Become a Creator today!Start creating today - Share your story with the world!
Start for free
00:00:00
00:00:01
Where is AI taking us? - with The Pragmatic Programmer Gergely Orosz
4 Plays3 days ago
AI is moving faster than our collective ability to metabolize it. Between copilots, agents, vibe coding, and the ever-shifting definition of “senior engineer,” developers are asking a deeper question. Where is this all actually going? In this episode, Scott sits down with Gergely Orosz, author of The Pragmatic Engineer and longtime observer of how software gets built inside high-performing teams, to separate signal from hype.
They dig into what AI is really doing to day-to-day engineering work. Productivity boosts versus skill atrophy. The changing expectations for junior developers. Whether “AI-first” companies are structurally different or simply marketing-forward. Gergely brings his trademark data-driven pragmatism, grounded in conversations with hundreds of engineering leaders navigating hiring freezes, agent experiments, and the reshaping of career ladders.
Scott and Gergely also explore the human side. What happens to craftsmanship when code is abundant. How we teach the next generation to think, not just prompt. Why developer experience may matter more, not less, in an AI-accelerated world. Along the way, they consider whether we are watching a platform shift on the scale of cloud and mobile, or something even bigger.
Recommended
Transcript
00:00:00
Speaker
I would never write that app. That would be ridiculous. It would take me. Ridiculous. Why would you? No. Right. But now suddenly the Lego pieces, we've got OAuth, we've got personal access tokens, we've got nice clean REST APIs, a pattern to do it. We've got Python and.NET and JavaScript, all very well understood to go and do these things. And I just said, go and tell me if any meetings are stressing me out. And it turns out that I'm going low blood sugar on Mondays because I don't eat lunch on Mondays.
00:00:29
Speaker
I never put it together until I combined effectively a join across Outlook calendar and my blood sugar. And it it took 20 minutes.
00:00:40
Speaker
And then I wrote a whole... a report, and then I said make it a scale and put it in GitHub. And now other people are using it. That's insane. Hi friends, I'm Scott Hanselman. This is another episode of Hansel Minutes. Today I have the extreme pleasure of chatting with Gorgay Oroz, the author of the Pragmatic Engineer newsletter, number one technology newsletter on Substack, and just a lovely gentleman. How are you, sir?
00:01:01
Speaker
Doing great, Scott. it's It's really nice to to be here and catch up this time over video. Last time it was in person. Yeah, yeah. We hung out in person for a little while, and now we're on we're on video, we're on audio on the podcast. You've got the Dune Ornithopter Lego on your credibility bookshelf with all of the great books. I see Code Complete by Steve O'Connell there in the background. I can immediately say this is a serious person right now.
00:01:25
Speaker
Yeah, and I had the extreme joy and and privilege to interview Steve McConnell. justconnell Did he sign it? About a year ago, he did sign...
00:01:36
Speaker
it's Yes, he did. I have a signed book. I'm showing it to the camera. Oh my God. This was a big deal because Steve McConnell, he actually left tech as a whole about three years ago. He had an amazing run and now he's just reinventing himself. But he is just as thoughtful as as ever. And the the crazy thing about this book, Code Complete, that was so inspiring for me, Steve McConnell wrote this when he had five years of experience.
00:02:02
Speaker
or so he wrote 900 pages which has been the bible for about 20 years for so many people and one thing that reminded me is you don't need to wait to you know have 20 or 30 or 40 years experience do something that can be industry defining or helping just so many people you can start when you have one year two years three years of experience you don't need to wait for longer You know, that's a really great thing that you've said because I've always tried to express to people that I'll read your blog. I don't care how many years you've been doing this because no one has your perspective. No one has...
00:02:35
Speaker
You're i like, oh, I don't know. Everyone's already written everything there is to write about Python. I don't know your perspective. I don't know how you got into it. i think that's great. That book, a Code Complete, that, of course, is the new version 2. That book came out in 1993. I started coding for money in 92.
00:02:51
Speaker
So Code Complete was literally my entree into software engineering. like i I landed in software around April of 1992, and then Code Complete like just People don't understand. It was the biggest thing.
00:03:07
Speaker
it was so it was a word of mouth book. I did not realize that he only had five years experience at the time. Yep. Wow. In fact, fun fact, just on like how funny things are, he told me and we and I have a podcast that is episode on on on my podcast with him for where we talk about an hour and a half about these topics. But when he published, apparently the publisher did not expect this book would sell. They just wanted a so-called backfiller in their catalog just to have something there. And apparently the publisher was the most surprised at how many people started to buy. So again, just another A thing that even even the publisher, even the person who read this 900 pages did not expect this to be big. So sometimes you just got to do things. And even if you don't think it's a big deal, Steve told me that he didn't think this was that revolutionary. I mean, who was he? Everyone probably should have known this thing. So just one more thing. Just do stuff. Put it out there. Worst case is, you might have help one person. and Even that's an amazing feeling, I can tell you.
00:04:00
Speaker
You know, that's a great that's a great way to start the conversation because there's this funny this this lovely comedian that I'm mutuals with on TikTok named Rodney Norman. And he looks like a crazy mad scientist like from Back to the Future. And he's got a wonderful long ZZ Top beard. And he kind of pops up on your screen and he says, you know, you can just do stuff.
00:04:20
Speaker
you can just You don't have to ask permission. You just make things. Okay, have a great day. And it just you know you're just doing your thing, and he's just there to tell you that you can just do stuff.
