# AI Coding Inflection: Opus 4.5 and Developer Evolution

**Podcast:** The Changelog: Software Development, Open Source
**Published:** 2026-02-27

## Transcript

Well, friends, the end is here.
Not the end of the show, but the end of a fantastic partnership.
I started the Change Law back in 2009 with Win Netherland, and the show has been a beloved breakout ever since.
In 2012, Wynne stepped away to lead GitHub's API, so I had to reinvent what the change law was.
That same year, Jared joined as a contributor and guest on the podcast.
Eventually, it made sense for him to join as a full-time host with me.
I grew into a business partnership where Jared joined as a part in the business and managing editor, and the rest is kind of history.
Without going into too much detail, late last year it made the most sense to part ways.
No drama, no issues.
We remain friends.
Just time for change.
And this week is the week of that change.
Today I am solo once again on this podcast, and of course, I am reinventing what it is we do here.
For now, it'll be more the same, but in the near future, expect change.
Good change.
In the meantime, you can join the community at changelaw.com slash community.
It is free to join.
Hang with us in Zulu chat.
It's a ton of fun.
And to my dear friend Jared, you will be missed.
Thank you so much for the many laughs and all the good times and just everything.
Friends forever.
Alright, let's do the show.
Welcome back.
This is the changelog.
I'm Adam Stakoviak, editor-in-chief here at Changelaw.com.
And today, I'm joined by Burke Holland from the GitHub Copilot team, and we're talking about how Opus 4.5 changed everything.
This is coming straight from a post Burke shared in January, just after the AI holiday high we were all on from the generous 2x usage bump with Claude and the major step function Opus 4.5 offered.
Burke and I get into all the details.
But GPT 5.3 Codex is certainly living up to the hype.
A massive thank you to our friends and our partners over at Fly.io.
That is the home of Changelaw.com.
Learn more at Fly.io.
Alright, let's do this.
I'm a fan.
I use Augie on the daily.
It's one of my daily drivers.
Now I use Claude Code, I use Augment Augie.
And I also use AMP code and others, but Augie, I keep going back to it.
And here's where I'm at.
I feel like not enough of our audience knows about Augment Code.
Not enough about Augie, the CLI.
It's amazing.
I love it.
What can you share?
Yeah, we often say Augment is the best coding assistant you've never heard of.
And that's both frustrating as someone that works there and it's like very proud of the work we've done, but also like inspiring.
Like we want to go and and sort of punch above our weight because like we aren't anthropic and we aren't open AI.
And so the quality of the product itself, you know, with our context engine, once you do touch it, people are like just blown away by that.
And so, like that keeps me going every day.
So, not to bear the lead here, but this is a paid spot.
You are sponsoring this show to get this awareness.
Now, at the same time, we're selective, and I love to use your tool.
But there is in the world, so a lot of developers look at the space and they say, Okay, well, how long can this work?
How long is this sustainable in the case of Cursor or Windsurf, or you pick the name and you think discounted tokens, help me shape a lens for our audience?
I think it's a lot of awareness, right?
Like, um, Cursor got a lot of um publicity early on for like fast revenue growth, which well deserved.
I think, you know, frankly, some of the media got this gets the story wrong in that like if I gave you a dollar fifty for every dollar you sent me, I'd be the fastest growing startup in the in the valley.
And so when you're selling discounted tokens, yes, of course you're gonna grow very fast, but all that money plus more goes to the model providers.
So I think the real story is the story of anthropic and you know, being an API provider.
I think the market has just moved so fast, and there's so many pieces of competition out there that it's just hard to get noticed.
So, friends, I love augment code and I love using Augie, and I highly recommend you use it.
I love using Augie.
I can hand Augie a well-defined specification, a well-defined pep, as I call them in my world, an agent flow, and it executes flawlessly.
So the cool thing about Aug that I love most really is that context engine, and I can hand it a task, and it can just churn away on my well-defined plan and just never bother me and accomplish the mission.
It is so cool leveraging the latest models, the context engine, and all the fun things behind the scenes in that awesome CLI.
So, yes, go try it out, augmentcode.com.
Right in the top there is a CLI icon, a terminal icon.
Click that, install it, and change your world.
It's gonna be awesome.
Augmentcode.com.
Well, friends, we're here with Burke Holland, a dear friend, finally on the pod.
We can't tell if you've been to the podcast before, Bert, but you know what?
I'm glad you're here.
You work for Microsoft, working on the GitHub team, running co-pilot.
And uh, you know, I just I just don't know.
This is a crazy world we're in.
You know, what sparked this idea was actually Jared, who's since retired from the podcast, but you you shared a post, one of the most recent posts, but not you're not an avid blogger.
Other than that.
Uh January 5th, Opus 4.5 is going to change everything.
Yeah, and that was January 5th.
And obviously, you know, today is February 25th.
A lot's changed in those two months.
What do you think?
Yeah, so just a quick rejoinder on the intro there.
I I I work on GitHub Copilot.
Um, but it that's a massive product surface area.
There's the cloud coding agent, there's the CLI, and there's Visual Studio Code, and there's Code Review, and there's the STK.
There's like there's so many different teams working on it.
So I I'm I work in developer relations and I work across those different groups.
But so um, yeah, am I not?
I'm not an avid blogger, am I?
I think I I think I do more video now.
I do.
Well, you're like, you know, I'm I'm uh I haven't posted in a while, and here comes a major.
That's how I wanted to frame like you hadn't posted in about a year.
Uh you do post quite frequently, other than that, but it was like a year gap, and then you're like, listen, Opus 4.5 is changing everything.
Well, bam.
Yeah, I saw that.
And then it uh well, I mean, I yeah, that's what happened.
I saw that it went to uh it was on the front of Hacker News.
I was like, that's whenever you blog, this happened to me maybe two or three times in my career, and something like that happens, it's not the post you think, right?
Yeah, you just sort of throw something up.
Would you have written it differently given the attention it's a good one?
Of course, yeah, of course.
Right.
Like if you go in, there's this big like disclaimer at the top that was added after the fact that just like is essentially everything I wish I had said coming out of the gate.
Uh but yeah, let's talk about that.
I mean, I so there's this inflection point around right around December, and everybody knows that this is true.
Like I I'm intrinsically, people can just they just I'm not sure everybody knows, Burke, honestly.
I think a lot of people who are the inner circles know this, but I'm having conversations they're like, you used AI to do that.
Why?
No one wants to use AI.
AI is, you know, this or that.
And you and I, and a lot of people in this audience are in the know, and some of them are actually like, I don't know, you know, so maybe not everybody knows.
Not everybody knows, I don't think.
Yeah, so let's let's add some context there.
So I've been working on GitHub Copilot for years, for literally for years.
So I've been with it since GPT 4.1, which is kind of like the first model we got, and actually created a custom chat mode called Beast Mode, which would just get 4.1 to like do things, like just to get the model to do something instead of telling you it was going to do something and then not doing anything at all.
And and and then we the model started to get better, and then we got Sonnet 3.5, and Sonnet 3.5 was like I mean, it was crazy, right?
People were building all kinds of stuff with it.
Yeah, it would actually do the thing, and it would build you a nice purple gradient website every single time.
But the but the point is that like it could do a lot, but it was a really sloppy model.
Um, like it just would generate a lot of spaghetti code.
Sonnet models are super eager, so they want to please you, and so they end up just doing just running kind of willy-nilly through your code base.
But they will build things agentically.
When we say agentically, we mean like the agent is like calling tools, it's running terminal commands, it's looking stuff up on the internet, it's acting like a developer.
But the problem was, you know, even for us from where I was sitting, I could see that like it would get you to like a demo or a prototype, but then it's like you couldn't, then it would get stuck on an error, and then you had a problem because it doesn't understand the error, and neither do you because you didn't write that code.
And that's a that's that's a problem.
You can't really sit in both spaces.
You can't like have an agent that is half right half the time.
You need it to be like all right all the time, ideally.
And so in December, well, it was November, December, I forget.
Um, Enthropic releases this model called Opus, which they've had Opus for a while, but they release Opus 4.5.
And it's because my job is to like test these things out, and like, what does this tool do?
How does this model work?
I'm testing out Opus 4.5 over the Christmas break.
And the first thing that I did was I tried to, I was building like native Windows tools.
I tried to build a tool that would allow me to resize Windows on Windows to a specific width and height.
Like I'm just testing models inside of Visual Studio Code with Copilot, and it just one shots it.
Just one shots it.
And I was like, what the heck?
And not only did it one shot it, but it used native win UI libraries and it just did it right, right?
And then I'm going through and I'm looking at the code, and I'm like, this is really well structured.
Right?
It's not, it's not perfect, but it looks really good.
And I and the model's thinking is clear.
And I was like, that's that's nuts.
Uh and so then I built another tool that it was like, let's capture part of the screen and then turn it into a gift.
So like, you know, for sharing on Twitter and things like that.
So I did that and it one shotted that.
And I was like, well, shoot, I wonder if I could just like turn this into a complete screen video editing tool, like snag it or something like that.
And I did in the course of like, I don't know, a couple hours, right?
I was able to build something that functioned approximately.
Approximately not product label, but it worked.
It worked, exactly.
And it's like that that's just that's just nuts.
Like when you think about all and all I'm doing is prompting the model.
I don't, it's there's no special workflows happening here.
It's just me telling the model what I want, brainstorming with it a little bit, and then he goes off and does the thing.
So when we went into the Christmas break, I was like, I was pretty confident that I could actually build useful things.
And my wife owns a small business.
Um, people who are listening to this put to the pod may have seen this before, but like if you're in the US, you may have driven by houses, and there's like a big happy birthday sign in the front yard.
It's like different letters.
Have you seen this?
You may have seen this.
Yeah, yeah.
I'm in Texas, so we do things like that in Texas.
Okay, we have a big front yards.
Yeah, so yeah.
So it's a franchise, and she owns that franchise for our city uh in Tennessee.
And so she has a lot of it's called Card My Yard is the name of the company.
Yeah, yeah.
Um, yeah, cardmyyard.com.
Go order a sign for your There you go.
Do it up for your for your kid's birthday uh or your dog's birthday, it doesn't matter.
Uh okay.
So she has I I build all these little apps for her, and these little like there's her entire business runs on a Raspberry Pi.
