highly respected. As time progressed and you know we had Stack progressed and you know we had Stack progressed and you know we had Stack Overflow and it became a bit easier to Overflow and it became a bit easier to Overflow and it became a bit easier to to onboard. It became easier to figure to onboard. It became easier to figure to onboard. It became easier to figure out the maybe the code. Like I think out the maybe the code. Like I think out the maybe the code. Like I think those people still got valued, but those people still got valued, but those people still got valued, but people who are a bit more social and people who are a bit more social and people who are a bit more social and collaborative started to get become a collaborative started to get become a collaborative started to get become a little bit more valued. Now that we had little bit more valued. Now that we had little bit more valued. Now that we had the internet, conferences, online the internet, conferences, online the internet, conferences, online forums, you know like including Stack forums, you know like including Stack forums, you know like including Stack Overflow, Overflow, Overflow, the people who started to be valued by I the people who started to be valued by I the people who started to be valued by I think the top-tech companies were both think the top-tech companies were both think the top-tech companies were both like really good software engineers but like really good software engineers but like really good software engineers but also also also kind of good at teamwork, collaboration.

kind of good at teamwork, collaboration. kind of good at teamwork, collaboration. Well, it's humans in the loop. We keep Well, it's humans in the loop. We keep Well, it's humans in the loop. We keep hearing this humans in the loop, humans hearing this humans in the loop, humans hearing this humans in the loop, humans in the loop. Like in the loop. Like in the loop. Like we never should have tolerated brilliant we never should have tolerated brilliant Yep. And for And fortunately many of the Yep. And for And fortunately many of the brilliant and we won't speak brilliant and we won't speak brilliant and we won't speak their names have have recognized that their names have have recognized that their names have have recognized that and in their older age become and in their older age become and in their older age become quite pleasant people that acknowledge quite pleasant people that acknowledge quite pleasant people that acknowledge that if you're not making software for that if you're not making software for that if you're not making software for people, whether it be yourself or your people, whether it be yourself or your people, whether it be yourself or your family or your friends or to make family or your friends or to make family or your friends or to make someone's life better, then what are we someone's life better, then what are we someone's life better, then what are we even what are we even doing? So Yeah, even what are we even doing? So Yeah, even what are we even doing? So Yeah, but but but but but but some of the recent job adverts of like some of the recent job adverts of like some of the recent job adverts of like modern companies that are doing a bunch modern companies that are doing a bunch modern companies that are doing a bunch of AI stuff of AI stuff of AI stuff I no longer see technologies listed but I no longer see technologies listed but I no longer see technologies listed but I do see for example empathy for I do see for example empathy for I do see for example empathy for customers. I see a lot more soft skills customers. I see a lot more soft skills customers. I see a lot more soft skills being listed. Like if you read just being listed. Like if you read just being listed. Like if you read just search for product engineer at any search for product engineer at any search for product engineer at any company that has raised funding, a company that has raised funding, a company that has raised funding, a VC-funded company that raised funding in VC-funded company that raised funding in VC-funded company that raised funding in the last like one or two years and it's the last like one or two years and it's the last like one or two years and it's it's almost like it's describing this it's almost like it's describing this it's almost like it's describing this really pleasant colleague and I've really pleasant colleague and I've really pleasant colleague and I've talked with some of these companies and talked with some of these companies and talked with some of these companies and how they hire and they reject a lot how they hire and they reject a lot how they hire and they reject a lot based on soft skills on on not being based on soft skills on on not being based on soft skills on on not being open up and a lot of the because a lot open up and a lot of the because a lot open up and a lot of the because a lot of the work has become is becoming of the work has become is becoming of the work has become is becoming software engineers talk with customers.

software engineers talk with customers. software engineers talk with customers. They sit with meetings with them. They They sit with meetings with them. They They sit with meetings with them. They ask like how are you using that? Like ask like how are you using that? Like ask like how are you using that? Like oh, that's interesting. Can you tell me oh, that's interesting. Can you tell me oh, that's interesting. Can you tell me more? And this is a brand new more? And this is a brand new more? And this is a brand new a brand new persona that was not a a brand new persona that was not a a brand new persona that was not a developer. Like this used to be a developer. Like this used to be a developer. Like this used to be a project manager or product manager back project manager or product manager back project manager or product manager back in the day. So I think the profession is in the day. So I think the profession is in the day. So I think the profession is changing where where what is valued is changing where where what is valued is changing where where what is valued is is changing because again is changing because again is changing because again and I think it goes back to like back in and I think it goes back to like back in and I think it goes back to like back in the you know, like 60s, 70s, 80s, there the you know, like 60s, 70s, 80s, there the you know, like 60s, 70s, 80s, there were so few people who could understand were so few people who could understand were so few people who could understand how to write that really really how to write that really really how to write that really really difficult assembly code and then of difficult assembly code and then of difficult assembly code and then of course C and and all those things and course C and and all those things and course C and and all those things and some the personalities were as they some the personalities were as they some the personalities were as they were. I mean it just happens. But now were. I mean it just happens. But now were. I mean it just happens. But now there's so many more people. Everyone there's so many more people. Everyone there's so many more people. Everyone can write code with with with AI but now can write code with with with AI but now can write code with with with AI but now we need people who can still engineer, we need people who can still engineer, we need people who can still engineer, who are empathetic, and can do all these who are empathetic, and can do all these who are empathetic, and can do all these other things as well. So, it's it's other things as well. So, it's it's other things as well. So, it's it's interesting to see how the profession interesting to see how the profession interesting to see how the profession changes, and I think it's really worth changes, and I think it's really worth changes, and I think it's really worth paying attention. Like, if you're in paying attention. Like, if you're in paying attention. Like, if you're in this industry, pay attention to what's this industry, pay attention to what's this industry, pay attention to what's happening, and see if you're lacking happening, and see if you're lacking happening, and see if you're lacking some of those skills, get those get that some of those skills, get those get that some of those skills, get those get that experience. Like, experience. Like, experience. Like, if you have few years of experience, if you have few years of experience, if you have few years of experience, you're in the industry, congratulations. you're in the industry, congratulations. you're in the industry, congratulations. Like, that's great, cuz it's hard it's Like, that's great, cuz it's hard it's Like, that's great, cuz it's hard it's harder and hard to get into the harder and hard to get into the harder and hard to get into the industry. If you're not yet in the industry. If you're not yet in the industry. If you're not yet in the industry, know that these things will industry, know that these things will industry, know that these things will will also become valuable.

will also become valuable. will also become valuable. That is a great place to end, because it That is a great place to end, because it That is a great place to end, because it is a very pragmatic perspective. is a very pragmatic perspective. is a very pragmatic perspective. And as you are the pragmatic engineer, And as you are the pragmatic engineer, And as you are the pragmatic engineer, uh uh uh I appreciate you offering your I appreciate you offering your I appreciate you offering your perspective and spending so much time perspective and spending so much time perspective and spending so much time with me today. with me today. with me today. It was great, Scott. Thanks very much. It was great, Scott. Thanks very much. It was great, Scott. Thanks very much. Thank you. You can check out more of Thank you. You can check out more of Thank you. You can check out more of Gergely at pragmaticengineer.com. Gergely at pragmaticengineer.com. Gergely at pragmaticengineer.com. You can subscribe to the number one You can subscribe to the number one You can subscribe to the number one technology newsletter on Substack. technology newsletter on Substack. technology newsletter on Substack. This has been another episode of This has been another episode of This has been another episode of Hanselminutes, and we'll see you again Hanselminutes, and we'll see you again Hanselminutes, and we'll see you again next week.