00:04:30
Speaker
And, ah man, I'm just doing so much stuff right now. I have gotten more done since Opus ah than probably in the previous two years. And by doing stuff, I mean shipping interesting stuff. I feel like I've got a rocket ship strapped to my back.
00:04:45
Speaker
Are you having as much fun as I am? Yeah, I've been very surprised on on how... just really good these agents have gotten. I'm someone who's skeptical with any any any hype, any claim. I've been skeptical about crypto, not not for the sake of crypto, but just the hyperbolic claims. I've been skeptical about AI because early on, about a year and a half ago, we had people saying, oh, here's this AI that's going to replace software engineers. And again, it sounded very hyperbolic and also a little bit depressing, to be fair. 100% agree. but But then I always like to look at stuff. I like to try out firsthand what can it do. And again, it was it was pretty good. It was decent autocomplete initially. It then started to do some stuff, but it started it hallucinated when I used ChatGPT or I tried to use it for anything more complex, you know like cursor early on. The suggestions were maybe not exactly what I was thinking of. But also like over over the the winter break, i I can still code pretty well.
00:05:39
Speaker
if I put myself to it, but I just don't really do it because it's a lot of time to get in the zone. my My side projects are, are i have a lot of side projects and and also I have some of my my business runs on my own APIs. I try to build whenever I can, for example, for a newsletter group descriptions, there's like a self-service API.
00:05:57
Speaker
Companies can sign up and their whole domain can go on there and they get reporting and all that stuff. I built that on it's a tech stack that I wasn't that familiar at the time. I wanted to play with Express.js and Node.js and TypeScript.
00:06:08
Speaker
And every now and then I go back to it, but it always took me about 30 minutes to like get back, you know remember the structure. Thank God I have tests, so whenever I make a change, i can actually tell if I broke something. And this winter break, I just went there again. like I have so many ideas. And you know like this time, I heard Cloud Code is great. So I just told Cloud Code, they you know build this endpoint and and build me this this feature.
00:06:30
Speaker
And it did it. And then I looked at it, i said, run the test. And it did. and the tests And then I looked at it, and like one of the tests was not great, so I had to fix it. But then it it did it. And I found myself that I had spent about...
00:06:43
Speaker
five minutes on this thing. And it's already added a thing that I thought would take me two hours, 30 minutes to get in the zone, an hour to be in there. And then my wife said like, hey, how long are you going to be?
00:06:53
Speaker
And usually, whenever I'm coding or writing for that, like being in the zone, my time estimate is terribly often. This is a lot of source of conflict. But with this one, I was like, ah just just one more minute. And I literally just put another prompt. And then I stood up and I went for dinner. And i was like, oh,
00:07:08
Speaker
what happened like you're early like we're not working i'm like i was working but i'm using this thing this agent and it's just i'm just having this wow moment again and again and again another story was where again i had this like massive wow moment on my website i have testimonials of like ah you know people saying nice thing about the newsletter or or podcasts on twitter real people and i i paid about a hundred dollars a month for this software as the service where i can just they have a nice or not a nice, a very simple admin interface where I can post a Twitter link. It generates a UI and I can embed it with an iframe and I pay for the service.
00:07:42
Speaker
And I got a bit pissed because I didn't get an invoice from them. Turns out this service has been like sold twice over. Their invoice system is a mess. I have a new invoice coming up. I don't know how much I'm going to pay. And I was thinking to myself, like, hang on, like, can I not have an agent replace this because I know i like I'm paying attention. I just don't want to maintain an HTML file that has all these nicely formatted things. So I told the agent, hey, go there, collect all these testimonials, put it in a structure that is easy to maintain because I'm thinking about that already. Put it in a JSON format and you know like like put it separately and in build time generate this HTML and then show me the results.
00:08:22
Speaker
And in about, I actually measured it, end-to-end 20 minutes I went from, i have the third party that I'm depending on to, I have no third party, the build is passing, it's now pushed out to production, and I did two tweaks to it, and I'm done.
00:08:35
Speaker
yeah And to me, this is mind-blowing, like the implications. So like until now, like again, as a software professional, as someone who knows how to code, knows how to deploy, i was willing to pay, like my time is pretty valuable. I kind of like value my time roughly as like, I don't know, something like $300 an hour or $200 an hour when I work for kind of myself, because I want to put value on the time. So for me, If it takes an hour, it's worth paying for me $100 a month. And you know you can agree or disagree with this.
00:09:00
Speaker
But now it took me 20 minutes to replace it for good. Why would I pay $100? yeah, just like you, I've been mind blown with how many things I can do, not to mention my personal expenses, some of these things. It's just opening a whole new world. And it's not just me or you. I'm talking to a lot of ah people, folks working at startups, at as as engineers, and everyone's having this like This winter break was the weirdest winter break. People are coming back and saying, damn, like so many things work, and everyone's changing like how they work, experimenting, and just getting a lot more stuff done.
00:09:32
Speaker
Yeah, i've good I'll give you two quick stories. So the back end for Hansel Minutes, which has been this way for... probably 15 years, maybe longer, the the podcast is over 20 years old, is JavaScript files in Azure storage.
00:09:46
Speaker
And once a week, I would take 10 or 15 minutes. I'd open it in Visual Studio Code. I'd edit the JavaScript files, which would express a new show has come out, and then there's a linkage to some advertising. And every single week, I was like, in one of these days, I'm going to take a weekend.