No way.
Yeah.
And it does things like it.
She gets orders in her email and it prints them out for her and stuff like that.
But one of the things that they wanted people to do that the franchise wants people to do is to like get on Facebook and post pictures of the signs that people have put out in yards along with a caption.
And like running a page for a small business is inherently marketing slop, as it were.
But it's like it's a pain.
People don't want to do it, and she doesn't want to do it, right?
So she has no Facebook presence at all.
And I was like, this is so automatable because of the nature of what it's doing.
It's posting a picture of a sign, describing what's in the sign, and then saying like happy birthday or something like that.
So I built in an afternoon, I built an iOS app for her that does exactly that.
It just allows her to upload as many pictures as she wants, and then it uses the Gemini, uses Gemini to look at the images and generate captions.
And then she can tweak the captions, and then all of that is saved, and so each time the model is called, it's like, oh, by the way, these are the last 10 captions that the user accepted.
So they like it when it looks like this, right?
And so it's it's mixing it up.
And so I did that inside of an afternoon.
What was crazy about that is I had tried to build that app like a year ago at night.
I was spending like two or three hours a night using AI, and I got like 80% of the way there and could not get it over the finish line.
And I did it in an afternoon with Opus.
And then I built another app for her that just replaced an app that she used for driving where it would route to the different stops that she has when she goes out to set up signs.
So she's paying for that.
Yeah.
Um, the SAS killer around here before, like this is an example of were you paying for an application before that driving one where she paid for something and then you replaced it with something that she's gonna do.
That's exactly what we did.
Oh my gosh, yeah.
Yeah, and of course, because it's personal software, it's not distributed through the app store, it's just loaded straight to her phone because I can do that.
So this was when I I just had this moment of I'm just sitting here like, well, like I can do anything at right now, right?
Like, what is this?
Doing for the world, right?
Totally.
And I thought that I was discovering something that nobody else knew about when I was doing this on my own.
Only I know, but no, that's not at all.
Over December, like Claude code usage just skyrocketed because everybody's figured this out.
2X used, I believe, over the Christmas holiday as well.
So let me that that helped out uh a ton, just to be like, if you've got the $20 plan or the low plan, then you got like uh effectively $100 plan, you got max limits in a way.
And if you had the $200 plan, the max the true max plan, I believe like the sky was literally the limit.
You could not reach the upper bound of that.
Now the context window is still a uh a deafening factor, of course, but usage limits overall across the model daily weekly was was quite high.
Yeah, and they still are, right?
Like if you're paying, so in for co-pilot, you can pay so co-pilot regardless of what people think about it, um, is the best deal on going but by an enormous margin.
So it's like 40 bucks a month, and you get it, it's it's premium request based, it's request-based billing right now.
So if you if you do one request and that request does 6,000 things, that's just one request.
You just paid for one request and you have 1500 of those a month for a claude code, even at $200 a month, right?
You can beat that thing up to the tune of like a billion tokens a month.
I mean, that's like, I don't know, the cut their cost on that is like $25,000, and your cost is $200 bucks.
It's just the subsidy subsidization that is happening right now is wild, and it won't be around forever.
It can't be, or we're gonna have to figure out how to make clean, cheap energy in a hurry.
Either that or it's gonna get real expensive to build with models at some point in the future.
Yeah.
I don't know.
I have no idea.
Yeah, this is a really interesting thing because we have a lot of angles.
We have, you know, you and me and everyone else in the holiday break, uh, literally being flabbergasted at what we can do.
Weeks prior to that, hitting walls, hitting errors, hitting hurdles, not being able to really ship something of high quality with AI to then using Opus 4.5 and just literally opening our eyes to be like, that thing just did everything I asked and more.
Uh, and not being able to believe that.
Then you got energy concerns, obviously, is in there.
But now the status quo is this level of AI and assisted development that high performance teams are now like super high performance teams.
The front, the lowest rung of developer is now high performance.
And so the status quo now is high performance, but it comes at a cost.
You have to pay to be a developer, maybe, or to build software, you're gonna want to use this kind of tooling because it's gonna keep getting better and better.
I think the concern I have is this toll booth.
I'm enjoying the benefits of what we're all using right now.
But the concern I have is the toll booth that to be a developer, you have to pay enormous amounts of money or have maybe Eve, you know, even several team members that are high performance team members to do the things that are now the benchmark of the marketplace and industry because the bar has just risen so high.
What do you think about that?
Uh I mean, I think that you still need to be a really high performing developer to be able to actually ship.
And the reason for that is that you need to understand a lot about architecture and security and how an app actually gets to production.
The coding something is easy.
Code has never been the hard part.
That's always been the easy part, honestly, if we're being.
How do you understand what a REST API is if you don't understand how to call that REST API or how it's consumed underneath?
And the only way to really understand all these levels of abstraction, but it but the second that that comes out of my mouth, I'm like, yeah, but at some point you had to understand what the compiler was doing, and you don't anymore.
I don't know what the compiler does, nor do I care.
So as you said, like we don't know where all this is going, but I don't think that like you couldn't bring a non-technical person in and just drop them inside of an AI tool and be like, do it, unless it was like V0 or something for Vercell, where it's really abstracting.
Um, but to actually ship a piece of software, no, you still need to be a dev.
I think that for your high performing devs, I actually wonder about this.
Because the thing is, like in the past, your really high performing devs are people that could do things like um build very complex algorithms to solve speed problems, sorry, performance issues, et cetera.
But AI is really good at that, right?
Like it knows all the algorithms.
Um, it can just destroy leak code.
So I'm unsure at this point if that's really the case, other than that you need to know what to ask for a lot of times.
Um, like you may need to know that you need a binary search at this point, right?
And and to be able to direct the AI and say, why don't we do why don't we do a binary search here and see if that's faster?
You don't have to implement, you don't have to know what that is, how that's implemented.
That's not your problem.
But it is your problem to understand the con the conceptual nature there.
I think concepts is a bigger thing to learn.
I'm not saying nay against learning the code as we've known it, like boot camp level kind of thing, or even a hackathon, you go and go to a hackathon because somebody says it's cool, and then you get hooked on software development.
I'm not saying nay to that, but I think if you can conceptually understand even things like ETL pipelines, like even that, I'm using ETL pipelines never before.
Before December, November last year, never.
Knew what they were, knew how they were utilized, but my ETL pipeline is not exactly the definition of extract transform load, but it's a version of take something from here, have a silver layer or have a bronze layer, then transform it into a silver layer and then have a final production to goal, which is the Medaya method.
And I didn't even know that until AI taught me it.
It's like, hey, what we're doing here is.
Oh, you learned like via brainstorm.
Yeah.
Yeah.
Well, because I knew about ETL as a concept, and then when it explained it to me, I'm like, you know, there's gotta be a better way.
And I'm like, yeah, we should build a pipeline.
I'm like, okay, let's talk about that.
And then I I learned about Medaya method, which is the bronze silver gold kind of process to an ETEL pipeline.
And I as a practitioner, I began to learn more.
Now I'm really well versed in it, but before that, I had only understood it as a concept.
And so I was using a concept to drive the direction, which then taught me through iteration, and now it's, you know, table stakes.
It's too easy now.
Yeah, that's a really good point.
I somebody had made this point, I think I've made this point before that like my fear was oh, we're all gonna stop coding and just prompt AIs and we're all gonna get dumber because no one is gonna know what they're doing anymore.
Because uh if you don't use it, you lose it kind of thing.
But that's not what that's not what's happening.
What's actually happening is that, like you said, I'm learning all sorts of concepts that I never would have learned before.
The world is expanded versus contract.
Correct.
That's exactly right.
So instead of being overly focused on like how do I compose this function, it's like who cares?
Do you know what a Unix socket is and how cool that is and how that works in Go?
I didn't last week, but I do now.
All right, that's that's a wild, and so I think that like as the people who are using AI are getting this knock on effect benefit that no one really realizes, where they're just learning at an accelerated rate.
Yeah.
Because they are they've let go of how whether or not this needs to be an if or a ternary or whether I should abstract this out to a different file.
Who cares?
Yeah.
Take us into, I suppose, more of your world.
You know, for one, you work for Microsoft, you're playing with other people's models, that's a thing.
But tell me how your practices to build something has changed.
Like what specifically has changed step by step.
Uh I mean, part of what I do is try to figure out the workflows that developers actually need to be successful.
And there's sort of two different ways to do this.
When you're teaching someone, you really want to start like greenfield and simple.
But in the real world, it isn't like that.
It's more complex.
So let's talk about like the first one first, and we'll talk about the second.
So for my greenfield projects, I've experimented a lot with composing workflows that allow me to get from okay, I have nothing, and I want to get to this end point.
What are the things that I need to do along the way, and how involved do I need to be?
Because you have all these different, you have the agentic tool itself, whether that's VS Code or the Copilot CLI, and then you have or others, sorry, right?
Cursor, Claude Code, there's many others.
Um, and then you have like MCP servers, which is how your agent can talk to GitHub or how it can talk to Figma, or and then you have skills, which have serious overlap with MCP servers, and then you have instruction files, and then you have custom agents, which is you basically just overriding the agent behavior and defining workflows, and it's all very confusing for people because they don't know, they don't know what they're supposed to do with these things.
And the honest truth is that neither do the people who are building them.
Like we don't know what the future looks like.
All we can do is look at what building blocks we could create, create them, and then see how people put them together and then iterate.
That's the honest truth is that need.
And so that's what I try to do is figure out what does a workflow look like for me.
So currently my workflow is I'm I'm now fully into the Copilot CLI using it within VS Code, but I start off with a plan where I basically talk to the CLI and I tell it kind of what I'm what I want, and I'm in plan mode.
And these plan modes have gotten really, really good.
And people are like, I don't need a plan, but it's not about the plan.
That's not what you need.
What you need is the agent to think through with you all of the things that you just forgot to tell it that it needed to include in this initial prompt.
Because prompting is super hard.
Within this idea of like prompt engineering, which is just prompt engineering is just giving the model the answer that you want.
If you give it enough context, it will get the answer right and give you right.
If you were to spell out exactly what to do, it could literally build Minecraft on its own.
But you can't do that.
You're that's not, you can't put the prompt to be too big, you can't do it.
