He's right.

Coding is solved. Bugs are not yet Coding is solved. Bugs are not yet solved. Fix incoming. Oh boy, it's been solved. Fix incoming. Oh boy, it's been solved. Fix incoming. Oh boy, it's been a bit since a Boris tweet annoyed people a bit since a Boris tweet annoyed people a bit since a Boris tweet annoyed people as much as this one. I miss the days as much as this one. I miss the days as much as this one. I miss the days where he would just randomly post about where he would just randomly post about where he would just randomly post about how Cloud Code has replaced all of their how Cloud Code has replaced all of their how Cloud Code has replaced all of their engineers and everyone would get mad. engineers and everyone would get mad. engineers and everyone would get mad. But at the same time, a lot of the But at the same time, a lot of the But at the same time, a lot of the things he said before now kind of seem things he said before now kind of seem things he said before now kind of seem right. They were obnoxious at the time right. They were obnoxious at the time right. They were obnoxious at the time and were just very far off, especially and were just very far off, especially and were just very far off, especially the timeline aspects of what he said. the timeline aspects of what he said. the timeline aspects of what he said. But the reality of engineering nowadays But the reality of engineering nowadays But the reality of engineering nowadays is that if you're writing your code by is that if you're writing your code by is that if you're writing your code by hand still, you are largely falling hand still, you are largely falling hand still, you are largely falling behind. And I have to do a thing I am behind. And I have to do a thing I am behind. And I have to do a thing I am not excited to do. I have to defend what not excited to do. I have to defend what not excited to do. I have to defend what Boris said here because a lot of people Boris said here because a lot of people Boris said here because a lot of people are looking at this in the wrong light are looking at this in the wrong light are looking at this in the wrong light and pushing back in ways I don't and pushing back in ways I don't and pushing back in ways I don't necessarily find fair. Matt PCO's push necessarily find fair. Matt PCO's push necessarily find fair. Matt PCO's push back in particular is beautiful. Been back in particular is beautiful. Been back in particular is beautiful. Been thinking about this quote for a solid 24 thinking about this quote for a solid 24 thinking about this quote for a solid 24 hours. It's like a raspberry ripple of hours. It's like a raspberry ripple of hours. It's like a raspberry ripple of a vanilla ice cream of VC a vanilla ice cream of VC a vanilla ice cream of VC funding stirred with a little pinch of funding stirred with a little pinch of funding stirred with a little pinch of turd. And the hottake you probably don't turd. And the hottake you probably don't turd. And the hottake you probably don't expect from me here, Matt's also right. expect from me here, Matt's also right. expect from me here, Matt's also right. And I want to do my best to break down And I want to do my best to break down And I want to do my best to break down what both people are saying here because what both people are saying here because what both people are saying here because they're using the same terms to say they're using the same terms to say they're using the same terms to say very, very different things. And if you very, very different things. And if you very, very different things. And if you understand where they come from and what understand where they come from and what understand where they come from and what they're actually trying to say they're actually trying to say they're actually trying to say underneath, I think you can learn a lot underneath, I think you can learn a lot underneath, I think you can learn a lot about where software is going and how about where software is going and how about where software is going and how people are applying these things in people are applying these things in people are applying these things in their work. But first, I have to do my their work. But first, I have to do my their work. But first, I have to do my job quick, which means it's time for a job quick, which means it's time for a job quick, which means it's time for a sponsor break. I've been landing a lot sponsor break. I've been landing a lot sponsor break. I've been landing a lot of PRs recently. Like a truly insane of PRs recently. Like a truly insane of PRs recently. Like a truly insane amount. Before filming today, I ended up amount. Before filming today, I ended up amount. Before filming today, I ended up landing like eight PRs on a day where I landing like eight PRs on a day where I landing like eight PRs on a day where I also had a bunch of meetings. Sorry, it also had a bunch of meetings. Sorry, it also had a bunch of meetings. Sorry, it looks like it was actually more than looks like it was actually more than looks like it was actually more than that. It's crazy. And today's sponsor is

that. It's crazy. And today's sponsor is that. It's crazy. And today's sponsor is one of the pieces that has helped the one of the pieces that has helped the one of the pieces that has helped the most here is the CIU Blacksmith. These most here is the CIU Blacksmith. These most here is the CIU Blacksmith. These guys have revolutionized what I'm guys have revolutionized what I'm guys have revolutionized what I'm willing to use GitHub actions for. I was willing to use GitHub actions for. I was willing to use GitHub actions for. I was just so used to them being really slow just so used to them being really slow just so used to them being really slow and unreliable that I just stopped and unreliable that I just stopped and unreliable that I just stopped putting things on them I didn't have to. putting things on them I didn't have to. putting things on them I didn't have to. And then I started using Blacksmith and And then I started using Blacksmith and And then I started using Blacksmith and all of our times got cut by like 2x or all of our times got cut by like 2x or all of our times got cut by like 2x or more. There's a lot of layers to what more. There's a lot of layers to what more. There's a lot of layers to what make Blacksmith so much better than make Blacksmith so much better than make Blacksmith so much better than traditional GitHub actions. From the traditional GitHub actions. From the traditional GitHub actions. From the hardware that's two times faster to the hardware that's two times faster to the hardware that's two times faster to the cache downloads that are four times cache downloads that are four times cache downloads that are four times faster to the absurd 40 times faster faster to the absurd 40 times faster faster to the absurd 40 times faster Docker builds. All of that by itself is Docker builds. All of that by itself is Docker builds. All of that by itself is enough to feel a real difference. What's enough to feel a real difference. What's enough to feel a real difference. What's even cooler is that their documentation even cooler is that their documentation even cooler is that their documentation is so good that your agents can parse it is so good that your agents can parse it is so good that your agents can parse it really well. I asked my agents how I can really well. I asked my agents how I can really well. I asked my agents how I can speed up CI even more and they found a speed up CI even more and they found a speed up CI even more and they found a bunch of ways to do more parallel work. bunch of ways to do more parallel work. bunch of ways to do more parallel work. But more importantly, they found sticky But more importantly, they found sticky But more importantly, they found sticky discs from Blacksmith, which lets you discs from Blacksmith, which lets you discs from Blacksmith, which lets you set up a chunk of your disc that is set up a chunk of your disc that is set up a chunk of your disc that is stored across runs, which make a bunch stored across runs, which make a bunch stored across runs, which make a bunch of things from downloading a ton of node of things from downloading a ton of node of things from downloading a ton of node modules to giant file transforms to your modules to giant file transforms to your modules to giant file transforms to your old huge git history, all way, way old huge git history, all way, way old huge git history, all way, way faster. I look at this chart and I cry a faster. I look at this chart and I cry a faster. I look at this chart and I cry a bit because I've seen GitHub action bit because I've seen GitHub action bit because I've seen GitHub action cache downloads take way over a minute.