00:10:01
Speaker
I'm going to write an admin. I wrote an admin. it I used GitHub Copilot CLI. I used Opus 4.5. It was 42 minutes. It took longer to figure out how to deploy it to the cloud than it did to write the thing.
00:10:16
Speaker
And I think the that's that's idea number thing number one. And then... A couple weeks ago, I use ah a blood sugar management system called night scout, which is an open source software. And I have a rest API, which is my blood sugar. So when I'm overseas or I'm traveling, my wife can see my blood sugar on like screens around the house and things like that. And there's a notification. If my blood sugar goes higher, goes low.
00:10:39
Speaker
it's um It's very specific, it's very grounded, and it's a number. I don't want to hallucinate that. But I now want to have joins with other data, like how does my blood sugar interact when I walk, when I travel, when I eat certain foods, when I'm in certain meetings. So now there's and ambiguity.
00:10:57
Speaker
The agent loop, the agentic loop, is an ambiguity loop. And that ambiguity loop then now allows me to join two things. So I used two pieces of data, one, my blood sugar system.
00:11:10
Speaker
And the other one is a thing called work IQ, which is effectively like talking to the Microsoft graph. So it's like, you know, using Google calendar API. And I just said, are any meetings correlating with my blood sugar?
00:11:21
Speaker
Like, I would never write that app. That would be ridiculous. It would take me. Ridiculous. Why would you? No. Right. But now suddenly the Lego pieces, we've got OAuth, we've got personal access tokens, we've got nice clean REST APIs, a pattern to do it. We've got Python and.NET and JavaScript, all very well understood to go and do these things. And I just said, go and tell me if any meetings are stressing me out. And it turns out that I'm going low blood sugar on Mondays because I don't eat lunch on Mondays.
00:11:50
Speaker
I never put it together. until I combined effectively a join across Outlook calendar and my blood sugar. And it it took 20 minutes.
00:12:01
Speaker
And then I wrote a whole a report. And then I said, make it a scale and put it in GitHub. And now other people are using it. That's insane. Yeah, and i I was always skeptical when I heard the return of personal software because I've been here for 10 plus years. Oh, I love personal software. look But i was I was skeptical just personally because i I personally did not see it. And again, you you might have seen more than I have. But I'm starting to become a believer in the sense that i I mean, what you told me and also what I'm doing, it's kind of personal software, software that I wanted for myself or for a very small business. And for example, for my own business, the Pragmatic Engineer,
00:12:37
Speaker
It would not make sense. It would have never made sense to hire anyone. So I was buying SaaS services, even though I'm a software engineer. And now with AI, again, i I would have not hired anyone at all. It just would have not been built. And now I'm building stuff. And also, oftentimes, as you say, you're building stuff that just would have not made sense at all. so This is a great point. I'm not going to buy a back end for my bespoke podcast any more than you're going to buy, you know, well, you did pay for this this embedded thing. But now you're probably wondering, why is that a business?
00:13:06
Speaker
And now the question is, should you spin off the thing you wrote as its own business? This is the other thing I'm watching people do, spin off 30, 40 little tiny micro sasses for other people.
00:13:17
Speaker
Yeah, that's a good question, what will happen Microsoft. But when you said your open sourcing thing, one thing that I'm also hearing, my my brother startup, they just open sourced a visual representation of cloud code that they built for themselves and other people can use it. And he's seeing a lot of remixing going in at open source where, for example, in that open source project, he does not want to merge other people's port requests because he wants to keep...
00:13:43
Speaker
direction Like he he wants to keep it consistent. So he he looks at the whatever comes in a pull request and he looks at the idea. And if he likes it, he will then ah use the agent to actually build it the way he thinks it should be done. So strong control. But what he's seeing here is a lot of people are forking off their open source project and remixing it. Because with an agent, again, you can you can tell an agent, like hey, generate a pull request and hope someone merges it. Or you can just say, like hey, make this change in the software, in this fork, especially when it's open source. And a lot of people are putting it on on GitHub as open source, because again, it's easy. Open source product projects are, I think, for free, or maybe it's free otherwise.
00:14:20
Speaker
But we might see an explosion in open source because of this remixing nature. It's it's very So this is the thing, though, we're hearing this term slop and AI slop. And some people are saying, well, this is just slop.
00:14:32
Speaker
But if it works well and it's personal and it's only on your machine and it does the thing you want it to do, maybe it's not slop at all. Two things that I remixed recently, the Mac has that ring light that is a feature. I made a Windows ring light, had a lot of fun with it. So it's basically an artificial drawn ring light. And then just literally two days ago on on Hacker News, I saw the most clever thing called Posture for Mac, where if you slouch, it detects that you slouched. Amazing. It blurs your screen.
00:15:04
Speaker
So then it causes you to have to sit up straight in order to you know make your screen clear again. So I told Copilot CLI to go and make me a Windows version. So now I have an application that literally dims the screen if my posture is bad to force me to like think about it. That's just silly so personal software. And now we've got Claudebot.
00:15:25
Speaker
um I just spun up in WSL, Windows Subsystem for Linux, and I'm debating if I should run it in my Synology. which would be my my NAS, my network. yeah So like why shouldn't I have a little server in my own house doing my own thing, plus something like Home Assistant?
00:15:42
Speaker
I'm curious, are you a Home Assistant person? and Not as much. I use it all a little bit, but i've i've just not I think I don't have the integrations for it, but I could see myself using it. But I i totally agree with you. like the The idea of like a you know personal assistant, I feel we're back into the...