So in plan mode, you get this iteration where the agent's like, okay, cool.
Here's here's uh did you think about this?
Here's what I recommend, but here's three other options, or you can do a fourth one.
And you go through about like four or five, six loops of this, and I'm using Opus 4.6 for this.
It's incredibly good.
And then once you get to a point where you're like, yeah, that's pretty good.
Of course, you're not gonna one-shot an operating system.
But for a lot of us, we can get to sort of like an MVP and a one-shot.
So you can like one shot to MVP and then iterate from there.
So in your MVP, see that, and then in Copilot, we have something called autopilot.
And autopilot's like a Ralph loop.
You're familiar with Ralph loops?
Yes.
Where the agent is just so orchestrator, it's a Rust project.
Uh yeah.
So similar, similar concept where it will uh basically feed the agent's output back to itself.
It's just running the agent in a loop.
And it does this until the agent has some amount of confidence.
There's this idea of like if you tell agents like do this until it's done, they're like, okay, I did it, it's done.
You're like, it's not done, it isn't done.
But if you tell them do this until you have 95% confidence that it's done, then they will run and run and run and run and run, building up a confidence level.
And so a lot of that stuff's abstracted into the tool, but then I'm also like using a custom mode, a custom agent in that that I call Anvil.
And what Anvil does is it it does two major things.
The first thing that it does is it decides: like, is this a is this an easy task, a medium task, or a hard task?
Because you want different workflows from the AI depending on what those are.
Those are not, it's not the same thing.
If you ask the agent a simple question, that's an easy task, it should just answer that.
But if you give it a hard task where you need it to build something, then it really needs to plan, it needs to use sub agents, it needs to farm workout.
In GitHub Copilot, you can use different models.
So like you can use Gemini 3, 5.3 codecs, and Opus 4.6 all in the same run, and you can use as many of them as you want to.
Okay, so now we're in an orchestration scenario.
If we're let's say we're gonna do a massive refactor, it might farm out the design work to Gemini, it might farm out the refactoring to 5.3, you might have 26 subagents running.
You need to review that code.
Um, and so this is my workflow now is to try to automate all of that.
So I'm I'm planning and then I'm autopilot with my custom agent, which out the other side needs to give me something that's verifiable.
Like, how do I know that you think that this worked?
What is the evidence that you have that this worked?
And if it's in a browser, then you can use skills like the agent browser skill to have the the thing check its own work.
That's like the easiest scenario.
Like for native apps, this gets really tough.
Like, if you're building a native Mac app, how the how the heck is the agent gonna do that?
It it can't, right?
It could write unit tests, but unit tests, as we're learning, are like woefully inadequate for telling you whether or not your code actually works.
So I that's a long way of answering your question is that like I don't have all the answers.
These are just the things that I think about on a daily basis.
And then how do I further get myself out of the loop?
So if I'm sitting here babysitting the thing constantly, how can I automate what I'm doing right now?
Is it possible?
Could Adam, for instance, is it possible for me to give Copilot CLI a large job and then walk away and have it message me on Telegram and say, hey, listen, like I did this much.
I think this is what we should do next.
Let me know what you think, and then I can respond and say, Yes, do or don't do this.
And then it goes off and continues to do it.
Can it operate more as like a team lead and less as and the I think the answer is yes, but you have to have the workflows and the checks and balances set up to actually make that happen.
Now I use Squarespace personally.
I love it.
We use it on a one of our small businesses, it's amazing.
But here's one that hits closer to home for some of us.
Maybe you got friends, family, yourself, maybe even.
Maybe you're selling content.
Maybe you do consulting.
Maybe you have the desire to do content and put a paywall in front of it and make some money from different ideas you want to share.
Well, that's the gap that Squarespace fills.
It's the all-in-one platform for turning what you know into a real business, not just a website, but a way to offer services, book clients, send professional invoices, and even get paid.
It's all in one place.
Two things worth knowing.
First, offering services.
If you do consulting, workshops, coaching, freelance, speaking, dev work.
Squarespace gives you scheduling, on-brand invoicing, online payments, email marketing, all of it built right in.
No stitching together five SAS tools, just one dashboard, one way, no chasing payments in your inbox.
You set up your offerings, clients book and pay, and you get back to actual work.
Back to that AI project you're doing.
Second, selling content.
Got a course idea, maybe video tutorials, probably.
Second, maybe you're selling content.
Maybe you have a course idea, video tutorials, premium posts.
Squarespace lets you gate content behind a paywall, add value, deliver on that value, get a one-time fee or subscription, your call, and even recurring revenue from what you already know.
The platform handles the access control for you, the payments for you, the presentation for you.
And all you gotta do is bring the expertise and ideas.
Here's the next step: head to squarespace.com slash changelog for a free trial.
And when you're ready to launch, use our offer code changelog to save 10% off your first purchase of a website or a domain.
Again, squarespace.com/slash changelog.
Get that free trial, use it, enjoy it, and have fun.
That's an interesting one because recently I did a version of that.
Uh I'd been uh I'm trying to decide if I should say the brand name.
I I similar to the way you SaaS killed something for your wife, I SAS killed something for myself because I use an invoicing tool that is largely glorified email.
It's it's really just an email through a service that look that is a paying service, and they largely pay us via wire or ACH, which is not at all through the conduit of the invoicing service.
And the invoicing service is like 500 to 800 bucks a year because of the kind of clients and brands we work with.
There's a lot of them, and I just don't feel like I need to delete uh brands to kind of get back to a lower tier service.
And it's kind of like paying extra for a database just for a couple rows of brands that work with us a couple times a year, but don't need to get deleted.
All I have to say is I just kind of thought about it.
I was like, could I just build this in Rails?
Uh, because I love Rails and I actually miss Ruby a lot.
Um, could I build this in Rails?
And could I one shot this in a way?
And I was like, here's all the things I want.
And I I wrote my own list, and I handed that to uh to Claude Webb.
I call it Cloud Web, not Cloud Code.
Cloud Webb, Opus 4.6, Extended Thinking.
Hey, this is my thinking.
I'm gonna go to bed.
Give me the best prompt to get a good V1 in place.
I'm gonna hand this, and in this case, I'm gonna name drop uh to Augie because Augie is from our friends over at uh Augment Code.
They're one of our sponsors, not sponsored from this show, but one of our sponsors, and I love them.
But Augie uh is is also good at doing things on a loop with a great prompt, uh, and not have to do it in that dash dash dangerously way, if you know what I mean.
And so I can walk away happily knowing that it's not gonna arm anything or do anything negative to my system.
And so I'm like, I'm gonna hand this.
I'm literally telling Claude this, I'm gonna hand this play by play.
I'm taking what you give me, I'm gonna copy and paste it directly into Augie, let it go, and I'm gonna walk away.
Okay.
The next morning I wake up, Ledger is born.
Okay.
The next morning I have a an app that works invoices, emails, PDFs, logs in, uh all the things.
I mean, there's a couple things I could probably do to make it more production ready, but like it's the V1.
And so that's that's one thing.
The other thing is is on the Telegram front, the challenge I wonder is that there are times when I'm in those kind of loops like you are, and as a great teammate, it may have a more complex problem that I can solve in Telegram.
I may actually need to be there with it.
And I guess in that case, it might be great to know that, but it might bug me on that walk, or it might bug me on that restful step away.
So I'm kind of torn on that bug me on telegram front, but it'd be kind of nice because maybe I'm at lunch with a colleague and I'm still working and I want to be in work context.
But sometimes the thing that I have to that that sort of you know human in the loop scenario with the agent to take that next step requires deeper thinking than I can do in a telegram message, or I may need to access more tools or whatever.
And so then I might just be like, oh man, I now I got this agent anxiety again.
I gotta get back to my agent.
You know what I'm saying?
Yeah, so that's my long-winded response to you is like I one-shotted something recently out of frustration, but it wasn't a true one-shot.
It was a thoughtful, deep V1 one-shot.
It wasn't like build me a Rails app to replicate X.
It was more like, here's what I use, here's what I use about it, here's what I really care about it.
Here's all the things I don't want you to do, here's the things I do want you to do.
And I'm literally going to bed.
I just told him what I'm doing.
Came back the next morning and Ledger's born.
Yeah, I I've thought about this a lot myself, where it's like what you really want is for the agent to just work all night, like you said, and then build the thing that I want.
But the problem is it doesn't know what you want.
And you cannot get out everything because you don't know.
And that's not how software is built anyway.
In no world, is are all the requirements and constraints to find up front.
What happens instead is that you you think you know you discover it as you go.
That's right, and it changes and you make trade-offs, and the agent has to do the same thing.
And so I don't know what the answer to this is, other than whatever product you and I are replacing, currently probably has a team of devs and an engineering lead, and every Monday morning they get together in a stand-up, and maybe they have a stand-up every day where they go over all of the work that's in the backlog, what the status is on each one of those things.
And I almost wonder if that isn't the future, right?
Because you can't just hand this work off and then just walk away and expect that the agent is just magically gonna know exactly what you want.
It just doesn't.
And so, in order to really build anything of size, you'd almost have to have a daily stand-up with your agent where you go over all of the things that it's working on and review.
And that's tedious.
That's actually the part no one likes, right?
Like Chad, if you're listening to this pod, like if you're in a daily stand-up, you're like, that's I that's my least favorite part of the day.
Yeah.
I mean, I'm with you.
But there are reasons why we have processes, and that's so that we can actually build things that work.
I did something similar where I have a Ralph loop, I have Copilot CLI running in a loop, and it's building a multiplayer game where you just uh yeah, you just LARP as a baby bird, and you're hatched from an egg and you fly around, and I'm letting it, it's deciding everything.
It decides what features it should add, it decides what's engaging, it decides what bird behavior is.
And I check on it every morning, but it's just running 24-7, and it does a pass and it adds something, and then it comes back and looks to see what it could add, and it just keeps going.
Do I think that this will end in a playable, like viable piece of software?
I do not.
Right?
Probably not.
I think it will be some monster of a thing that is interesting to look at, but is not it's not something you would ship.
And from what I can tell, this is currently where we're at.
So like I I won't name names, but there are companies that have built like they sent agents off to build an entire browser, or they sent agents off to build an entire compiler.
And it's phenomenal that the agent can even do that.