cache downloads take way over a minute. cache downloads take way over a minute. Some of our CI spent more time Some of our CI spent more time Some of our CI spent more time downloading than running. But if you downloading than running. But if you downloading than running. But if you switch over to sticky discs, there's switch over to sticky discs, there's switch over to sticky discs, there's literally no download speed because it's literally no download speed because it's literally no download speed because it's already there. It takes 3 seconds already there. It takes 3 seconds already there. It takes 3 seconds instead of over a minute. If you want instead of over a minute. If you want instead of over a minute. If you want faster CI today, tell your agent to faster CI today, tell your agent to faster CI today, tell your agent to check out sidv.link/blacksmith. check out sidv.link/blacksmith. check out sidv.link/blacksmith. Okay, good to have you back. Let's start Okay, good to have you back. Let's start Okay, good to have you back. Let's start here with Boris's tweet. This is a here with Boris's tweet. This is a here with Boris's tweet. This is a response to Peter's post showing a bug response to Peter's post showing a bug response to Peter's post showing a bug in the Cloud Code desktop app, which in the Cloud Code desktop app, which in the Cloud Code desktop app, which admittedly is a terrible showcase of admittedly is a terrible showcase of admittedly is a terrible showcase of what AI models are capable of because what AI models are capable of because what AI models are capable of because there is no excuse for the Cloud Code there is no excuse for the Cloud Code there is no excuse for the Cloud Code desktop app to be in as rough of a shape desktop app to be in as rough of a shape desktop app to be in as rough of a shape as it is. The team is working hard on as it is. The team is working hard on as it is. The team is working hard on it. They've taken my feedback it. They've taken my feedback it. They've taken my feedback surprisingly well. They were a little surprisingly well. They were a little surprisingly well. They were a little beat up when I first called out how bad beat up when I first called out how bad beat up when I first called out how bad the Cloudco desktop app was, but they the Cloudco desktop app was, but they the Cloudco desktop app was, but they realize I'm doing it in good faith. I realize I'm doing it in good faith. I realize I'm doing it in good faith. I just want it to be better. So now just want it to be better. So now just want it to be better. So now they're making real improvements. Those they're making real improvements. Those they're making real improvements. Those improvements involve shipping updates improvements involve shipping updates improvements involve shipping updates all the time. And when you get an all the time. And when you get an all the time. And when you get an update, you can't actually read the update, you can't actually read the update, you can't actually read the update text because it gets truncated update text because it gets truncated update text because it gets truncated because a model wrote this field. And because a model wrote this field. And because a model wrote this field. And when the model wrote it, it was just when the model wrote it, it was just when the model wrote it, it was just reading the code and it didn't realize reading the code and it didn't realize reading the code and it didn't realize that the window space available for this that the window space available for this that the window space available for this little callout thing wasn't long enough little callout thing wasn't long enough little callout thing wasn't long enough to actually fit the text being rendered.

to actually fit the text being rendered. to actually fit the text being rendered. This is such a common mistake that I see This is such a common mistake that I see This is such a common mistake that I see all the time with AI generated code that all the time with AI generated code that all the time with AI generated code that frankly didn't happen a whole lot before frankly didn't happen a whole lot before frankly didn't happen a whole lot before AI generated code took over. If you were AI generated code took over. If you were AI generated code took over. If you were building a feature like this, you would building a feature like this, you would building a feature like this, you would probably make sure it renders in the probably make sure it renders in the probably make sure it renders in the browser while you're working on it so browser while you're working on it so browser while you're working on it so that you could see how it looks. that you could see how it looks. that you could see how it looks. Hypothetically speaking, you could just Hypothetically speaking, you could just Hypothetically speaking, you could just write the code and put up the PR having write the code and put up the PR having write the code and put up the PR having never tested it. But in a world of never tested it. But in a world of never tested it. But in a world of humans writing code, why would you do humans writing code, why would you do humans writing code, why would you do that? Why would you waste the time of that? Why would you waste the time of that? Why would you waste the time of your co-workers with code that you never your co-workers with code that you never your co-workers with code that you never even saw the output of? You'd probably even saw the output of? You'd probably even saw the output of? You'd probably make sure it shows up in the browser at make sure it shows up in the browser at make sure it shows up in the browser at the absolute least. And when you did the absolute least. And when you did the absolute least. And when you did that, you would notice this edge case that, you would notice this edge case that, you would notice this edge case and fix it before you bother your team. and fix it before you bother your team. and fix it before you bother your team. By default, agents don't do that at all. By default, agents don't do that at all. By default, agents don't do that at all. And the result is things like this. In a And the result is things like this. In a And the result is things like this. In a world where we've learned the agents world where we've learned the agents world where we've learned the agents write good code and it's usually safe to write good code and it's usually safe to write good code and it's usually safe to merge, we get really used to doing that merge, we get really used to doing that merge, we get really used to doing that where we just hit the merge button if we where we just hit the merge button if we where we just hit the merge button if we look through the code quick and look through the code quick and look through the code quick and everything seems fine. We've always everything seems fine. We've always everything seems fine. We've always trusted that original developer to test trusted that original developer to test trusted that original developer to test the thing they changed and make sure the thing they changed and make sure the thing they changed and make sure there are no bugs before we put it up there are no bugs before we put it up there are no bugs before we put it up for code review. But now we live in a for code review. But now we live in a for code review. But now we live in a world where the code review going up world where the code review going up world where the code review going up does not imply any effort was put into does not imply any effort was put into does not imply any effort was put into checking the thing ahead. And you end up checking the thing ahead. And you end up checking the thing ahead. And you end up with stuff like this. This is why with stuff like this. This is why with stuff like this. This is why Peter's post quoting the coding is Peter's post quoting the coding is Peter's post quoting the coding is solved thing is actually hilarious and solved thing is actually hilarious and solved thing is actually hilarious and rightfully so. Because while agents can rightfully so. Because while agents can rightfully so. Because while agents can write the code, they're missing so many write the code, they're missing so many write the code, they're missing so many of the things that we would expect of the things that we would expect of the things that we would expect modern software to do and we would modern software to do and we would modern software to do and we would expect more importantly for the humans expect more importantly for the humans expect more importantly for the humans writing the software to get right. It is writing the software to get right. It is writing the software to get right. It is also absurd that we can't hot reload also absurd that we can't hot reload also absurd that we can't hot reload agents that are supposed to run 24/7. I