00:15:57
Speaker
the good old days of when PCs were starting to become mainstream, where we just had like you know home homemade software. like It was distributed on the internet, and and you know you controlled your own hardware and and you had your own software. like Again, for a personal assistant, why why could I not have it run on my stuff and and me choosing my subscriptions and me choosing what it had access to? like It feels like the hacker mentality is back. like yeah There was a time for hackers in the ninety s and pop fiction everywhere, but it was happening, I remember. And then it kind of went away the last like few years, decades.
00:16:31
Speaker
Yeah, I feel like there's ah other than the part where the LLM runs in the cloud, a lot of this stuff can be done internally. And I always try to think about, ah would my software work in airplane mode?
00:16:44
Speaker
I just feel like that's important. and My house needs to work in airplane mode. And also, don't forget, like I personally think it's just a matter of time, a matter of years, where LLM will run on your machine. I mean, there's a lot of a lot of work being done. I know the Windows 11 team is is doing a bunch of stuff around infrastructure pieces to make that one day happen. LLMs are getting so smaller. and And actually, some of them run on your laptop. They're just not nearly as good as state-of-the-art. But again, yeah like i'm I'm hoping this will be the case because I 100% agree. I've got, um you know, LM Studio is a fantastic app. Everyone talks about Olama, but they're sleeping on LM Studio, LM Studio dot AI um running that.
00:17:22
Speaker
It then presents an open AI endpoint that's available inside your house. totally works locally. And if you do that, plus like a GPT 20 billion OSS, you've got a perfectly good model that will run inside your house. It makes me wonder, will it run on your laptop?
00:17:38
Speaker
Will it run on your desktop? Or again, I bring up this idea of the NAS. If you remember things like Windows Home Server, the Synology, TrueNAS, FreeNAS, why wouldn't I have a tiny machine that would sit in a closet that would provide a totally private LLM for the family?
00:17:56
Speaker
100% agree. I have NASes running back in my Dropbox already, and it's it's already on. I wouldn't mind like you know doing a little inference when we need it. yeah yeah I don't know if you can see over here, people who are listening won't be able to see it, but this is a Ricci mini robot that is a from Hugging Face. And this is a little robot that you buy from Hugging Face, and then you can deploy, it's got a Raspberry Pi in it, and then you can have it do stuff.
00:18:20
Speaker
um It took me about 15 minutes to create a skill. So when when ah Copilot CLI is done with something, he'll celebrate. Like it's, it's so much more interesting and personal to hack and build your own robot than to like yap at Alexa. Who's just going to remind you that like to buy more crap.
00:18:41
Speaker
Like I built that guy and he can talk to me and he'll order food and he'll put things on my grocery list and he'll dance when my, when my, my build is done.
00:18:52
Speaker
that's, you know, make the web weird again is kind of where I'm where i'm at. Yep. Yeah. So have you looked at ClaudeBot? you been spending time with that? Because there's a lot of controversy about the security aspect of it. And I think it's people should just relax a little bit because everything starts insecure to start with.
00:19:11
Speaker
So interesting, you would say, because I talked with Peter Steinberger. I met him in London two weeks ago, and I have a podcast episode coming out. Oh, great. It will have been out but by the time we we talked. So I knew a little bit of CloudBall before, but he showed me on his phone. And he showed me what he had it had it hooked up, and it was wild. like Again, he gave it full access to all these things. you know he He is living on the edge, and he's very clear, by the way, that you should probably not do this.
00:19:37
Speaker
He is YOLOing it. I mean, he's not giving access to the bank account, some some other things, but he's giving way wider access than I would be comfortable with. But then he showed me how he uses day to day.
00:19:48
Speaker
He showed it, he kind of dely wasn't demoing, he was just like just using it. And after five minutes, my thinking was like, oh my gosh, this is what Siri would be like in 10 years, but he has it working here. I mean, yeah it's got a lot of shortcuts, clearly like a lot of things that that you need. What's an example of something that blew your mind? Because I use Siri, all and i I want to preface this by saying, I'll use Siri very often for things like ah geo geofencing.
00:20:15
Speaker
So I'll say, remind me when I get home to do this. And I find that magical. I could say, hey, you know make me an appointment with Gergay tomorrow at this location. Those things are nice, but it's the giving it arms and legs part that's interesting.
00:20:31
Speaker
So like... He showed me how he uses this. He just tells it to book me an appointment, for example, for his barber. And it goes off. And and the the wild thing about that was that it tried to go online, but it struggled or something crashed for some reason, or it had an issue with the the browser.
00:20:51
Speaker
And it created itself a voice skill using Eleven Labs, which it had access to because like he oh no like like he has a subscription and actually made the call without asking him. so And it then added this skill to the functionality. It's all in the logs, though. soration But the fact that it's an agent that can that can improve itself already, this was well, then it got the stuff done that he wanted, which was a bit of a scary thing for me. Like, okay, I just went off and like actually made this call with with Eleven Labs Wild.
00:21:22
Speaker
but Which is funny because that's what Google did and everyone thought that was creepy. Yeah. And yeah you you can decide where are. But again, this this is the fact that it can and and it can do a lot of things where it can figure stuff out and it can browse and it can create a new skill for itself, which is very, very surprising. I think this has so many like fascinating and slightly terrifying implications, but I'm more on the fascinating side. And then the other side, which was crazy, he he took a photo of two of us and said, like hey, like who who who am I here with?
00:21:51
Speaker
And it looked at the the photo, it it analyzed it it, it ran a search, and then cross-referenced his calendar and said, like, oh, yeah, this is going to be great. Like, that was easy because I just i just have you here.