Like instead of throwing stones when this happens, people should just step back and acknowledge the incredible feat that that is.
That you had a thousand agents that built a browser, that's amazing.
But to actually ship that browser, that is a whole other story.
To ship that compiler, that is a whole other story.
I don't have answers here other than to acknowledge that these are the gaps that we're currently trying to think through.
I have some verse of an answer.
Okay.
And I think this is the lens we need to take.
Because this is the lens I'm taking, and it's it's helpful to me is that not all software is created equal, right?
Just like your game is not the same kind of production level shippable, sellable, SLAable software.
Like those are not, they're still software, but they're not the same software.
The benchmarks, the requirements, the desires are totally different.
And so I think the lens we have to take is that there's a lot of naysayers like, oh, but it can't do this, or oh, it can't do that.
Well, let me just tell you like uh you even called it out in your post, Sam Altman and you know, others talking about where we're going and engineers being replaced, where we're like, nah, that ain't gonna happen.
And this year we're like, oh my gosh, it's gonna happen soon.
It might happen like three months from now, you know.
And so I think not all software is created equal.
I think versions of software will change in terms of like your toy game, and it's probably that for you, versus somebody else's browser they want to like figure out if they can actually ship.
Getting that to production, getting it to ship is way different, but it's a different kind of beast.
Even the most recent example, uh, with Cloudflare and Open Next.
Like, I don't know.
I saw that.
Did you see this?
Yeah, shout out to Steve.
I used to work with Steve here at Microsoft, the guy that wrote that that blog post.
That was a great post.
Yeah.
I mean, like, even just like the way they rolled it out was just phenomenal.
Uh, I'm excited about that because the the uptick of software getting created, the uptick of repos being created on GitHub, the uptick of all the things essentially, apps on the app store.
Uh, there's a lot.
And I think what's happening is people are learning how to build more software.
They're learning like you are about Go and WebSockets or go and how you can use a Unix socket, for example, uh, and what that does for the way you can connect and stuff like that.
I mean, RPC versus a REST API, you got GRPC, I mean.
Uh, you've got all sorts of things that are happening where you're now learning different things, and that's the explosion happening is that your world, your world and my world as well, and hopefully our audience's world is now flattened in terms of well, I can touch pretty much any piece of language or protocol or software as I'd like to because the AI the AI is getting enough better, getting better enough to take me there, and I'm learning with it.
And hopefully, you're not just simply one-shotting and praying, but you're more like iterating with it.
Because I find the most fun I'm having building software is iterating with it, learning with it, and not like it's teaching me and I'm teaching it, but more like I'm just learning through the process of an actually actually being a developer again, touching things I would have not touched a year ago, building things I wouldn't have even dreamed about, and learning along the way and iterating along the way, using iterating, using iterating.
That feedback loop for me is really just a one-person shop in that regard, because a lot of my software is just built and by me for the most part.
Yeah.
Yeah.
Somebody said the age of personal software is here, and they're 100% right.
And I think that's what most of us are doing right now.
And so, for people who are listening to this that are like skeptical, like I can't stress enough, you can build anything.
And if you're listening, thinking to yourself, no, you can't.
I've seen what AI can do.
The problem is that we've tr been trying, we've been on this sort of like hype grind for so long that we sold people like six months ago, like a year ago.
We were like, you can build software with AI, and you could, but it was tedious.
And then a year later, we're telling people like, no, no, no, no, no.
You can build software with AI, and they're like, fool me once, right?
You're not gonna fool me again.
But I don't know what to tell you besides just go, y'all, just go do it.
Like ever wanted to build a triple A game, just go do it.
Just go do it.
See if I'm wrong.
Test me and see if you can't get to something that's functional inside of an hour.
Yeah, and you can.
You really can.
Now these and really thanks to open source.
I mean, we were and maybe you could speak to this given GitHub and Copilot.
Like there was a lot of outrage on the initial in uh release of GitHub Copilot in that, oh, GitHub released this thing and it trained on all of our code.
Damn you, GitHub and all this stuff.
But then open source is still here and still I would say open source is thriving more than ever.
And there's this massive swing back to uh just simply open source and free and open tooling.
I mean, open next is the example we just led with there.
I mean, that's a great thing.
That's a good thing.
Yeah, because it's so cheap to create software now that it's nothing for you to just create something and then make it available to everyone.
Um yeah, I think until you know, as we're well, right.
Well, not the cheap side of it, but until it's not until it's not worth sharing, you know, where you want to protect your moat or build a moat.
100%.
Um, but I do think like there are emerging problems that we don't really have answers for.
So, like the VS Code is probably one of the biggest open source projects.
And I think last year, every year when we get to December, they do like a triage of the open issues, and they spend December just trying to do spring cleaning essentially to get the repo down to a manageable number and do clean up the backlog.
And it was like a year ago, it was 8,000 issues.
This year, when we went into December, they were like, okay, how many issues are we working through?
It was 15,000 issues.
Wow.
Like, this is not we have to figure out the process.
And the team is actually doing this, right?
So the VS Code team doesn't just build VS Code, they're also trying to figure out the AI processes for their own workflows that you use to create a tool which has to be reliable, it has to be fast, it has to work, it cannot go down, right?
We can't just ship a release where people are like the editor doesn't work anymore.
We can't do that.
Catastrophic.
Right.
Exactly.
And so it's a like you said, there's different kinds of software, but when we're talking about what we build for ourselves, that's one thing.
But these teams, and I was just in Radman talking with um one of the engineers, Michael Lively on the team, who's just that's what he's doing, is trying to figure out what are the workflows and putting them together so that the team can actually ship software with AI and have it remain at the quality bar that they are going to insist that it is.
We that it just has to be a non-negotiable for people.
Yeah.
We should add we should talk about like your point about our developers going to be replaced.
We should talk about that because I have I have thoughts here.
I know you do.
Let's let's do it.
So what uh what I see right now is this sentiment just keeps getting thrown out, but it isn't actually happening.
Like AI is taking jobs, but not in the sense that it's doing them, it's taking them in the sense that like if you're in tech, that is money that's being diverted to GPUs.
Everybody's investing in GPUs and not headcount.
And if you're in the enterprise, I think a lot of places are using it as an excuse to to downsize, right?
Like it's it's just being it's in it's a it's a convenient scapegoat, right?
So it but it isn't taking the job in the sense that like, oh, we don't need you because now AI does what you do.
We're not there.
Models are extremely capable.
And so I'm pessimistic that that's actually gonna be the case.
And I actually wonder if we don't end up with more developers.
But then you start to ask, well, what is a developer exactly?
And and we even have looked at this at Microsoft.
Like, am I a am I an advocate?
Am I a PM?
Am I an engineer?
Or am I all of those things?
Because I can now open if there's a a feature that's missing in VS Code, I can open an issue, or I could open a PR with three different implementations of that issue done with the AI.
And then we can either approve and say, yes, we're going to do this, or we could just be like, nope, we're not actually going to add this at this time, close it out.
What do I care?
It's a 15 minute job for me to create three different iterations.
So it's like this age of abundance where I can contribute in a place where I before didn't have the time to.
I just don't.
I have other things to do.
But now I can actually, I can contribute.
So am I an engineer?
Am I an advocate?
Am I a PM?
And I think we're going to see more of this where like, what is it exactly that the job title is, right?
Is there such a thing as just a developer anymore?
If I'm in marketing and I need to build up, I need a quick page or something.
Can I just vibe that up?
If I'm in sales, right?
And I need a system that makes it easier for me to answer questions the customers have, can I just vibe that up?
I mean, I don't know the answer here, other than to say that it seems to me that like the the AI is going to replace developers, would be better stated as like AI, everybody is going to be a developer at some level, maybe going forward.
I don't know.
Yeah.
Yeah, yeah.
I'm I'm with you on that.
I feel like calling everyone a developer is a slight challenge.
Calling everyone a builder is more plausible.
I think it comes down to why is let me push back on that a bit though, because I think that for us as developers, one of the things that we've always had over other people is that we have the knowledge and the skills that they don't have, and therefore we're worth a lot of money.
Yeah.
It's a lucrative field.
And we don't want to give that up.
We don't want to give that up if we're just being honest.
And I don't blame people for not wanting to give that up.
Doesn't make you a bad person.
But I think like we're still trying to gatekeep some concepts.
We don't want these things to be available to everyone because then if they do, then we're in an existential crisis.
I'm kind of for everyone being a builder, honestly.
Um I I'd I'd actually toy with um creating a new podcast uh focused on the idea of builder.
I was gonna call it future builder.
It was a double entendre.
It's like, you know, you're literally building the future, and it's the future builders of tomorrow is in a sense.
And it's developers today, but tomorrow it's everyone's a builder.
And I I'm not sure the world's ready for that yet.
I'm not sure I'm ready to produce that kind of show yet, but I like the idea that everyone is a builder because uh, and the reason I I feel that way, I talked to a good friend of ours, uh Damian Tanner, he runs uh Layer Code.
And we talked recently on the podcast, and one of the things we talked about was that he just in time built something for himself, and then his sales team and sales folks just in time built dashboards for themselves.
And so now you have production level software that's good for them because they're production of one, right?
They're the user of one, you know.
They're not only the builder, but they're also the user of it.
So it's good for me, it's it works.
That's all that matters.
I think that's super cool.
I want that world to exist because the more people who can build software for themselves is gonna be there's a there's a long tail upside for that.
Um whether or not, and the reason why I teeter on if they're a developer or not, is for the reasons you said before, which was they have they may miss this deep knowledge of say uh the Unix socket with Go, for example, or ETLs for me, or software development lifecycle.
They don't understand this larger, truly developer world kind of thing, and maybe that will erode over time.
And I'm fine with that too.
I I I'm mostly fine with that.
I think there's gonna be more software and more people building software.
And if we want to call them software developers, I'm cool with that.
I'm zero about gatekeeping.
In fact, I invite them all.
It's like saying it's it's no different than being anti-nubie into our world.
We've been so pro-Nubi for years and years and decades, basically, or at least this last decade, been pro-Newbi and kind of anti-calling people juniors, even.
Like there's a lot of tickets of pejorative.
I'm for everyone coming in.
I'm like a, you know, like um the one song Arms Wide Open kind of thing, you know, with arms wide open.