agents that are supposed to run 24/7. I agents that are supposed to run 24/7. I wish it was easier to do that. I wish it was easier to do that. I wish it was easier to do that. I understand technically speaking why it's understand technically speaking why it's understand technically speaking why it's not. I have been working on this a not. I have been working on this a not. I have been working on this a little bit with T3 code, so I can little bit with T3 code, so I can little bit with T3 code, so I can empathize to the difficulty of this empathize to the difficulty of this empathize to the difficulty of this problem. But I think the bigger call out problem. But I think the bigger call out problem. But I think the bigger call out here is that you can't actually read the here is that you can't actually read the here is that you can't actually read the text in this. Boris's response here is text in this. Boris's response here is text in this. Boris's response here is less about the hot reload thing and more less about the hot reload thing and more less about the hot reload thing and more about the visible bug in this image, about the visible bug in this image, about the visible bug in this image, which is why his follow-up saying that which is why his follow-up saying that which is why his follow-up saying that this isn't a bug. It's a UX issue that this isn't a bug. It's a UX issue that this isn't a bug. It's a UX issue that we have a fix for. This is a bug. I got we have a fix for. This is a bug. I got we have a fix for. This is a bug. I got to reply to this one. Boris, I'm doing to reply to this one. Boris, I'm doing to reply to this one. Boris, I'm doing my best to defend you here, but this my best to defend you here, but this my best to defend you here, but this reply is making it harder. By what logic reply is making it harder. By what logic reply is making it harder. By what logic would you say the text being cut off in would you say the text being cut off in would you say the text being cut off in all reasonable display sizes isn't a all reasonable display sizes isn't a all reasonable display sizes isn't a bug? I'd be really curious what your bug? I'd be really curious what your bug? I'd be really curious what your definition of a bug is because this definition of a bug is because this definition of a bug is because this cannot be the intended experience. In cannot be the intended experience. In cannot be the intended experience. In order for us to have a conversation order for us to have a conversation order for us to have a conversation about this, we need definitions for the about this, we need definitions for the about this, we need definitions for the words coding and for solved. I hope we words coding and for solved. I hope we words coding and for solved. I hope we all know what is means. Coding can mean all know what is means. Coding can mean all know what is means. Coding can mean a lot of different things. It can mean a lot of different things. It can mean a lot of different things. It can mean telling somebody about an idea and they telling somebody about an idea and they telling somebody about an idea and they go build the whole thing, turning the go build the whole thing, turning the go build the whole thing, turning the idea into an experience. That whole end idea into an experience. That whole end idea into an experience. That whole end to end could be coding. Coding could be to end could be coding. Coding could be to end could be coding. Coding could be just the part where you open up your just the part where you open up your just the part where you open up your editor and you write code. Coding could editor and you write code. Coding could editor and you write code. Coding could be the process of turning a Jira ticket be the process of turning a Jira ticket be the process of turning a Jira ticket into a pull request. Coding could also into a pull request. Coding could also into a pull request. Coding could also include the process of reviewing that include the process of reviewing that include the process of reviewing that code or pulling down someone else's code or pulling down someone else's code or pulling down someone else's changes. Coding can be a very narrow changes. Coding can be a very narrow changes. Coding can be a very narrow task or a very wide one depending on how task or a very wide one depending on how task or a very wide one depending on how you want to use the term. And let's be you want to use the term. And let's be you want to use the term. And let's be real, even before AI, how much of an real, even before AI, how much of an real, even before AI, how much of an engineer's time was actually spent engineer's time was actually spent engineer's time was actually spent writing code in their editor? If we writing code in their editor? If we writing code in their editor? If we think of coding as the endtoend aspect think of coding as the endtoend aspect think of coding as the endtoend aspect of what an engineer does, obviously of what an engineer does, obviously of what an engineer does, obviously coding is not solved. If coding is the

coding is not solved. If coding is the coding is not solved. If coding is the thing I do from when I walk into the thing I do from when I walk into the thing I do from when I walk into the office as an engineer to when I leave, office as an engineer to when I leave, office as an engineer to when I leave, no, AI has not solved coding. But if we no, AI has not solved coding. But if we no, AI has not solved coding. But if we think of coding as the thing that think of coding as the thing that think of coding as the thing that happens when I open up my text editor happens when I open up my text editor happens when I open up my text editor and I'm pressing keys on my keyboard, if and I'm pressing keys on my keyboard, if and I'm pressing keys on my keyboard, if we narrow that definition down to be we narrow that definition down to be we narrow that definition down to be that small, where coding is the act of that small, where coding is the act of that small, where coding is the act of typing code on my keyboard inside of an typing code on my keyboard inside of an typing code on my keyboard inside of an editor, yes, absolutely coding is editor, yes, absolutely coding is editor, yes, absolutely coding is solved. I'd even widen a little bit and solved. I'd even widen a little bit and solved. I'd even widen a little bit and say if you include things like finding say if you include things like finding say if you include things like finding the right Jira ticket, going through the the right Jira ticket, going through the the right Jira ticket, going through the stuff that users are doing, turning the stuff that users are doing, turning the stuff that users are doing, turning the data from the experiences users have data from the experiences users have data from the experiences users have into the code that you want to write, into the code that you want to write, into the code that you want to write, that whole experience from like rough that whole experience from like rough that whole experience from like rough idea to code that works. That all can be idea to code that works. That all can be idea to code that works. That all can be done with the AI now. And when it comes done with the AI now. And when it comes done with the AI now. And when it comes to actually generating code that to actually generating code that to actually generating code that functions, AI has solved that. But functions, AI has solved that. But functions, AI has solved that. But engineering isn't just coding. Going to engineering isn't just coding. Going to engineering isn't just coding. Going to do a silly example. Please hear me out. do a silly example. Please hear me out. do a silly example. Please hear me out. This is the password game by Neil Fun. This is the password game by Neil Fun. This is the password game by Neil Fun. This is meant to mock how hard it is to This is meant to mock how hard it is to This is meant to mock how hard it is to sign up to most websites nowadays sign up to most websites nowadays sign up to most websites nowadays because their password requirements are because their password requirements are because their password requirements are absurd. So, every time I fix what is absurd. So, every time I fix what is absurd. So, every time I fix what is missing, I have to make additional missing, I have to make additional missing, I have to make additional changes. Now, it says the digits of my changes. Now, it says the digits of my changes. Now, it says the digits of my password have to add up to 25. Cool.

password have to add up to 25. Cool. password have to add up to 25. Cool. There we got that. Password must include There we got that. Password must include There we got that. Password must include a month of the year. April a month of the year. April a month of the year. April must include one of our sponsors. must include one of our sponsors. must include one of our sponsors. Hilarious. Okay, so why am I showing Hilarious. Okay, so why am I showing Hilarious. Okay, so why am I showing this? This is obviously a terrible this? This is obviously a terrible this? This is obviously a terrible experience. If this was the password experience. If this was the password experience. If this was the password system in a real website, we would make system in a real website, we would make system in a real website, we would make fun of it endlessly because it's bad. We fun of it endlessly because it's bad. We fun of it endlessly because it's bad. We don't want to use this. But was Neil don't want to use this. But was Neil don't want to use this. But was Neil coding when he built this? Obviously, coding when he built this? Obviously, coding when he built this? Obviously, yes. When Neil made this game, he coded yes. When Neil made this game, he coded yes. When Neil made this game, he coded it. He had the idea. He opened an it. He had the idea. He opened an it. He had the idea. He opened an editor. He wrote code to make this thing editor. He wrote code to make this thing editor. He wrote code to make this thing exist. And now it exists and we can exist. And now it exists and we can exist. And now it exists and we can experience it. He did intend for it to experience it. He did intend for it to experience it. He did intend for it to be this rough, buggy, messy experience be this rough, buggy, messy experience be this rough, buggy, messy experience because that's the point is making fun because that's the point is making fun because that's the point is making fun of these types of experiences. So he did of these types of experiences. So he did of these types of experiences. So he did it with intent, but he did code this. it with intent, but he did code this. it with intent, but he did code this. And I hope we all agree that the process And I hope we all agree that the process And I hope we all agree that the process of somebody like Neil having this idea of somebody like Neil having this idea of somebody like Neil having this idea and then putting it out there, that and then putting it out there, that and then putting it out there, that coding is at the very least involved coding is at the very least involved coding is at the very least involved heavily in this process. So now I have heavily in this process. So now I have heavily in this process. So now I have to ask, if somebody built something this to ask, if somebody built something this to ask, if somebody built something this bad accidentally where they were told to bad accidentally where they were told to bad accidentally where they were told to implement a password field in their implement a password field in their implement a password field in their website or web app and when they did website or web app and when they did website or web app and when they did that they made it really rough and that they made it really rough and that they made it really rough and miserable like this, were they coding? I miserable like this, were they coding? I miserable like this, were they coding? I would hope we can also agree the answer would hope we can also agree the answer would hope we can also agree the answer there is yes. That just because the code there is yes. That just because the code there is yes. That just because the code didn't come out good or useful based on didn't come out good or useful based on didn't come out good or useful based on the actual goal that a user would have the actual goal that a user would have the actual goal that a user would have using it doesn't mean they weren't using it doesn't mean they weren't using it doesn't mean they weren't coding. I hope we can also agree there's coding. I hope we can also agree there's coding. I hope we can also agree there's a difference if this type of horrible a difference if this type of horrible a difference if this type of horrible experience happens because there wasn't experience happens because there wasn't experience happens because there wasn't enough detail in the request made to the