00:22:02
Speaker
and But what really, the biggest thing that fascinated me is how how hooked Peter was with his... agent and how much it was tuned on to his personality. It knew what he was doing. And it it was, I'll be honest, it felt a bit weird on how clearly addicted to it it it was.
00:22:22
Speaker
And I'm kind of thinking there's going to be a danger. And I mean, you look at a danger or opportunity. Like, you know I know people were addicted to chat GPT, but this is going to be way more addictive. And you're right it might not be cloud bought, but it it might be the next version that's No, but it's the concept of immediacy. Like we we are a certain we are men of a certain age, but the idea that like you used to wait six to eight weeks for the thing to come in the mail.
00:22:44
Speaker
And now if it's not there by the afternoon, you're upset. Or you used to wait two to four weeks to get your passport renewed. If you can't renew it overnight, you're mad. The idea that you can have food delivered to you by a stranger or a stranger can bring their car to you and then take you anywhere is is amazing. And if that breaks down, we will have a group of helpless people who are unable to do anything for themselves, much less do their own laundry.
00:23:10
Speaker
yeah But to your question on the security, like I kind of view it, it like I'm also a bit more chill about it like i view it. I remember the times where Windows was just starting to become big in the 90s, where I was getting my first machines.
00:23:21
Speaker
And you know the way you got software is you you kind of pass it on floppy disks. And later there were websites that you could download. Mm-hmm. And of course, later there were ways to get you know likes so-called cracks for the for the... A lot of the games had protections with like you had numbers to fill in from manual and all that. And there were cracks that would that would crack this or make a modification. And people were downloading that. And a lot of it was viruses. And a lot of people got nasty viruses and their computers and all sorts of stuff.
00:23:48
Speaker
And over time, people learned, well, a this is bad. B, like, okay, we will have... like protection like antivirus or turn to a professional in your family on what to do. And I think we're we're going to have exactly the same age where these AI agents can do a lot of stuff. If you give access to sensitive stuff, they will be both more powerful, but also they can be a lot more vulnerable and they can do like crazy stuff. So I think we'll have the whole learning, except it'll happen a lot faster because now the whole world well has access and it'll be a lot bigger storm.
00:24:16
Speaker
Did you have, we're a little bit different in age. Did you come up putting like your your, your homework on a floppy disk, like a thesis or were you a little beyond that? i I was a little beyond that. it It was already email for me. So there was a saying back when we used to carry our homework around on a three and a half inch floppy that like everyone has to lose their thesis once.
00:24:35
Speaker
It's like a rite of passage. Like you're you're walking around with your entire PhD thesis on a three and a half floppy and you leave it out in the sun or whatever. And then you call a friend with Norton Disc Doctor. So like that happens one time.
00:24:49
Speaker
right you You get your your Twitter hacked, or you lose your Dropbox key, or you lose your Bitcoin in ah in a dump somewhere. Somebody's going to get absolutely destroyed at some point. But in doing that, we will all learn.
00:25:03
Speaker
So when I say I'm less chill about it, the idea that you have to ship it sloppy and wide open first in order to get... what the but What is the limit here? And he's obviously on the on the limit.
00:25:14
Speaker
I had a delightful moment with ah Claude Bott recently. I installed it in. So I'm on Windows. I installed it in WSL, which is the subsystem within Windows, because i want it sandboxed. It's not a legitimate sandbox in the sense of there's no auditing, but it's extremely transparent that it stores everything in memories.
00:25:31
Speaker
And i I talk a lot about this and I'm curious what you think. I call it AI's uncanny valley, right? The uncanny valley in like 3D animation is like, ooh, what's wrong with that?
00:25:42
Speaker
What's wrong with face? Like the rock and the scorpion king. It's like, it's clearly bad CG. If an AI breaks into the uncanny valley and calls your barber on your behalf, that would break deeply into the uncanny valley for me.
00:25:56
Speaker
But I gave it access to my book. That that was a task to to book an appointment. But it did it by any means necessary. And I would need to say, don't, don't, tell you know, doing like that's too far. Like it would have to have a sense of taste. but yeah But I do like the idea of proactivity because a good a good assistant, oh, i took the I took it upon myself to put you in the aisle seat because I know you love the aisle.
00:26:19
Speaker
That's cool. You know what I mean? Oh, I put you in first class because I love you and I charged it and I opened a credit card for you. i didn't think you'd mind. That's not okay. right yeah But um i told about my blood sugar, right?
00:26:32
Speaker
And I said, remind me if my blood sugar goes too high because it has cron jobs. And I'm looking at it right here. It said, i also added a low because you're diabetic and lows are more dangerous. I'd rather be more annoying than let a low blood sugar slide. I hope you don't mind. Yeah.
00:26:51
Speaker
that's that's very like, I don't know. it's It's enthusiasm. it's it's It's easily solved. It's all in a markdown file. I think that the there's the novelty of it, but there's also the idea that I know why it's happening.
00:27:07
Speaker
Like if you compare it to Siri, I don't know why it thinks these things. I don't know what weird stuff it knows about me. It's in, or Alexa, it's in the cloud somewhere. But with this, it's in a file called, it's literally called soul.md.
00:27:23
Speaker
And I think that Windows and I think that you know everyone, Mac, went all the big players can learn about it. Just put it in a text file in a folder and I will trust it more. But if you hold it in the cloud, I don't trust i don't trust you if I can't see the file.