The creed song.
Yeah, man.
Creed all the way, man.
I love creed.
I'm a I'm a metal gems kind of guy.
Yeah, with arms wide open, come on in, come build.
It's gonna get more fun, more lively, more software is better for the world.
And I think that as this as this world evolves, as this thing evolves, we're gonna need more people to build good software, bespoke software for personal use, bespoke software for just in time, business level, functional personal software, and then truly platforms and production systems like our friends at Cloudflare just did with you know open next as an example of them using you know a thousand twelve hundred bucks to take Next from uh what it was with you know for sale only, essentially, and uh enabling VT and all the process behind that.
Like that's a different kind of thing than you are in our building, but they've got a team and some smarts and some true talent that not so much you and I don't have, but they've got some skills behind that, behind those tokens.
Yeah, you have to know a bit about what you're doing to pull that off.
If I was gonna take the other side of the argument of what I just said, it would be that the reason why we recoil at this is because to us, to because those of us that have been writing code for decades, it's a craft.
It is and I really remember what was in your post.
I did.
And when we had this big influx of people, and even my my kids, when they were in high school, they're in college now, but it was this big push, you know, that everybody should learn to code.
And like literally everybody was in these coding classes because they wanted to make a ton of money.
That's not a bad reason to want to be in to want to learn to code, but they had zero interest in the craft, right?
And that's why so many, so few of them just made it out the end of the pipeline, is because it's hard.
It's hard and it isn't fun and it's tedious, and you really have to enjoy the the craft.
And it's like AI is never gonna write code that's up to our standards because it's not a craftsman.
We're craftsmen, AI is not.
And so I do worry that we're building essentially like strip malls and tract homes, right?
Whereas, like if you go back in history in my town here, they were built the homes that they built were just beautiful.
And if you fast forward to today, they're nothing, right?
Even my house is just a brick square.
And that's fine.
I I don't want to be ungrateful, but at the same time, can we even build?
Can we build cathedrals, Adam?
Anymore?
Does anyone even know how?
I don't know that we do.
And I was so I worry that we're not we're gonna forget how to build cathedrals.
This is this should be the next blog posts.
Oh, yes.
You know, I I actually uh I agree with that sentiment because I was recently in Pittsburgh, Pennsylvania.
And if you haven't been to Pittsburgh, it is a beautiful city.
There's a lot of history there because it's one of the original 13 colonies.
There's a lot of history there.
Whereas, you know, other places are sort of new, everything's new.
California, everything's new, you know, uh, as an example.
Nothing against California, but just doesn't have the same kind of history that Pennsylvania, Ohio, or other states might have.
And I'm in downtown Pittsburgh, and there's this courthouse where they literally conduct court, and uh it's just breathtaking.
It's massive, a massive like you know, craftsman level stone building that when my wife and I and our kids were walking through Pittsburgh, we're like, we gotta go tour this thing.
No one in Pittsburgh.
Yeah, no one cares, right?
Everyone who lives there, it's like, yeah, been there, done that, seen it.
Nobody's going there.
And when my family's like, what'd you do today?
Um, we're like, uh, we toured the courthouse.
Like, why?
I'm like, because it was beautiful, it was massive, it was amazing.
Like the the level of quality of work it took to make that.
And like it was just breathtaking.
I'll throw a photo in the show notes because it's just it really is just breathtaking.
And to your butt, do you think could we do that today, right?
Like we even possess the skills.
I think we do.
There's a small margin of folks who do still have those skills.
And because it's a a um a rare skill, they can charge high dollars.
And because they can charge high dollars because it's a real ski rare skill, it happens less.
I don't think we can't do it.
I think it's become such a uh smaller minority that does that kind of craft, and for those reasons it's elevated in cost, and for those reasons it's just done less.
Yeah, you never see it because it doesn't make any sense to do it for only the hyper rich can afford it, and so only the in the unique places where the hyper rich can afford it does it take place.
For sure it happens.
It just doesn't matter.
Right, but it used to be everywhere.
That used just used to be, you know, how things got built.
A long time, right?
And it took time, it took years, decades for things to get built.
And now we can throw these things up in a matter of months, right?
Like we could if we could throw up a whole house in like less than three months.
It used to take years.
But the thing is, like the difference in the quality is unmistakable, right?
These these, and so anyway, the analogy being is that are we moving into a place where like we look at software?
I'm already at the point where people are like post stuff they built on X, and I'm like, I'm not impressed because I know what you did.
I know that because I can do it too.
And how sad is that?
I remember people used to post stuff on like hacker news about like these CSS transformations that they pulled off, and you're like, that's unbelievable.
How did you do that?
And now it's nothing.
I can write a whole JavaScript framework.
By the time this podcast is over, I could literally enter that prompt and we'd have one.
I'm not saying it would be good.
But you you see where I'm going with this, right?
It's like it's devaluing the thing.
Let's let's talk about that though.
Okay, so there's things that are incumbent in the in the marketplace.
I'm trying to think of like particular ones.
Uh like NPM, for example.
They say that NPM can't be unseated because of its ubiquity and because of its just tentacles out there.
I think we're two or three.
I mean, I guess this might actually hit closer to home because I just said NPM and I'd forgotten where you work.
Um I forget that GitHub owns that too all the time.
Okay, good.
I'm not throwing, I'm not throwing shots.
It's just my example.
But I kind of am in a way.
Because we talked about this recently was that securing GitHub, or sorry, securing NPM is table stakes.
And I I do believe that.
That's still the show we did recently with Nicholas Zacis.
Uh oh, Zekis was on the show.
He's awesome.
Yeah.
A lot of great things to say.
We talked about the details of that.
And I think we're we're a couple major security issues away, which we've already had a couple with NPM, away from an the incumbent being threatened by a newcomer.
If a newcomer came with the abilities of NPM, and maybe a couple people with the seat that have the clout to be behind X, whatever X may be, not literally X.com, but whatever X as a variable may be.
If we're a couple security issues away from NPM, having the possibility of people saying, you know what?
If there was an alternative, I'd choose it.
We're there.
We're so close to that.
There's a lot behind that.
Don't get me wrong.
There's a lot behind that.
Let me think through that.
Because I see where you're going with that, but then there the two things pop into my head.
First of all, right now, people's appetite for risk seems to be ludicrous.
Like it's just like they are open for risk, or they're not open to risk.
Yes.
They're just open to risk, right?
Even my own, right?
There's a flag that you can pass into CLI.
YOLO.
Exactly.
It's a yellow flag.
Just let the agent do whatever it wants.
Right.
Now, I have not been bitten by this yet, and there's some things that you can do to help mitigate this, but that is inherently super dangerous.
Open claw is one of the coolest things I've seen.
What a great project, right?
And you can lock it down, but you kind of have to you have to do that.
You have to lock down, say, well, only telegram, this telegram user, and then you have to test and make sure that that's actually the case.
Did that actually just happen, or did it just tell you that it did it?
And but I think that when it comes to things like NPM, one of the things that NPM has going for it is that these models are, they know so much about it.
And there's they know how to use it, they know what these modules look like.
There's all this history, it's in the training data, right?
The second that you invent something else, well, now the model doesn't know what that is.
And you can mitigate that by providing context, and maybe future iterations will know.
But it's like models are so good at using these established tools.
For instance, like um, I know I work at Microsoft, but if you want to have some fun chat, you can use Firebase.
Um, models know everything there is to know about the Firebase CLI.
So you can literally log in on your machine and then tell the agent to build something, tell it it can stand up its own fire-based services, which are free, right?
You have to physically enable billionaire.
And it can do everything, it knows how to use the Firebell Firebase CLI from front to back.
That makes it really hard for you to supplant that with something else because people are choose the path of least resistance.
That's my immediate reaction to that is that it's just too easy.
It's already there, models already know how to use it, and that makes it really, really hard to supplant it.
But then again, like we're just in a space where nobody knows anything.
No one, if you take nothing from this podcast, it's this.
Listen, chat knows.
No one knows anything.
No one knows what they're talking about.
That is the TLDR of this whole podcast.
You've said chat a couple times.
You've addressed it like chat.
What does that mean when you say that?
I think I know what you mean.
What do you mean when you say that?
Yeah, sorry.
I mean, I always I don't know.
I mean, my kids say it all the time.
Like when they're talking to their friends, they're like, hey, chat.
Well, it's like if you're a streamer and you're talking to chat.
Yeah, I think.
I don't stream on a page in my.
I understand what you mean now.
Okay, cool.
The audience, gotcha, gotcha.
Sorry, yeah, sorry, listeners.
I guess for you it'd be listeners.
Right.
Well, it's okay.
I just want to make sure I I thought I knew what you meant, uh, but then I wasn't sure if I knew exactly what you meant.
Okay, so I think here's an example.
Man, I'm trying to make sure I have the right kind of context for this.
Is there was I thought it was entire.io, but I and you know, former CEO of GitHub.
Oh, Thomas.
Come back.
But wasn't there like a uh a way to render diffs that was like re-implemented in like record time by a different uh GitHost?
And I'm just like paraphrasing that because I thought I saw some posts on a brand new diff out there.
It wasn't entire, it was something else, I believe.
Uh a new one uh it could be.
I wish I had I wish I had the context.
I don't have the I mean I know I know Reese over, I think that's how you say Reese it's R Y R H Y S.
I apologize if I'm butchering your name.
Um built faster GitHub, uh just like vibed up.
It's like really fast, super fast interface for GitHub.
So it's it's possible that that's 100% true.
I think right now, like everyone has to basically you have to take your priors and just throw them out.
Here we go.
I think I might have this context.
I think I might actually have it.
Um, yeah.
Here you go.
Uh diffs.
Check this out.
D I fancy that S.
Diffs.com.
A different rendering library.
Now I could be wrong, but I thought I saw some some posts around this.
So it's Pierre Computer Company, uh, Pierre.computer.
Uh they link out to uh code.storage, they link out to diffs.com.
Now this is burgeoning in the last week, so I'm catching up myself even on this, which is why I'm less versed in it.
Maybe next week I'll be super steeped.
But there is a uh, and somebody out there is like, Adam, shut up because you don't know what you're talking about, but this is it, okay?
The these diff styles are just amazing.