enough detail in the request made to the enough detail in the request made to the developer where if I told them make a developer where if I told them make a developer where if I told them make a password system for our site and then password system for our site and then password system for our site and then they went and whipped this up because they went and whipped this up because they went and whipped this up because they didn't know what a good or bad they didn't know what a good or bad they didn't know what a good or bad password like experience was that is password like experience was that is password like experience was that is different from if I write a bunch of different from if I write a bunch of different from if I write a bunch of tickets that say we have all of these tickets that say we have all of these tickets that say we have all of these crazy rules make sure that you apply all crazy rules make sure that you apply all crazy rules make sure that you apply all of them and the developer creates of them and the developer creates of them and the developer creates something with all of that bad something with all of that bad something with all of that bad decision-m applied to it. These are very decision-m applied to it. These are very decision-m applied to it. These are very different. Bad code happening because of different. Bad code happening because of different. Bad code happening because of no detail given in the planning process no detail given in the planning process no detail given in the planning process versus bad code happening because of bad versus bad code happening because of bad versus bad code happening because of bad details in that same planning process. details in that same planning process. details in that same planning process. Missing details can lead to code that Missing details can lead to code that Missing details can lead to code that doesn't behave as expected. And bad doesn't behave as expected. And bad doesn't behave as expected. And bad details can also lead to code that details can also lead to code that details can also lead to code that doesn't behave as expected. But that's doesn't behave as expected. But that's doesn't behave as expected. But that's the input side. Bad info going in, the input side. Bad info going in, the input side. Bad info going in, whether it's missing stuff or is just whether it's missing stuff or is just whether it's missing stuff or is just bad with the details it has, going into bad with the details it has, going into bad with the details it has, going into the code box, results in bad code. But the code box, results in bad code. But the code box, results in bad code. But there's another thing that can often there's another thing that can often there's another thing that can often result in bad code, which is the other result in bad code, which is the other result in bad code, which is the other side. Not that the code comes out bad, side. Not that the code comes out bad, side. Not that the code comes out bad, but because you don't have a system that but because you don't have a system that but because you don't have a system that allows you to verify the code on the allows you to verify the code on the allows you to verify the code on the other side. Let's look at it like this.

other side. Let's look at it like this. other side. Let's look at it like this. You have these different qualities of You have these different qualities of You have these different qualities of plan. You have the engineering cycle. It plan. You have the engineering cycle. It plan. You have the engineering cycle. It could be one person. It could be a team. could be one person. It could be a team. could be one person. It could be a team. It could be three engineers doing a It could be three engineers doing a It could be three engineers doing a sprint. It could be whatever. And when sprint. It could be whatever. And when sprint. It could be whatever. And when you put in a good plan, we hope that out you put in a good plan, we hope that out you put in a good plan, we hope that out of this comes good software. There are of this comes good software. There are of this comes good software. There are plenty of ways that this can change. plenty of ways that this can change. plenty of ways that this can change. Obviously, if the quality of the Obviously, if the quality of the Obviously, if the quality of the engineers isn't great, if the good plan engineers isn't great, if the good plan engineers isn't great, if the good plan gets lost along the way, if somebody gets lost along the way, if somebody gets lost along the way, if somebody rewrites the plan and goes off course, rewrites the plan and goes off course, rewrites the plan and goes off course, but generally speaking, if you have good but generally speaking, if you have good but generally speaking, if you have good engineers and a good plan, we hope that engineers and a good plan, we hope that engineers and a good plan, we hope that the result would be good software. If the result would be good software. If the result would be good software. If you have a bad plan, the most that we you have a bad plan, the most that we you have a bad plan, the most that we can hope the engineers do is give can hope the engineers do is give can hope the engineers do is give feedback on that bad plan and say, "Hey, feedback on that bad plan and say, "Hey, feedback on that bad plan and say, "Hey, I'm not sure if this is the right idea." I'm not sure if this is the right idea." I'm not sure if this is the right idea." But if I've learned anything from my But if I've learned anything from my But if I've learned anything from my time as an engineer, it's that people time as an engineer, it's that people time as an engineer, it's that people outside of engineering often don't like outside of engineering often don't like outside of engineering often don't like when you come in and say that their plan when you come in and say that their plan when you come in and say that their plan for how to change the software isn't for how to change the software isn't for how to change the software isn't great. And I understand it's their job great. And I understand it's their job great. And I understand it's their job on the product team to figure out what on the product team to figure out what on the product team to figure out what we should be doing, not the engineer's we should be doing, not the engineer's we should be doing, not the engineer's job. It's our job to do it. But I would job. It's our job to do it. But I would job. It's our job to do it. But I would then ask you, is a truly exceptional then ask you, is a truly exceptional then ask you, is a truly exceptional coder, a person whose job is to turn coder, a person whose job is to turn coder, a person whose job is to turn ideas into code, are they going to push ideas into code, are they going to push ideas into code, are they going to push back on a bad plan or would they just back on a bad plan or would they just back on a bad plan or would they just implement that bad plan because they're implement that bad plan because they're implement that bad plan because they're good at coding, not making good good at coding, not making good good at coding, not making good software? Because those are different software? Because those are different software? Because those are different things. a bad plan going through great things. a bad plan going through great things. a bad plan going through great coders that aren't there to push back on coders that aren't there to push back on coders that aren't there to push back on plans. They're there to execute those plans. They're there to execute those plans. They're there to execute those plans. They're going to make bad plans. They're going to make bad plans. They're going to make bad software because the thing going in is software because the thing going in is software because the thing going in is bad. The thing going out is obviously bad. The thing going out is obviously bad. The thing going out is obviously also going to be bad. And then there is also going to be bad. And then there is also going to be bad. And then there is the empty or bare plan where there just the empty or bare plan where there just the empty or bare plan where there just isn't enough detail in the plan. This isn't enough detail in the plan. This isn't enough detail in the plan. This has the widest range of potential has the widest range of potential has the widest range of potential output. Like if the plan is good and the output. Like if the plan is good and the output. Like if the plan is good and the engineers are good, we can say the range engineers are good, we can say the range engineers are good, we can say the range of success here would be like 8 to 10 of success here would be like 8 to 10 of success here would be like 8 to 10 obviously out of 10. Where with the bad