00:27:38
Speaker
I'm curious what you think about that. i I like it. I mean, i think it's it's it's worth looking at why Cloud has become so popular so quickly to the point that it it is and how it's pulling in so many different people, not just software engineers, but non-software engineers as well. And all all built one by one person who is scratching their itch to have this like you know like this imaginary future assistant that can do all of these things.
00:28:03
Speaker
So like i I'm just mostly fascinated by, like first of all, like It gives me a little bit of hope into software engineering as a whole. So Peter is has was an amazing software engineer before yeah he built PSPDFKit. And then he just took a very long break.
00:28:19
Speaker
And he came back and he started to obsessively you know create stuff. He built a lot of different projects. There was one form where you could remotely run your agent from your phone on your server, this kind of stuff.
00:28:30
Speaker
And if I look at Claudebot, he... you know we talk a lot There's a lot of talk about Vibe coding, what happens with software engineering now that the AI can write all the code, which which he is letting AI write all the code. He uses codecs, I believe, because he likes the long-running tasks.
00:28:44
Speaker
And he But when I talk with him, the crazy thing about it he keeps the architecture so much in his head. He is so opinionated about how to build it. He refactors all the time.
00:28:55
Speaker
And when I talked with him, I felt like this is a software engineer, an architect who is this is this is his baby. Like he's still he's the one merging all of the pull requests single handedly. Really? That's also what, yeah. Well, I think he might have like one or two people helping, but for the most part, it's just him. See, if you juxtapose that with the enthusiasm around Ralph Loops and autonomy and agents that do the merging itself, it's interesting that here's a person who's obsessive about what he wants CloudBot to do.
00:29:22
Speaker
He's obsessive about its tasks. He's vibe coding all of it, but then he's also curating each pull request manually and not and going in. Pete actually says he doesn't believe in the Rolf idea. he He thinks that's just like you you've not given the prompts. He spends a lot of time, a lot. So he runs about five or six or seven parallel agents. He spends a lot of time with each of them planning.
00:29:41
Speaker
He asks them about this, what about that? And when he's happy with the plan, it's a bit like a tech lead. He says, okay, go and do it. And then he likes Codex because Codex will go and it will work away up to like an hour or even longer sometimes.
00:29:53
Speaker
And so like and if if I look at success, I think i think this is where, like let's look at the output. Claude is clearly popular. It's hitting a nerve, and it's evolving with people. And it does have a personality and a taste, and it's consistent.
00:30:06
Speaker
I'd love to see. um you talking Claude Opus or Claude Bot? Sorry, Claude Bot. ah Yeah, and now now it's called Mold Bot. He just renamed it because ah like it was getting confusing and entroffing. Oh, wow. He renamed it Yeah, that was today.
00:30:17
Speaker
It's called Mold Bot. So it's still the crab, the crab bot, the Mold Bot. So like he built a product this way where he isn't one person is in charge, one person is kind of the architect.
00:30:28
Speaker
And I would just love to see a successful Ralph project, which is also successful. People like it where the AI went off and did it. i I don't have an example yet, which does not mean it does not exist. But I'd love to see if... you know like We're in an age where I'm sure eventually something will pop up. But to me, Ralph seems a little bit like, I'm kind of lazy. Let me see if the AI can do and make all the decisions.
00:30:49
Speaker
And as a... professional, I would like to think that it makes a difference with sitting behind the drive the the the wheel and you know like and like doing this. And we'll see if if this will be more of a self-driving thing where you know like after a while when the car is doing good enough job, it doesn't really matter that you're behind it. or But but it but if because the the roads are so well mapped ah and and the streets are so well known, but if it's rough terrain,
00:31:17
Speaker
I remember I was in Mongolia where the roads are very, very rough and we were going on on rough terrain. And this driver was insane on how they drove. it To me, it all looked the same, but sometimes we were doing crazy turns and then you realize that he saw the like he saw the land that that would be mushy. He saw the riverbeds that go around. This is an expert.
00:31:38
Speaker
and And it's an expert. And I'm sure that expert can also use, like some sometimes he'll holdll like turn on or or use assists as well. But I, you know I love creating software. I used to say that I loved coding and I'm not sure that's true, that ever was true. I think I learned to to like it. and i loved being good at it.
00:31:58
Speaker
I loved that few people could do it. i i so I still kind of love when I do stuff with code that no one can do. When we go to the movie theater, ah the website does not allow you to book a ticket that is that has one seat in between.
00:32:11
Speaker
Well, guess what? It's a JavaScript only side trick. And I figured out it pretty early. I literally hit that yesterday where I did not want to sit next to random people. Yeah, so it's a client-side thing, and I can go around it, and everyone in my friend group knows me, and sometimes people ask me to do it for them, and it makes me feel special. Out of the 10 or 20 immediate people I know, one else can do it, and it's not a big deal. You just open DevTools, you figure out which class it is, you place a breakpoint, and then you override the variable, right? But you know what I mean? And that's what I mean. I would like to think that
00:32:47
Speaker
I think we'll have an identity crisis where we already are a software engineer, figuring out, okay, if AI can write all these things, what makes us special? But I think there is something much more than coding that makes us special. And I think we should cultivate that. And that's why I love what Peter is doing, which is like, he is in charge. He is the architect. He has a taste. And that's why I'm not a huge fan of like, let's give it to Ralph.