Somebody came out with this as a uh brand new startup that's been funded, and Pierre.computers that, and one of their products is diffs.com.
Now I saw I thought I saw a post that this is being implemented by folks faster than ever.
And I don't know how that really relates to to NPM, but just that you can go from the old way or a way or the known way or the incumbent way to a totally new way because it's just revolutionary, uh really well done and compatible.
So I think the one thing that may be an NPM kill, and I could be way wrong, and I could be just a pundit in this scenario, not so much somebody who's been an NPM user for many, many years.
But I think that if you can come up with if you can come up with an NPM compatible way and teach agents quickly enough, npm could be threatened.
The fact that it's that it's an incumbent and could be no different than you have S3 compatible object storage out there.
No different.
I mean, you have Tigris.
I'm a user of Tigris, Tigers.com.
Is it Tigers.com?
Tigersdata.com, I believe.
Yeah, Tigris, Tigersdata.com.
And they're S3 compatible.
They have an amazing GoSdK.
They used to have, they actually used to use the Amazon, uh, the AWS S3 CLI SDK for me to use.
And now I just use their native Go SDK just to go right to Tigris and it's S3 compatible.
So no different than you can actually compete at the object storage level with R2, which is a great example, T3, which is Tigris, or straight up S3, that you can compete on that level.
So I I don't know if being an incumbent and being not known by agents, I think you can quickly get versed in this world so fast.
Could be, yeah.
You're absolutely right.
I do think your point's well made though, that like nothing is nothing is nothing.
I don't say nothing is nothing is gonna say well, software is so cheap to create now that if you're a software company, like that the odds that somebody can re-implement what you just did on their own uh are pretty high and are not are only gonna get higher, right?
And so I don't know what that means other than to say that I don't think anyone is there is no one is safe.
Everyone is gonna have to reinvent themselves and think differently about things.
They have they're gonna we're all have to forget our prior uh assumptions about literally everything.
Yeah.
Do you have a lens?
Uh, because you probably have a lot more colleagues than I do.
I have zero now.
Uh it's just me.
Some editors, but uh, as you may know, Jerry recently retired from the show.
Uh love and the death, no ill will, no drama whatsoever, just just change.
But I'm literally a team of one now, and so I have no colleagues, but you probably have colleagues, Burke.
And so my my question is this is given you have colleagues, and maybe it's not the case here, but I'm sure somewhere in Microsoft, are there people who are sort of not so much anti-AI but resistant?
Do you have awareness of their position, their posture towards what we're going through right now?
Yeah, 100%, right?
Like, I think that there's a strong contingent of devs out there, even who are like, I would never let, you know, and they call them clankers and they call them slot machines, and they're not wrong, right?
Like these folks aren't wrong, they're really pushing back and saying, like, this is a bad idea.
I don't think this is good.
Um, and a lot of these folks are craftsmen, right?
Like they have a lot of pride and they're extremely good at what they do.
Um, but I do think that at this point it's kind of like trying to hold back the water, like you're trying to be the damn, yeah.
Believe me.
Like it's just, and so for those folks, first of all, you always need people to tell you that you're doing it wrong or that this is wrong.
You need these people on literally every issue you can think of.
If you don't have someone questioning it and saying we should not be doing this, something is wrong.
So I think that it's healthy to have that, but I do think that the inertia in the momentum here is these folks are, and I've seen a lot of them come around to where they say, like I was just um talking to uh who was it?
Uh Ryan Florence, the um who did React Router on Twitter last night, and he said, I have not written a line of code in a month and a half.
And I thought that I and and I I had responded and just said I see more and more of this.
I haven't written a line of code in quite some time, right?
And Ryan Florence is no slouch.
This guy knows what he is doing.
He's a very, very smart, and so I think that I'm just seeing more and more of these really like S-tier devs basically saying, like, AI is writing my code now.
That's what I would say to the to the people that are holdouts, is just that I understand it's a really hard time right now.
It's yeah, we don't know what's gonna happen.
Like the threat is existential.
It feels like the pandemic hit, and then everything after that has just been uncertainty on top of uncertainty.
And we just we just want to go back, but you can't go back.
It just gets worse.
No, it's here, it's it's here to stay, and it's part of me, it's like it's never been more exciting to build, and then the other part of me just grieves.
It just grieves like I you know, like I'm just it hurts, it's a loss.
And so all I can tell people who are resistant is that I understand how you feel.
It keeps me on track.
Notion agents, Notion AI, Notion, all the things.
Here's the thing: you probably spent weeks building out your team's knowledge base.
You probably wrote the onboarding docs by hand, the run books, the architecture decisions, the how we deploy guide.
Of course you did, and it's all notion, organized, searchable, beautiful, and your team still DMs you.
Hey, quick question, except it's never quick, it's not just one question, it's 10 questions.
Every interruption costs you 23 minutes of context switching.
Your productivity is going down, and your carefully documented knowledge base collects dust while your DMs are on fire and stack up.
Well, Notion is an AI-powered connected workspace for teams.
It brings all your notes, all your docs, all your projects into one space that just works seamless, flexible, powerful, and it's actually fun to use.
With AI built right in.
You spend less time switching between tools and more time creating great work.
And now with Notion's new custom agents, the busy work that used to take hours or actually never get done at all, it now runs itself.
Custom agents automate time-consuming repetitive workflows directly within your Notion workspace where your team already works, where all your knowledge base already lives.
Here's what makes them different from most AI, because most AI still waits for you to prompt it.
But custom agents run on schedules and triggers.
One person sets it up, putting a workflow for repetitive tasks like weekly reports or triaging feedback, and it becomes a shared resource for the whole team.
Think of custom agents like AI teammates with a specific job, whether it's a status update agent, a QA agent, a task routing agent, or a custom agent you've just built for your workspace.
The busy work is now handled.
And don't just take my word for it.
Notion is used by over 50% of Fortune 500 companies.
And some of the fastest growing companies like OpenAI, Ramp, Vercell, they all use Notion AI every single day to help their teams stay ahead.
So here's the next step.
Try custom agents now at Notion.com slash changelog.
That's all overcase letters, Notion.com slash changelog to try custom agents today, right now.
And when you use our link, you know you're supporting the show.
And we love that.
So Notion.com slash changelog.
There's a book.
Okay.
I'm gonna recommend this book, and you may have read this book, Burk.
Uh, Who Moved My Cheese?
Oh.
And this book.
Right?
Yeah.
Do you know the story well?
It's been a while since I've seen my heart.
Yeah, but I know, yeah, I essentially know the fundamentals.
But go ahead.
Well I don't know by heart.
I just know I just know you have Scurry and you have him and you have Ha.
And essentially the story is is there's cheese.
There's mice, right?
They're in this maze and there's cheese.
And there's been an abundance of cheese in this area for a while and and they're all going back there.
And one day they go back there and the cheese is gone.
This represents change, right?
Okay.
Used to come here every day, get our daily cheese, enjoy enjoy, come back, whatever.
And then him and Ha kind of keep coming back, keep coming back, and the cheese is just never there again.
Meanwhile, Scurry is gone looking for the cheese.
And I think as sad as it makes me to say that, to lament that idea for us that this craft is changing.
It truly I am.
But if we sit there, if that story is true at all for anybody, if we sit there like him and Ha and worry about the cheese and it didn't move or it didn't move, or where is it going to be at?
And they're just so worried and anxious about that future.
Meanwhile, Scurry just was like, out of here, gonna go find the cheese.
I think we have to take that into consideration.
We have to find a way to move around the value chain.
And we have to adapt because otherwise we'll be like him and how we'll be in the past.
Meanwhile, Scurry found the new cheese back to this new world to they're gonna enjoy again.
I think we have to figure out that uh that kind of way.
And I want to mention a friend of mine, John Daniel Trask.
He is the co-founder and CEO of Ray Gun and recently of Autohive.
And you may know Ray Gun, they've been an air tracker for and performance platform and you know uh Core Web Vitals for you know years.
Stand-up software, amazing team.
And uh John Daniel Trask said this recently.
Uh geez, I thought I had that.
I had a couple of his bookmarks.
Let me find his actual other one.
Give me a sec.
He's like, I've been yeah, I've been a for 34 years, I've been a development, or sorry, he says 34 years of development experience here, haven't manually written the line of code in about 18 months.
Now he is one of these examples of a CEO coming back out of retirement, so to speak, and writing code again, but I know John Daniel Trask, and he's always been in the details.
He's always been a tinkerer, he's always been on the side doing something wild.
It may not be production rigging code or something like that.
And I'm just always speaking from my awareness, not his truth.
But he said, I haven't written uh a manual line of code in about 18 months, never have had higher output.
Shocks me how few have adapted yet, though.
Yeah.
And that's why, you know, our audience, uh, some may be like Adam, shut up, or my gosh, why do you keep talking about AI?
And I think it's just natural because it is the it is the it's the conversation out there.
The cheese is moving or is moved.
How do you adapt?
Yeah, we get this on VS Code all the time.
It's because as you can imagine, there's this, there's VS Code has, I don't know what the public number we share is millions of users.
It's astronomical.
Yeah, yeah.
And it's a lot of these folks, a lot of these folks, they they just want to live their life, right?
They just want to write code.
And most of the updates that we make are in the realm of AI.
And people rightfully get upset.
And they're like, why?
Where is the rest of the stuff like for the editor?
And the truth is that this is the direction that everything is going.
Like it just is.
In order to remain a relevant tool, VS Code has to adapt and move and meet developers where the future is.
But it has to do that while still supporting the devs who need to open up index.js and be productive with their code today with no AI.
And so it's it's a focus on doing both, but I understand and we hear that feedback, and we understand how you feel.
We understand, but that is not the direction that things are headed is very much a genetic in AI.
That is that is just where the industry is going.
And in order to be a relevant tool, you have to move in that direction too.
Do you think we'll get to a point uh a year from now, two years from now?
And I know this can be major step function changes as we keep progressing.
But do you think we'll get back to that?
Uh wow, this was a handcrafted piece of software.
And then that that person or those persons or that kind of team is like, we only build handcrafted software here.
Um like art artisanal.
Uh yeah, I mean, yeah.
I mean, like, and maybe even charge a major premium.
I don't know.
Like, well, I so let's use an analogy.
It's like you could go if you could buy a piece of furniture today.