obviously out of 10. Where with the bad obviously out of 10. Where with the bad plan, I would argue that the software plan, I would argue that the software plan, I would argue that the software coming out will also probably be bad as coming out will also probably be bad as coming out will also probably be bad as low as like a one to a four out of 10. low as like a one to a four out of 10. low as like a one to a four out of 10. Regardless of how good the engineers Regardless of how good the engineers Regardless of how good the engineers are, this just kind of affects what are, this just kind of affects what are, this just kind of affects what range you're falling in there. And then range you're falling in there. And then range you're falling in there. And then with an empty or bare plan, the range is with an empty or bare plan, the range is with an empty or bare plan, the range is massive. I would say as far as 1 to 10, massive. I would say as far as 1 to 10, massive. I would say as far as 1 to 10, you have no idea. It depends on a lot. you have no idea. It depends on a lot. you have no idea. It depends on a lot. It depends on how complex the thing is It depends on how complex the thing is It depends on how complex the thing is that is being requested. Depends on how that is being requested. Depends on how that is being requested. Depends on how well the engineer understands all of well the engineer understands all of well the engineer understands all of this as well as how well they understand this as well as how well they understand this as well as how well they understand the needs of their users. how complex the needs of their users. how complex the needs of their users. how complex the software is, how complex the request the software is, how complex the request the software is, how complex the request is. There's so many layers to this that is. There's so many layers to this that is. There's so many layers to this that the range, I would say, could be the range, I would say, could be the range, I would say, could be anything. If you give great engineers an anything. If you give great engineers an anything. If you give great engineers an empty plan that is a very, very vague empty plan that is a very, very vague empty plan that is a very, very vague idea of what you want, and they're idea of what you want, and they're idea of what you want, and they're excited to just write code and put up a excited to just write code and put up a excited to just write code and put up a poll request, the likelihood that this poll request, the likelihood that this poll request, the likelihood that this is good is random, almost probably not is good is random, almost probably not is good is random, almost probably not looking great if I'm being real. So, looking great if I'm being real. So, looking great if I'm being real. So, what do we do to fix this? How do we what do we do to fix this? How do we what do we do to fix this? How do we handle this as an industry? Obviously, handle this as an industry? Obviously, handle this as an industry? Obviously, step one is to write better plans, but step one is to write better plans, but step one is to write better plans, but if we can't control the quality of plans if we can't control the quality of plans if we can't control the quality of plans at all times, we need to make sure we at all times, we need to make sure we at all times, we need to make sure we have other solutions. We also need to have other solutions. We also need to have other solutions. We also need to make sure that the code that comes out make sure that the code that comes out make sure that the code that comes out is matching the needs of the plan is matching the needs of the plan is matching the needs of the plan because we don't know if the engineers because we don't know if the engineers because we don't know if the engineers in this box are good or not either. So, in this box are good or not either. So, in this box are good or not either. So, how can we improve our outcomes in the how can we improve our outcomes in the how can we improve our outcomes in the box here? I would argue we've had a box here? I would argue we've had a box here? I would argue we've had a solution for this for a long time now.

solution for this for a long time now. solution for this for a long time now. It's the verification layer. things like It's the verification layer. things like It's the verification layer. things like QA, things like staging environments you QA, things like staging environments you QA, things like staging environments you can test in, things like slow rollouts can test in, things like slow rollouts can test in, things like slow rollouts that will make sure that bad code that will make sure that bad code that will make sure that bad code doesn't hit users and if it does that it doesn't hit users and if it does that it doesn't hit users and if it does that it minimizes the impact of that bad code. minimizes the impact of that bad code. minimizes the impact of that bad code. Good verification steps will allow for Good verification steps will allow for Good verification steps will allow for your engineers to verify the results your engineers to verify the results your engineers to verify the results against the plan and perhaps in some against the plan and perhaps in some against the plan and perhaps in some cases even notice that once you cases even notice that once you cases even notice that once you implement the plan, the experience isn't implement the plan, the experience isn't implement the plan, the experience isn't great. If I have a plan that looks good, great. If I have a plan that looks good, great. If I have a plan that looks good, I can't tell it's a bad plan because it I can't tell it's a bad plan because it I can't tell it's a bad plan because it all seems fine and then I build it and I all seems fine and then I build it and I all seems fine and then I build it and I put up the code, it's unlikely that I put up the code, it's unlikely that I put up the code, it's unlikely that I know the actual experience is bad until know the actual experience is bad until know the actual experience is bad until I try it. Trying it could be spinning it I try it. Trying it could be spinning it I try it. Trying it could be spinning it up on my machine. Trying it could be up on my machine. Trying it could be up on my machine. Trying it could be testing the preview build when it testing the preview build when it testing the preview build when it happens. Trying it could be your agents happens. Trying it could be your agents happens. Trying it could be your agents going through the loop with it and going through the loop with it and going through the loop with it and showing you a video of it when it's showing you a video of it when it's showing you a video of it when it's done. But you need something here to done. But you need something here to done. But you need something here to prevent the bad plans and even to an prevent the bad plans and even to an prevent the bad plans and even to an extent the good plans from having things extent the good plans from having things extent the good plans from having things sneak in that are not a good experience. sneak in that are not a good experience. sneak in that are not a good experience. Good plans and good engineers should Good plans and good engineers should Good plans and good engineers should result in good experiences, but I would result in good experiences, but I would result in good experiences, but I would argue they only do when the good argue they only do when the good argue they only do when the good engineer has a system to verify the engineer has a system to verify the engineer has a system to verify the changes are actually good. But if you changes are actually good. But if you changes are actually good. But if you have a bad plan or bad engineers, then have a bad plan or bad engineers, then have a bad plan or bad engineers, then you need this even more in order to you need this even more in order to you need this even more in order to verify the quality of those outputs.

verify the quality of those outputs. verify the quality of those outputs. Hopefully, you could already see what Hopefully, you could already see what Hopefully, you could already see what I'm about to do. Let's replace this team I'm about to do. Let's replace this team I'm about to do. Let's replace this team of engineers with who is really doing of engineers with who is really doing of engineers with who is really doing the work today. Swarms of agents. You the work today. Swarms of agents. You the work today. Swarms of agents. You take your plan, you give it to Claude, take your plan, you give it to Claude, take your plan, you give it to Claude, you give it to Codeex, it spins up a you give it to Codeex, it spins up a you give it to Codeex, it spins up a bunch of sub agents to execute all the bunch of sub agents to execute all the bunch of sub agents to execute all the parts, and then it puts up a poll parts, and then it puts up a poll parts, and then it puts up a poll request. If it hasn't actually run the request. If it hasn't actually run the request. If it hasn't actually run the code to check, it might look fine, it code to check, it might look fine, it code to check, it might look fine, it might seem fine, but you don't know if might seem fine, but you don't know if might seem fine, but you don't know if it is fine until someone checks it. it is fine until someone checks it. it is fine until someone checks it. Usually, that'll be a human. And sadly Usually, that'll be a human. And sadly Usually, that'll be a human. And sadly enough, the human is often the one using enough, the human is often the one using enough, the human is often the one using the software in the end. It's not one of the software in the end. It's not one of the software in the end. It's not one of the humans who work on the product. And the humans who work on the product. And the humans who work on the product. And that's exactly what happened here. Do that's exactly what happened here. Do that's exactly what happened here. Do you legitimately think after this code you legitimately think after this code you legitimately think after this code was written by an agent that any human was written by an agent that any human was written by an agent that any human or agent actually checked what it did in or agent actually checked what it did in or agent actually checked what it did in the app? Obviously no. Because this the app? Obviously no. Because this the app? Obviously no. Because this would be a very quick thing you see and would be a very quick thing you see and would be a very quick thing you see and you're like, "Oh yeah, that is wrong. I you're like, "Oh yeah, that is wrong. I you're like, "Oh yeah, that is wrong. I should fix it." But no one did because should fix it." But no one did because should fix it." But no one did because no one saw it. And by the time it has no one saw it. And by the time it has no one saw it. And by the time it has merged, the friction to unmerge it or to merged, the friction to unmerge it or to merged, the friction to unmerge it or to fix it is higher than the friction to fix it is higher than the friction to fix it is higher than the friction to build and merge it in the first place. build and merge it in the first place. build and merge it in the first place. To go back to our diagram here, let's To go back to our diagram here, let's To go back to our diagram here, let's say that after the verification loop, say that after the verification loop, say that after the verification loop, you've determined that the software is you've determined that the software is you've determined that the software is good. At the very least, based on your good. At the very least, based on your good. At the very least, based on your understanding that the problem you're understanding that the problem you're understanding that the problem you're trying to solve has been solved and the trying to solve has been solved and the trying to solve has been solved and the thing that comes out in all obvious ways thing that comes out in all obvious ways thing that comes out in all obvious ways seems fine. And I would expect that the seems fine. And I would expect that the seems fine. And I would expect that the result is good software, probably result is good software, probably result is good software, probably similar range. Maybe we could even bump similar range. Maybe we could even bump similar range. Maybe we could even bump from that 8 out of 10 to like 9 out of from that 8 out of 10 to like 9 out of from that 8 out of 10 to like 9 out of 10 or 10 out of 10 range. What happens 10 or 10 out of 10 range. What happens 10 or 10 out of 10 range. What happens if the result isn't good? Well, ideally if the result isn't good? Well, ideally if the result isn't good? Well, ideally that bad result will send you back up to that bad result will send you back up to that bad result will send you back up to the planning stage so that you can the planning stage so that you can the planning stage so that you can adjust the plan based on what you've adjust the plan based on what you've adjust the plan based on what you've learned from the verification. Maybe the