00:33:05
Speaker
You just nailed it though. And I love that you said it without me having to say it because you, the word is taste. Yep. The word is taste. He has a perspective. I would love to chat with him sometime because I appreciate when someone has a perspective, whether it be ah DHH on Rails, it was opinionated.
00:33:24
Speaker
If it's David Fowler on Aspire, he's got an opinion. I disagree on the Ralph thing, though, because it's not all or nothing. Because David Fowler, distinguished engineer on.NET and architect of Aspire, is a great example. He would never...
00:33:40
Speaker
architect the aspire orchestrator with a ralph loop however they had four or five hundred bugs that were all reported and they couldn't confirm that they were real bugs so he ran a ralph loop which i just think of being a really tenacious loop it's just an infinitely patient junior engineer i would never put an infinitely patient junior engineer on an architecture problem But he went and he said, hey, go and look at these 400 bugs and reproduce them.
00:34:08
Speaker
And I think it reproduced like 368 of them and then added context. It was literally the very definition of toil. That's what a Ralph loop is for. But I don't think a million monkeys and a million keyboards could create something may amazing. Like they always say that an infinite number of monkeys and an infinite, they could they could make Shakespeare.
00:34:29
Speaker
But they need good taste. I think you're right in the sense that I, you where everything is so new, like i feel as a professional, as an engineer, the engineering mindset is like, look, we've got this new thing.
00:34:41
Speaker
Like, you know, like the the kind of, Well, we have a new hammer, right? Is everything a nail? and New hammer, but like i'm at like the kind of the amateur approach is like, you're kind of wow, this is so cool. Oh my gosh. or Or the novice is like, it's magic. It can do all these things. And the engine mindset is cool.
00:34:57
Speaker
What are the limits? How well does this work? When does it work? How far can I go? And I think that's that's what we need to figure out. Like, it's like, okay, well, how can we use it? When does it work? Ralph, that's an interesting technique, which is what you said. like when When is it a great use?
00:35:11
Speaker
When has it been? And you just add it to your your tool set. And then you figure out which ones to use based on the problem, based on honestly your mood and your energy levels and what you want to get out of it.
00:35:21
Speaker
There's also this thing, like you know when you use AI, you you give up do you actually want to learn about a problem? Cloud Code hat has a a mode where it it can actually challenge you and it gives you tasks. I tried to use it and it looks like a good idea, but it didn't really work. But it's like, how much do I want to learn about a topic? Because then I will... be more involved versus if it's routine and toil.
00:35:40
Speaker
And yeah, I feel like as as professionals, like the best thing anyone can do is use all these things, learn them, have firsthand experience, do not believe what you read on the internet or validate it because you want to have those strong opinions. And then, you know, you have this, like your tool set has gotten bigger. if If you have a bunch of 20 years of experience, you already have a long tool set, add some more tools. if you If you have less experience, add these tools and get really good at them. And you're going to add a lot more as you go.
00:36:05
Speaker
Well, and that's going to be a problem because people who are in curious are going to become not just in curious, but ultimately just quite lazy. if If you don't want to learn more, if you just want to get it done, then it's no disrespect to the Swedes. It's kind of Ikea furniture. Yeah.
00:36:23
Speaker
ah versus bespoke furniture. like What kind of a craftsperson do you want to be? And that's going to be challenging. Do you want to just get from point A to point B, or do you want to learn how the engine operates? Now, what book have you grabbed off of the Gergely bookshelf? and this was like when When you say, ah you know like if if you're not learning, the best example of this is Chip Huyen, who wrote the book AI Engineering.
00:36:46
Speaker
okay And I had her on on on the podcast as well. And one of the most surprising things, so so she is one of the biggest experts on AI engineering and and how to like build these tools, how you use RAG and and embeddings and all these things. And it's an amazing book. like if if If you're doing anything with LMS or want to do, just read it, get it. It's such a great great investment.
00:37:06
Speaker
One of the surprising things I had is she had this really nice graph in the book that I'm showing that shows the cumulative GitHub repositories based on... Explosion. based based on what types of, if if they're applications, AI engineering model report infrastructure, and there's 900 repositories over a nice thing, and over like a few years. And so she's kind of seeing showing showing trends. And I asked her, like cool, like how what kind of AI did you use to like categorize these 900 repositories? She said, I didn't use an AI, and I did it by hand.
00:37:35
Speaker
was like, hold on, hold on, hold on. This is an AI engineering book. By hand by hand or by for loop by hand? she she said she manually categorized them for the most part. And said, like, why would you do manual? She said, like, one of the most underrated things in ML engineering is that you want to put manual work up front because it gets you better results. And she said that manual work is underrated for a few reasons. You will have better quality data.
00:38:00
Speaker
You will also learn a bit more. And then when you figure out the patterns, you do automate some things. But she said that people working in and ML engineering do actually not shy away from from manual work because it makes the end result better.
00:38:13
Speaker
So like to me, this is just a reminder, if you use AI for anything automation, it can do all all these things. Like the people I think will be a lot more successful professionally are the ones who do not shy away from doing to start by doing manual work at first and only then move to automating it when you're like sick and tired of it.
00:38:31
Speaker
Yes, that's a great point. like you have to You have to do the thing and then say, okay, now i want to I want to perfect the thing and now I want to package it up and do it at scale.
00:38:42
Speaker
I do feel like this reminds me, we were talking before we started recording about kind of like our sense of history and like you know having done this for 10, 20, 30 years, there's inflection points. And I've experienced four.