Like if you let's say you needed a dresser, you could buy from somebody who has handmade that.
They've they've rounded the edges themselves.
They've used the lathe, right?
It's beautiful.
They stained the wood.
I do some woodwork.
Are you a carpenter?
You can know these terms.
I love it.
I a little bit.
I've done some woodwork myself.
It's it.
I think if you're a developer, you just like to build things.
So I like I like Lego, I like woodworking, I like knitting.
Knitting is a very much like a building type activity.
Um, but that, but then the then the answer is well, you could buy that for you know $350, or you can go to Walmart and you can buy a particle board proximity of this thing for 25.
And the question is whether or not that matters.
Most people are going to choose the $25 particle board thing, right?
Or maybe they get someone in the middle, but it's really a luxury when you go out and you say, like, there isn't a logical reason to do that, other than you want to own a piece of handcrafted furniture.
And I just don't see, because software's digital, I don't see people caring.
I do think that there's I'm already at the point where it's I'm like, I can't believe we used to write every line of code by hand.
Adam, do you remember this?
We used to literally type function space bracket return tab.
Maybe like an occasional tab to get the tag complete some things.
Not so much the blue when I think about that.
Yeah.
Yeah, yeah.
Or even this is we used to uh code with AI via tab completion.
Yes.
Not like write the whole file, right?
Just write the whole thing.
Yeah, you know what I mean?
But we used to line completely on from that so quickly.
Because Copilot, when Copilot first came out, it was ghost text and autocomplete.
And uh, and I when they first showed it to us internally, I was like, oh my gosh, I'd never seen anything like it.
I had no idea that we would go from there.
That was listen to me, audience, listeners, chat.
That was like three years ago.
That was three years ago.
It was today, we are in a totally different spot.
And in fact, a year ago, there was no agent mode in Visual Studio Code.
There was an edit mode.
Fast forward a year later, and we have full-on like agency workflows from GitHub, which is something that was just announced, right?
Agents have memory, they can do deep research.
They you can you can deploy, you can type fleet in the GitHub Copilot CLI, and it will deploy a fleet of agents.
It will it will determine how many to deploy, what to focus them on, how to divide up the work.
Like we are moving it a click that is really hard to wrap your head around.
And even me, like when I see stuff that's coming up internally, I'm like, what the heck is that?
What even is that?
I don't understand what that is.
Can we please slow down?
Right.
Exactly.
Daily releases something.
Yeah.
We're in the ultimate season of build, build, build.
You know, I think it goes back to developers, developers, developers, maintainers, maintainers, maintainers.
It's a throwback.
And I think the love to see someone at Microsoft stand up on the stage and say, build, build, build.
Because that's the era we're in, right?
Just to just to throw back to the old day of developer building.
Um, I totally agree.
Like we're in this is like there's two ways to think about it.
It's like this is the death of developers, or this is the second coming, baby.
I think it's the second coming.
I I agree.
For the completely agree.
Yeah.
For the next, I would say, let me try to let me try to predict this, and I'll come back to this stage here again if I'm wrong.
I don't know.
I was gonna say 10 years, but I feel that's a long time.
Oh, that's an eternity.
It is an eternity.
I feel like, I mean, well, I don't want to say developers are gonna die anytime soon because that would be just an absolute shame.
But I think making software is not going to change.
We need smart folks with awareness, intent, understanding, moral high ground, etc.
to craft and mold the platforms, protocols, and software built on them over the next forever, perpetuity.
Uh I think we should always have I mean software is for humans largely.
And I think actually I take that back.
A lot of software is actually being built for agents to make better software for humans to make better software, which is a weird cycle.
But I would say for the next five years at least, for the next five years, it's it's a whatever developer is world.
You know, whatever a developer is gonna be, it's that world.
It's time to build.
Uh so go build.
It's available to you right now.
It does back to my notion of toll booth.
There is a toll booth in front of that.
You know, we used to have to buy an IDE, and then maybe in the case of VS Co we didn't because it was open source and free, but subsidized by Microsoft, right?
Uh bringing on more users to the platform, more users for Azure, etc.
Subsidize elsewhere, you know, and thankfully you've got an amazing team building VS Code for all these years, just diligently building some of the best software uh known to man.
I have some quirks with it, but that's okay.
I'm personally a Zed user, I like Zed.
Uh that's a good editor.
Yeah, there's so many great dev tools out there.
That's the other thing I tell people is that you can't lose.
All they're all of them are good right now.
So no matter which one you pick, first of all, they're about all on par at this point, and they're all excellent.
You can't make a bad choice.
You really can't.
I mean, we're in the plethora of amazing software, we're in the plethora of change, and we're in the plethora of making your own thing and potentially making something that everybody else loves too.
I mean, take take Peter Steinberg.
I mean, uh, just three weeks ago, I was DMing with him.
Now I can't get a return.
Why?
He's super busy, right?
We were just talking about the most famous man in the world.
Yeah, yeah.
I mean, he went from uh coming back from retirement, solving his own problem, releasing it for others, having a great uh product direction with it, and working his absolute tail off on it, uh, to now being called a genius by Sam Altman and working for OpenAI to keep building open claw in the open.
And there could be, you know, positives and negatives to that because there always is, but he went from, you know, peer to transcend it now.
I mean, still he's still talking to the world.
I'm not gonna say he's not, but he's definitely a busy person now, and I think he's got some really good taste, which I think is really important in this next era is taste in software.
You can't just come like you said before to a boot camp thinking that software developers make a lot of money, therefore I make software so I can make a lot of money.
You really have to enjoy the end, not just the means.
Like the means is software creation, is software developer, but you have to enjoy the end too, and you have to have clear uh developer user experience and user experience and good intent and ability to specify what should be in the world from where we're currently at.
I think that's the the hallmark that we can keep honing and exercising as as crafts folks.
And I think that's very well said.
And to your point, Adam, about like Peter, this is a really good example because it's not like Peter was just a guy that showed up and was like, I think I'm gonna build something with AI.
Yeah, this guy's a really good developer.
Like he previously solved an extremely hard problem.
So, yes, it happened rapidly, but we're also talking about an individual that's extremely an extremely high level engineer, extremely capable, right?
So I it doesn't lend credence to this idea that you don't need to be a developer, but rather that if you are a really good developer, that you really can you can really do anything.
Yeah.
We're in the era of polymath.
Are you familiar with this term polymath?
Yeah, yeah.
Okay.
I think we're in the era of that.
I think if you are a developer that's been seasoned quite a bit, maybe you haven't dabbled in everything that you possibly could have, but you've been aware.
Maybe you've been listening to those podcasts for many, many years.
We've touched, we've never been a Ruby camp or a JavaScript camp or a TypeScript camp or a Go only or Rust only.
We've never been a we've been agnostic to the software landscape, so to speak.
Very clearly for those reasons because we've been talking about and touching so many different areas.
I think you've been paying attention to the show, or you go back in its history and you connect those dots.
Now you're a polymath of sorts.
You can come with some version of context and get drafted into polymath.
If you can begin to connect dots, you can become a polymath, I think, in this kind of world here.
Because AI will help you do that.
And it's already smarter than most of us.
And uh it just needs us to kind of guide it a little bit.
And I say for now.
For now, it needs us to guide us.
Yeah, I I agree.
And I had actually tweeted out something like a couple last week or something where I had I was working on something, I wanted to build something, and I asked the AI about it.
It was like, oh yeah, you should use, we should use Go.
You should use Go to do this.
Yeah.
And I thought, I don't know Go.
And then I remembered, well, that doesn't matter at all.
So it's like I was this close to just being like, no, I don't want to do that.
I don't know Go.
But then remembering, oh, that doesn't, that's irrelevant.
I can I can actually learn it and let the agent do it as I go.
I can still do it.
And that is the thing that people are gonna have to do right now is is they're going to have to start thinking differently.
Everything you know has to be rethought, literally everything.
The next time you think that can't be done, the answer is probably absolutely can be done.
And you have to, you it's just, it's like I want to, I don't want to say think different, right?
I don't want to say like it's hackneyed to say you can do with any anything with AI.
You just have to figure out what that thing is.
If AI isn't useful, it's your problem, not the AI.
But at some level, there is truth to this in the sense that the limiting factor is you.
It's me.
It's my preconceived notions about what can and can't be done and what I'm willing to not or not do with the AI.
That's it.
Yeah.
I've gotten a lot of fruit in my labor around planning.
I've uh I've thought a lot about certain problems, and now there are personal problems for now.
Um, and at some point I'll start launching more things, and I've mentioned that on this podcast, and I'm not going to go into it here necessarily, but you know, I I've found a lot of value in just planning because in some cases I'm learning new ground.
I'm very well in one area, but you know, kind of mediocre in like 17 other areas.
And so I'm taking those 17 of those areas and I'm thinking deeply and I'm spending time learning, and I'm not, I'm not in a rush to get to the the me, the end.
I'm kind of kind of settling in the means in a way.
I'm learning about different protocols or different ways of doing things, or just zooming out a little bit to be like, wow, you know what?
This is actually I hadn't played with that.
I didn't considered how that would connect to this.
And I just sort of like steep, I would say, steep in that in that craft part of it, is learning about what's possible and then making a decent plan and then executing that plan.
That's kind of been my ground there is just really just enjoying that learning process again.
And the process of like making something and iterating with it, discovering learning, discovering, learning, and shipping.
That's been quite fun to kind of solve my own problems.
Because there's been areas where I've just haven't like, I have never built this much software in my entire life than I have in the last six months.
Yeah.
Right?
100%.
A bit of a ton of software.
Largely behind the scenes, but that's okay for now.
Uh, but I think as I level up and as AI is obviously leveled up, like we're only a few months away since Opus 4.5, which I think is what changed the world for a lot of folks.
That was a major step function in the right direction.
And now it's like, well, the world really is a developer's oyster.
So go for that.
Yeah, and we should point out that Opus 4.5 kind of like to me kicked off, started something, but it is not the only model, right?
There you we now we have 4.6, there's 4.6 fast, there's 4.6 within 1 million context window.
5.3 is an outstanding model context window.
Yeah.
5.3 is unbelievably good.
Uh Gemini uh is a great model, right?
They just released 3-1.
Great model, right?