learned from the verification. Maybe the learned from the verification. Maybe the bug is just something silly in the bug is just something silly in the bug is just something silly in the implementation and you can skip straight implementation and you can skip straight implementation and you can skip straight back to the agent swarm or the engineers back to the agent swarm or the engineers back to the agent swarm or the engineers working on it to have them fix whatever working on it to have them fix whatever working on it to have them fix whatever isn't right. The point I'm trying to isn't right. The point I'm trying to isn't right. The point I'm trying to make here is that if your verification make here is that if your verification make here is that if your verification system is good, then before the code system is good, then before the code system is good, then before the code ever goes to users, it should be able to ever goes to users, it should be able to ever goes to users, it should be able to identify the problems and fix them as identify the problems and fix them as identify the problems and fix them as they are working. And right now, agents they are working. And right now, agents they are working. And right now, agents don't do this at the very least by don't do this at the very least by don't do this at the very least by default. And this can be caused by a lot default. And this can be caused by a lot default. And this can be caused by a lot of things, many of which are actually of things, many of which are actually of things, many of which are actually human error. I cannot tell you how many human error. I cannot tell you how many human error. I cannot tell you how many code bases I've worked in where just code bases I've worked in where just code bases I've worked in where just spinning it up on my machine to see if spinning it up on my machine to see if spinning it up on my machine to see if my changes worked was more complex than my changes worked was more complex than my changes worked was more complex than making the change in the first place. making the change in the first place. making the change in the first place. And it ends up being easier to just file And it ends up being easier to just file And it ends up being easier to just file the pull request and wait for the the pull request and wait for the the pull request and wait for the preview build to come up than it is to preview build to come up than it is to preview build to come up than it is to try and test it on my machine. If it is try and test it on my machine. If it is try and test it on my machine. If it is too hard for you to spin up and test, it too hard for you to spin up and test, it too hard for you to spin up and test, it is way too hard for your agents to do is way too hard for your agents to do is way too hard for your agents to do the same. You need to make it easier to the same. You need to make it easier to the same. You need to make it easier to actually verify your code bases. And I actually verify your code bases. And I actually verify your code bases. And I find the companies struggling the most find the companies struggling the most find the companies struggling the most with this are the ones who are building with this are the ones who are building with this are the ones who are building in a way that is hard to verify. Funny in a way that is hard to verify. Funny in a way that is hard to verify. Funny enough, Anthropic is one of the most enough, Anthropic is one of the most enough, Anthropic is one of the most guilty of this. Since Claude Code guilty of this. Since Claude Code guilty of this. Since Claude Code Desktop is a full desktopbacked Electron Desktop is a full desktopbacked Electron Desktop is a full desktopbacked Electron app, in order to run QA and verify it, app, in order to run QA and verify it, app, in order to run QA and verify it, they need to give every thread its own they need to give every thread its own they need to give every thread its own graphical VM fully backed with a real graphical VM fully backed with a real graphical VM fully backed with a real instance of an operating system that is instance of an operating system that is instance of an operating system that is supported with Cloud Code Desktop so supported with Cloud Code Desktop so supported with Cloud Code Desktop so that it can run the build, spin up that that it can run the build, spin up that that it can run the build, spin up that Cloud Code Desktop instance in an Cloud Code Desktop instance in an Cloud Code Desktop instance in an environment where Claude can control it environment where Claude can control it environment where Claude can control it and check it and prod at it. And when and check it and prod at it. And when and check it and prod at it. And when you combine the fact that that is you combine the fact that that is you combine the fact that that is expensive and difficult and far from expensive and difficult and far from expensive and difficult and far from trivial to set up with the additional trivial to set up with the additional trivial to set up with the additional fact that cloud code models are just so fact that cloud code models are just so fact that cloud code models are just so much worse at computer use than models

much worse at computer use than models much worse at computer use than models from other places, you end up without from other places, you end up without from other places, you end up without that good quality verification loop that that good quality verification loop that that good quality verification loop that is necessary to prove this software is necessary to prove this software is necessary to prove this software works. It's silly to put it this way, works. It's silly to put it this way, works. It's silly to put it this way, but I think a significant portion of why but I think a significant portion of why but I think a significant portion of why the Cloud Code desktop app isn't the Cloud Code desktop app isn't the Cloud Code desktop app isn't improving meaningfully in comparison to improving meaningfully in comparison to improving meaningfully in comparison to the Cloud Code web app, which is the Cloud Code web app, which is the Cloud Code web app, which is improving constantly, simply comes down improving constantly, simply comes down improving constantly, simply comes down to how easy it is to set up Cloud Code to how easy it is to set up Cloud Code to how easy it is to set up Cloud Code web for testing versus Claude Code web for testing versus Claude Code web for testing versus Claude Code Desktop. Since the Cloud website is Desktop. Since the Cloud website is Desktop. Since the Cloud website is built on, you know, the web, it's a lot built on, you know, the web, it's a lot built on, you know, the web, it's a lot easier to set up a loop where your easier to set up a loop where your easier to set up a loop where your agents can test it. You could even have agents can test it. You could even have agents can test it. You could even have one given machine where your agents have one given machine where your agents have one given machine where your agents have eight tabs open for eight different dev eight tabs open for eight different dev eight tabs open for eight different dev builds checking different things, and builds checking different things, and builds checking different things, and it's totally fine. with Cloud Code it's totally fine. with Cloud Code it's totally fine. with Cloud Code desktop. Good luck launching eight desktop. Good luck launching eight desktop. Good luck launching eight separate Claude Code instances as a separate Claude Code instances as a separate Claude Code instances as a desktop Electron app on the same desktop Electron app on the same desktop Electron app on the same computer that I can poke and prod computer that I can poke and prod computer that I can poke and prod through without getting confused along through without getting confused along through without getting confused along the way. It's not going to happen. But the way. It's not going to happen. But the way. It's not going to happen. But this would also be hard for a human. If this would also be hard for a human. If this would also be hard for a human. If I was trying to review two different PRs I was trying to review two different PRs I was trying to review two different PRs and test their changes at the same time and test their changes at the same time and test their changes at the same time on my computer, it wouldn't be pleasant. on my computer, it wouldn't be pleasant. on my computer, it wouldn't be pleasant. I know cuz I've built Electron apps for I know cuz I've built Electron apps for I know cuz I've built Electron apps for a decade. If you have two things you a decade. If you have two things you a decade. If you have two things you want to check at the same time, you're want to check at the same time, you're want to check at the same time, you're kind of just screwed. And this means you kind of just screwed. And this means you kind of just screwed. And this means you have to build a system to make it have to build a system to make it have to build a system to make it easier. Again, if it would be hard for easier. Again, if it would be hard for easier. Again, if it would be hard for the human to verify, it is probably the human to verify, it is probably the human to verify, it is probably impossible for the agent to do it. And impossible for the agent to do it. And impossible for the agent to do it. And quadcode desktop is a golden example of quadcode desktop is a golden example of quadcode desktop is a golden example of what happens when you don't have a good what happens when you don't have a good what happens when you don't have a good enough loop for catching these types of enough loop for catching these types of enough loop for catching these types of things by actually testing the changes things by actually testing the changes things by actually testing the changes that you make. So going back to this that you make. So going back to this that you make. So going back to this diagram, my question for you would be diagram, my question for you would be diagram, my question for you would be what parts of this are coding? Do you what parts of this are coding? Do you what parts of this are coding? Do you think coding is narrowly scoped to this think coding is narrowly scoped to this think coding is narrowly scoped to this part here where plans are transformed part here where plans are transformed part here where plans are transformed into code? the act of typing on the