00:38:55
Speaker
And I'm curious what you think about this. when we and When I started in Assembler, I would have neckbeards. non-gender specific neckbeards, just people who are old programmers say, you don't want to use c That's for the weak. Real programmers you know poke it directly into a register.
00:39:11
Speaker
And then there was IntelliSense. I literally had people tell me that you know syntax highlighting would rot your brain. And you know don't let it auto-complete. yeah That was one. Then there was the stack overflow moment where we just started copy-pasting directly into production. oh yeah And now we're experiencing the death of the death of coding.
00:39:29
Speaker
And people think that means it's the death of the craft because we've suddenly got a power tool that knows how to like, it's like when you see those tick talks where they can like rip up an entire tree and chop it up into boards instead of like cutting it down.
00:39:43
Speaker
ah In the, in the U S we have this thing called the Yankee workshop, where it's like a man alone in his kind of like Amish barn with just like a planing tool. And he just does it the old fashioned way. And that's why I try to like build silly robots and make Commodore 64s. And, you know, I saw the Primogen writing a VI for C64. Like we're going to see a return to bespoke software for fun and interesting and unique and creative work.
00:40:08
Speaker
But I don't want to make another React database like text boxes over data. So toil, I am willing to give up if it frees up time to do interesting craftsperson work.
00:40:19
Speaker
Yeah, I think like these inflection points are real. And I've seen all of them except for the assembly. I've only heard about that one. But when I joined the workforce, I was using ReSharper and highlighting it. Oh, wow. all the old the old the The old timers were like, this is going to... like' I remember when ReSharper came out. I i was this at and then i was the generation that was dissing people for using Stack Overflow. Because I'm like, you don't need that. And it's it's inaccurate and all that. So I was kind of already by you know i only a few years experience. But this is...
00:40:49
Speaker
you know like There's a few things. In the industry, in industry like people surprisingly don't like change, even though the industry has been about change. But after a few stable years, people forget about it and they get good at it and they're very resistant to this and it's hard to get rid of. If you've gone to a few cycles, it's a bit easier. So you know anyone who's feeling bad about this change, like don't worry, it's going to happen in 5-10 years again. So might as well just get used to that.
00:41:12
Speaker
what yeah What does it say? The only thing that is constant is change. yeahp But I do think a big thing that will change, and and I have seen this play out as well with the inflection points, your typical software engineer changes a lot.
00:41:26
Speaker
In the early 2000s when I entered the field, the top software engineers, the top software developers were antisocial but brilliant. They were brilliant jerks. They were assholes. But they were highly respected, at least in the companies that I worked at, because they were the ones who could wrangle all this code and they they could they could fix the bugs.
00:41:43
Speaker
And they would hoard knowledge, but they were highly paid, highly respected. As time progressed and you know we had Stack Overflow and it became a bit easier to to onboard, it became easier to figure out the maybe maybe the code. like I think those people still got value, but people who are a bit more social and collaborative started to get become a little bit more valued.
00:42:03
Speaker
Now that we had the internet, conferences, online forums, so you know like including Stack Overflow, the people who started to be valued by, I think the top tech companies were both like really good software engineers, but also kind of good at teamwork, collaboration. Well, it's humans in the loop. We keep hearing humans in the loop. in the loop Like we never should have tolerated brilliant assholes.
00:42:27
Speaker
Yep. And fortunately, many of the brilliant assholes, and we won't speak their names, have have recognized that and in their older age become quite pleasant people that acknowledge that if you're not making software for people, whether it be yourself or your family or your friends, or to make someone's life better, then what do you even...
00:42:46
Speaker
What are you even doing? In some of the recent job adverts of like modern companies that are doing a bunch of AI stuff, I no longer see technologies listed, but I do see, for example, empathy for customers. I see a lot more soft skills being listed. like If you reach a search for product engineer at any company that has raised funding, a VC-funded company that raised funding in the last like one or two years,
00:43:10
Speaker
And it's it's almost like it's describing this really pleasant colleague. And I've talked with some of these companies and how they hire, and they reject a lot based on soft skills, on on not being open enough. And a lot of the, because a lot of the work has become, is becoming software engineers talk with customers. They sit up with meetings with them. They ask like, how are you using that? Like, oh, that's interesting. Can you tell me more?
00:43:32
Speaker
And this is a brand new but a brand new persona that was not a developer. like This used to be a project manager or product manager back in the day. So I think the profession is changing where where what is valued is is changing. Because again, i and I think it goes back to like back in the 60s, 70s, 80s, there were so few people who could understand how to write that really, really difficult assembly code.
00:43:57
Speaker
And then of course, see and all those things. And some of the personalities were as they were. I mean, it it just happens. But now there's so many more people everyone can write code with with with AI, but now we need people who can still engineer, who are empathetic, and can do all these other things as well. So it's it's interesting to see how the profession changes. And I think it's really worth paying attention. like If you're in this industry, pay attention to to what's happening and see if you're lacking some of those skills. Get those get that experience. like If you have a few years experience, you're in the industry, congratulations. like That's great, because it's hard it's harder and hard to get into the industry. If you're not yet in the industry, know that these things will will also become valuable.
00:44:35
Speaker
That is a great place to end because it is a very pragmatic perspective. And as you are the pragmatic engineer, I appreciate you offering your perspective and spending so much time with me today.
00:44:46
Speaker
It was great, Scott. Thanks very much. Thank you. You can check out more of Gurge at pragmaticengineer.com. You can subscribe to the number one technology newsletter on Substack. This has been another episode of Hansel Minutes, and we'll see you again next week.