So these model companies are really going at it, trying to deliver the best coding experience.
And then developers, listen, we're the ones who win, right?
We're getting all the best tools, we're getting all the best models.
That's right.
Like this now's the time.
So I agree with you.
I've never built so much software in my life.
And I'll have an idea.
I'll be like, oh, I wonder if I can do that.
And then I'll just go do it.
I'll just build it.
And you may throw it away.
Who cares?
Who doesn't matter?
There's yeah, there's gonna come a point where tokens need to be counted and matter.
That is not this point right now.
So throw the agent in a while loop and let it just run for days on end.
What do you care?
Right.
Well said, well said.
I'm personally getting some really good enjoyment from uh from Codex.
GPT 5.3 has been really cool.
Uh I feel like when I play with that thing, it it it spits things back to me.
I'm like, can you explain that to me?
Like I'm five, because like I don't even know what you just said.
You're just so next level in how it responds.
I'm like, you think I have the context here, but I'm not following you because you're way smarter than I am.
Can you please just dump me down a little bit?
Somebody described 5.3 as like a really, really senior dev, and like Opus 4.6 is like your best friend.
Yes.
Right.
And so they're they're they're different in the way they interact.
And so, like I said, I'll use I use 4.6, I interface with 4.6, and it just delegates work to 5.3.
Because I actually don't want to I don't want to interface with 5.3.
I know that it's a really good dev, so I went writing code, but I want to talk to 4.6 because it's always like, oh yeah, you know what?
You're totally right.
I'd miss that.
You're so smart.
We should that's the gaslighting.
So nice to me.
It's like, yeah, it makes me feel good.
Yeah.
Makes me feel good about myself.
I'm with you on that.
I've been I've been actually doing that exact step, which is I've used Opus 4.6 to do planning and then delegated to 5.3, uh GPT 5.3 uh for those exact reasons.
Because I'm like, you know, I thought I was smart, but now I'm talking to you, and I feel like I'm just not that smart anymore.
Or it's just not as nice.
It's like, Adam, can you just pick it up here?
I'm like, I want to be 10 steps down the road here, and you're holding me back here.
Yeah.
Which is uh which is part of the battle here.
What else you want to say, Burke?
I know that we got lots to say.
You got some cool stuff you're working on.
The you get a copilot CLI.
We didn't even mention that really.
I think it's a beautiful thing.
Uh great work on that front there.
I mean, there's a the the world's the oyster for the next coding CLI to kind of keep iterating.
You got open code out there, you got Claude, you've got Codex, you've got a copilot CLI, you got all the things out there.
What do you want to say in closing?
Yeah, I would just like to say, you know, for me, because I've been working on the Copilot CLI, that's exciting.
And it just went GA today, and that GA is just our way of saying, like, it's ready for production use because we have so many enterprise customers, and they won't touch anything until yeah, just today.
Wow.
Uh, and and they can't use anything until that thing is out of preview.
It has to be stable, right?
They have to know that it's supportable and usable.
And so today you can start using that.
Um, and I would just tell people like I'm super excited about the stuff that is being done to make AI even better so that you don't have to compose these like hacky workflows or make Ralph loops, whatever the heck that is, or use a gas town.
Like there's all these crazy ideas and terminology being thrown around.
And the truth is that like you don't have to use any of that stuff.
Just start working with the agent and see what works for you and create your own.
You're smart, you'll figure out the workflows.
You can make the agent do anything.
Don't I know it's easy to get overwhelmed.
Trust me, I know.
Yeah, very easy.
But just use it and figure out the workflows that make you most productive, and you're already.
If that's all you do, you're already in like the top five percent of folks at the moment.
Yeah.
I would say don't delay.
You know, really, really don't delay.
If your pocketbook can handle it, uh, get the get the smallest version of things.
If it can go further, go further.
And I would do that based upon graduated usage, of course.
So you'll hit limits and it'll it'll give you that feedback of like, hey, you've hit your plan limit kind of thing.
But I definitely did not would not delay.
My list of things to work on is so long, Burke.
And and tell me if this is your world here, that uh this morning when I woke up and I thought, I know what I gotta do today.
And I know my my daily tasks, I've got to get done.
But in terms of projects and moving things forward, I was like, I have to really, really work hard to prioritize because I have ADHD.
I like to have novel problems to solve, and that's where my brain just really thrives.
And so I try my best to push back on the Adam who wants to go the easier route, which is solve brand new problems and never actually finish and deliver.
Right.
To really kind of push the thing that really should go next over that hurdle to be usable by not just one, but by many, which is really my biggest issue with my software.
Uh but I really have to work hard to be disciplined because I am kind of overwhelmed on what I could do, what I should do, and what I want to do, that it takes a lot of discipline in this world.
So I would say be careful out there, y'all.
You are cracking up to something that could not be go back in in your bottle, so to speak.
But I've got it's very, very hard, and I have to be very disciplined to be balanced in my life and then also balanced in the work I put out there in terms of software.
Yeah, and if this is a whole other podcast, Adam.
You should probably have on.
I'm trying to think it would be great to talk about this, kind of like it's almost like a psychosis.
Oh, yeah, but this is a whole other podcast.
But like, do be careful, y'all.
Once you open this box, you can't shut it.
And you this is all you will do.
It's all you will think about, it's all you will do.
Right, it will consume your brain.
I know this because I do it.
I'm doing it in my sleep.
In my sleep, I'm doing it.
And so I think that that's that's the next podcast episode we need from the changelog here.
It's like what is this doing to us exactly?
Yeah, I think it's.
I mean, I I I don't want to be doom and gloom, but I do have uh a slight concur on that because I think before I leave my office, I think, what could I kick off while I'm gone?
Yep.
But then I have to really push back and say, you know what?
Doesn't matter.
Doesn't matter.
Every moment is a wasted moment.
You could be building software right now.
What are you doing?
I know.
Why am I talking to you, Burke?
I could be I could be making some bangs, you know.
You could have built a 100,000 MRR project and instead you did that.
It's quite possible.
It really is quite possible.
Who knows, man?
I don't know.
I don't know.
But hey, thank you so much for opening our eyes back in January to many and then coming on the pod to kind of go into some of those details about Opus 4.5 changing things for the game and just sharing some of the backstory there.
And thank you for the recommendation on the agent psychosis, I believe, is what you're referring to.
Because I don't know what to call that.
Like yeah, well, it's it's a term, it's a term out there.
It's a it's a household name, so to speak now.
This agent psychosis is like, am I crazy?
Did I think I could do these things because it can do these things?
Am I suddenly superhuman or superpowered because it's superpowered?
Then you have to be like, maybe not.
Yeah.
If I jump off this building, will I fly?
You will know.
Am I Neo right now?
Okay, yeah.
Am I am I seeing the ones that use, but I'm actually seeing the full am I seeing the lady in the radio?
Yes.
What is happening here?
Burk, thank you so much.
It's been awesome, man.
Thank you.
Thanks for having me, Adam.
Well, it is a new world here at the changelog, and it is a new world in our developer landscape.
AI is here.
You could be on the fence, you could be against it, you could be for it, you could be in between, you can resist it, you can do all the things.
But I think the one truth is it's just not going back in the bottle.
It is the new way.
The developer landscape, the operating system is being rebuilt on top of AI.
This is not hype.
This is real.
This is here.
And I want to talk to you about that in Zulup.
Changelog.com slash community.
Free to join.
Zulup chat is for you.
Come share your thoughts.
Come comment on this episode.
Come hang with friends.
Hang your hat, call it home.
All the good things.
And to our plus plus subscribers, hey, you know what?
It's still here.
Changelog Plus Plus.
It's still better.
It's better.
You know what?
So much about the changelog will get better.
Not because it was bad, but because there's always room for improvement.
Entropy cannot be resisted.
It is the way.
And Changelog Plus Plus is better.
There's a bonus on this episode.
Burke and I go a little deeper, a little more closer to the metal, as they say.
And you can do that if you're not already a plus plus subscriber by going to Changelog.com slash plus plus.
10 bucks a month, 100 bucks a year, drop the ads, get a little closer to the metal, get bonus content, and support our show.
And here in closing, I do want to say one more thank you to my good friend Jared because you know what?
This show is is better because of you, my friend.
And I'm grateful for our work together.
I'm grateful for our friendship over the years.
I'm grateful for you, and you will be missed by me, by the audience.
Take care, my friend.
I'll see you out there.
Okay.
This episode has sponsors.
We love our sponsor because hey, they pay the bills, and that's what we like.
We like bills getting paid.
Our friends at augment code.
Now I love Augie.
Seriously.
Augie is my one-shot tool.
Okay, if you heard it on the podcast, that's cool.
I love it.
Augie is my one-shot tool.
Uh, of course, I use Squarespace for my small business.
My wife runs a company.
It is amazing, and she could not do it without Squarespace.
And of course, Notion, my gosh, I love Notion.
Keeps me organized.
Notion agents, Notion AI.
It is so cool.
Of course, check them out.
Notion.com slash changelog.
Squarespace.com slash changelog.
And just augmentcode.com.
Well, one thing that's not changing around here is the beats.
Breakmaster is our beat freaking residence for life.
We have a fun project that we're working on.
Very, very fun.
And it's coming soon.
It's coming soon.
That's it.
The show's done.
We'll see ya.
We do have a plus plus version of it if you have one or two more things to say or time.
Which is a small paying audience, but it's mostly for the loyalist of loyalist fans of Changelog.
Well, what do you think they'd want to know about anything?
The down and dirty.
What's dirty we didn't throw out there?
I didn't even ask you about in the main show.
Like uh, has this changed your lens on how you think about your future?
You know, has this new ability, this new superpower, uh given you the desire to change anything major?
Maybe that's something.
Uh how are you thinking about your career, I suppose?
Yeah, that's uh that's a great question.
I think I'm like everyone in that I don't know what I don't know what the next six months holds, and that's the hardest part about the moment is that there's so much uncertainty.
For me personally, my skill set is code.
It is a technology, it's an intersection of technology and communication.
That's what I do.
I've never been a great developer, I've always been a good one, but I'm not the kind of dev where you could say, Hey, we need to completely rethink the way the editor buffer works in Visual Studio Code.
We're gonna need you to figure out what the I'm not that guy.
There's a guy on the channel.