into code? the act of typing on the into code? the act of typing on the keyboard in the editor or the agent keyboard in the editor or the agent keyboard in the editor or the agent transforming these ideas into source transforming these ideas into source transforming these ideas into source code that you can actually run and use code that you can actually run and use code that you can actually run and use or do you think it's wider? Do you think or do you think it's wider? Do you think or do you think it's wider? Do you think coding also includes the planning side coding also includes the planning side coding also includes the planning side actually figuring out what you want to actually figuring out what you want to actually figuring out what you want to do? Do you think it includes the do? Do you think it includes the do? Do you think it includes the verification side making sure the verification side making sure the verification side making sure the changes are valid or not? Do you think changes are valid or not? Do you think changes are valid or not? Do you think it includes the full loop where that it includes the full loop where that it includes the full loop where that verification layer goes back into the verification layer goes back into the verification layer goes back into the coding part? I think everyone defines coding part? I think everyone defines coding part? I think everyone defines this a bit differently, which is why the this a bit differently, which is why the this a bit differently, which is why the conversation has gotten as chaotic as it conversation has gotten as chaotic as it conversation has gotten as chaotic as it has. Because for some people, coding is has. Because for some people, coding is has. Because for some people, coding is just this section in the middle, the just this section in the middle, the just this section in the middle, the agent swarm part where you're writing agent swarm part where you're writing agent swarm part where you're writing the code. And for others, coding is the code. And for others, coding is the code. And for others, coding is everything you do going from idea to everything you do going from idea to everything you do going from idea to functioning software. I can hear the functioning software. I can hear the functioning software. I can hear the argument either way. I personally don't argument either way. I personally don't argument either way. I personally don't care that much. But at the absolute care that much. But at the absolute care that much. But at the absolute least, I would say that the whole least, I would say that the whole least, I would say that the whole process here from start to end is process here from start to end is process here from start to end is software engineering. And if anybody software engineering. And if anybody software engineering. And if anybody tries to say that software engineering tries to say that software engineering tries to say that software engineering is solved because agents write code, is solved because agents write code, is solved because agents write code, okay, in this middle section, then both okay, in this middle section, then both okay, in this middle section, then both Prime and I will be equally mad at them Prime and I will be equally mad at them Prime and I will be equally mad at them because software engineering isn't because software engineering isn't because software engineering isn't solved. Software engineering isn't just solved. Software engineering isn't just solved. Software engineering isn't just this little piece here where you make this little piece here where you make this little piece here where you make code. Software engineering isn't even code. Software engineering isn't even code. Software engineering isn't even just this square. It is far wider and just this square. It is far wider and just this square. It is far wider and forces you to think about the forces you to think about the forces you to think about the architecture of the systems you're architecture of the systems you're architecture of the systems you're building so that this whole loop can building so that this whole loop can building so that this whole loop can happen more effectively hundreds of happen more effectively hundreds of happen more effectively hundreds of times a day. The engineering isn't just times a day. The engineering isn't just times a day. The engineering isn't just what you do inside of this box. It's the what you do inside of this box. It's the what you do inside of this box. It's the platform you build for the boxes to sit platform you build for the boxes to sit platform you build for the boxes to sit on and stack up and continue to grow.

on and stack up and continue to grow. on and stack up and continue to grow. But Boris didn't say software But Boris didn't say software But Boris didn't say software engineering. He said coding. And that's engineering. He said coding. And that's engineering. He said coding. And that's historically what he has said. If Boris historically what he has said. If Boris historically what he has said. If Boris had said software engineering is solved, had said software engineering is solved, had said software engineering is solved, I would be making a very different video I would be making a very different video I would be making a very different video right now. But he didn't. Bugs are part right now. But he didn't. Bugs are part right now. But he didn't. Bugs are part of software engineering. The same way of software engineering. The same way of software engineering. The same way that building good verification loops is that building good verification loops is that building good verification loops is part of software engineering. part of software engineering. part of software engineering. Architecting systems in a way that you Architecting systems in a way that you Architecting systems in a way that you can make changes confidently is part of can make changes confidently is part of can make changes confidently is part of software engineering. These aren't just software engineering. These aren't just software engineering. These aren't just coding tasks. These are engineering work coding tasks. These are engineering work coding tasks. These are engineering work and that's why that word exists because and that's why that word exists because and that's why that word exists because it's not just the task of being a code it's not just the task of being a code it's not just the task of being a code monkey sitting at a computer typing monkey sitting at a computer typing monkey sitting at a computer typing letters on the keyboard. And if I'm letters on the keyboard. And if I'm letters on the keyboard. And if I'm being really frank here, agents need a being really frank here, agents need a being really frank here, agents need a lot of help with this part. The same way lot of help with this part. The same way lot of help with this part. The same way that an incredible engineer that you that an incredible engineer that you that an incredible engineer that you just hired would need help with these just hired would need help with these just hired would need help with these things in order to work in your things in order to work in your things in order to work in your codebase. If a new engineer showed up codebase. If a new engineer showed up codebase. If a new engineer showed up and they were assigned this change and and they were assigned this change and and they were assigned this change and they couldn't even get the test build they couldn't even get the test build they couldn't even get the test build running on their machine, much less running on their machine, much less running on their machine, much less three of them so they can test your three of them so they can test your three of them so they can test your changes too, they're just as screwed as changes too, they're just as screwed as changes too, they're just as screwed as the agents are. And I think a lot of us the agents are. And I think a lot of us the agents are. And I think a lot of us have code bases where a great engineer have code bases where a great engineer have code bases where a great engineer would be unhappy working in them and would be unhappy working in them and would be unhappy working in them and wouldn't have the resources they need to wouldn't have the resources they need to wouldn't have the resources they need to verify their stuff. Now imagine that verify their stuff. Now imagine that verify their stuff. Now imagine that person has been blinded that you person has been blinded that you person has been blinded that you literally force them to work with their literally force them to work with their literally force them to work with their eyes closed. How good of software do you eyes closed. How good of software do you eyes closed. How good of software do you think they're going to make? Probably think they're going to make? Probably think they're going to make? Probably still decent here and there if the still decent here and there if the still decent here and there if the changes don't require them to see what changes don't require them to see what changes don't require them to see what they're working on, but it's a lot they're working on, but it's a lot they're working on, but it's a lot better if you give them what they need better if you give them what they need better if you give them what they need to verify those changes. So when I'm to verify those changes. So when I'm to verify those changes. So when I'm hearing Boris say coding is solved, bugs hearing Boris say coding is solved, bugs hearing Boris say coding is solved, bugs are not yet solved. What I'm hearing him are not yet solved. What I'm hearing him are not yet solved. What I'm hearing him say is that this part here agents have say is that this part here agents have say is that this part here agents have gotten incredible at. If you give them a gotten incredible at. If you give them a gotten incredible at. If you give them a wellsp spec change, they will make that wellsp spec change, they will make that wellsp spec change, they will make that change. The change might not be what you

change. The change might not be what you change. The change might not be what you actually want, but if you tell them what actually want, but if you tell them what actually want, but if you tell them what to do, they will do it 99% of the time. to do, they will do it 99% of the time. to do, they will do it 99% of the time. And if they get it wrong, you can tell And if they get it wrong, you can tell And if they get it wrong, you can tell them what they got wrong, and they'll them what they got wrong, and they'll them what they got wrong, and they'll fix it 95% of the time. But the next fix it 95% of the time. But the next fix it 95% of the time. But the next part, which is finding and preventing part, which is finding and preventing part, which is finding and preventing bugs autonomously, ends up being bugs autonomously, ends up being bugs autonomously, ends up being significantly more difficult. Not just significantly more difficult. Not just significantly more difficult. Not just because the agents are stupid and don't because the agents are stupid and don't because the agents are stupid and don't know how, but because our code bases are know how, but because our code bases are know how, but because our code bases are stupid and don't set them up for it, stupid and don't set them up for it, stupid and don't set them up for it, too. We need improvements in our system too. We need improvements in our system too. We need improvements in our system and architecture in our apps in order to and architecture in our apps in order to and architecture in our apps in order to make them easier to test and verify. We make them easier to test and verify. We make them easier to test and verify. We need better tools from the labs and need better tools from the labs and need better tools from the labs and people building AI development tech in people building AI development tech in people building AI development tech in order to make it easier for the agents order to make it easier for the agents order to make it easier for the agents to actually access those systems that to actually access those systems that to actually access those systems that we're building and test things in we're building and test things in we're building and test things in verifiable, repeatable ways. We need verifiable, repeatable ways. We need verifiable, repeatable ways. We need better systems for our agents to show us better systems for our agents to show us better systems for our agents to show us that they actually checked their changes that they actually checked their changes that they actually checked their changes and to make that more normalized. Hell, and to make that more normalized. Hell, and to make that more normalized. Hell, we need a way for GitHub to allow our we need a way for GitHub to allow our we need a way for GitHub to allow our agents to upload an image or a video agents to upload an image or a video agents to upload an image or a video proving their work without having to proving their work without having to proving their work without having to commit it to the repo, which has caused commit it to the repo, which has caused commit it to the repo, which has caused all sorts of disasters across a lot of all sorts of disasters across a lot of all sorts of disasters across a lot of projects. Fun fact, there's a new GitHub projects. Fun fact, there's a new GitHub projects. Fun fact, there's a new GitHub CLI update where they did actually CLI update where they did actually CLI update where they did actually finally add this, which I think is a finally add this, which I think is a finally add this, which I think is a huge stepping stone in getting all of huge stepping stone in getting all of huge stepping stone in getting all of this right. But that's the key. We need this right. But that's the key. We need this right. But that's the key. We need to figure out both what we can do in our to figure out both what we can do in our to figure out both what we can do in our code bases to give agents more code bases to give agents more code bases to give agents more likelihood of verifying things well likelihood of verifying things well likelihood of verifying things well themselves as well as expect the themselves as well as expect the themselves as well as expect the providers we rely on whether that's providers we rely on whether that's providers we rely on whether that's anthropic and open AAI or if it's GitHub anthropic and open AAI or if it's GitHub anthropic and open AAI or if it's GitHub and Google Chrome whatever the layers and Google Chrome whatever the layers and Google Chrome whatever the layers are we need them to be exposed in ways are we need them to be exposed in ways are we need them to be exposed in ways where our agents can verify their work where our agents can verify their work where our agents can verify their work and prove that they have done such too and prove that they have done such too and prove that they have done such too and even then I've seen a few too many and even then I've seen a few too many and even then I've seen a few too many times where an agent shared a video of times where an agent shared a video of times where an agent shared a video of it proving the work it did is good just it proving the work it did is good just it proving the work it did is good just for the video to be obvious slop where

for the video to be obvious slop where for the video to be obvious slop where the thing didn't work at all. I cannot the thing didn't work at all. I cannot the thing didn't work at all. I cannot tell you how many times I've had to say, tell you how many times I've had to say, tell you how many times I've had to say, "Wait, the video you shared shows this "Wait, the video you shared shows this "Wait, the video you shared shows this not working. What did you see?" And then not working. What did you see?" And then not working. What did you see?" And then it realizes it got it wrong and it goes it realizes it got it wrong and it goes it realizes it got it wrong and it goes and fixes it. Another real hot take I and fixes it. Another real hot take I and fixes it. Another real hot take I have on this before we moved to Matt's have on this before we moved to Matt's have on this before we moved to Matt's post. I think if you have the bug speced post. I think if you have the bug speced post. I think if you have the bug speced out properly, like a detailed enough bug out properly, like a detailed enough bug out properly, like a detailed enough bug report that describes what is wrong and report that describes what is wrong and report that describes what is wrong and what the fix should look like and then what the fix should look like and then what the fix should look like and then add even the most minimal verification add even the most minimal verification add even the most minimal verification system there, the vast majority of system there, the vast majority of system there, the vast majority of frontier level agents and models can frontier level agents and models can frontier level agents and models can absolutely solve the bugs, too. They're absolutely solve the bugs, too. They're absolutely solve the bugs, too. They're not going to ship software without bugs. not going to ship software without bugs. not going to ship software without bugs. They're not going to preemptively find They're not going to preemptively find They're not going to preemptively find these bugs and fix them as often as we'd these bugs and fix them as often as we'd these bugs and fix them as often as we'd want. They're never going to ship want. They're never going to ship want. They're never going to ship bug-free software that's just not really bug-free software that's just not really bug-free software that's just not really possible. There will always be edges possible. There will always be edges possible. There will always be edges that you didn't plan for in your systems that you didn't plan for in your systems that you didn't plan for in your systems and in your verification. But if you and in your verification. But if you and in your verification. But if you make it easier and easier to identify make it easier and easier to identify make it easier and easier to identify these bugs and the models get smarter these bugs and the models get smarter these bugs and the models get smarter and smarter at fixing them, then yes, to and smarter at fixing them, then yes, to and smarter at fixing them, then yes, to some extent, bugs will start to be some extent, bugs will start to be some extent, bugs will start to be solved as well. Imagine a world where solved as well. Imagine a world where solved as well. Imagine a world where the agent starts working on the code. It the agent starts working on the code. It the agent starts working on the code. It makes the changes. It wants to test makes the changes. It wants to test makes the changes. It wants to test them. It realizes it can't because the them. It realizes it can't because the them. It realizes it can't because the repo isn't set up properly or its repo isn't set up properly or its repo isn't set up properly or its tooling isn't set up properly. So, it tooling isn't set up properly. So, it tooling isn't set up properly. So, it then goes and builds all the pieces it's then goes and builds all the pieces it's then goes and builds all the pieces it's missing in order to verify its own missing in order to verify its own missing in order to verify its own changes. I can't tell you how much time changes. I can't tell you how much time changes. I can't tell you how much time I've spent with T3 code setting up I've spent with T3 code setting up I've spent with T3 code setting up things so that the agent can actually things so that the agent can actually things so that the agent can actually spin up and test work as well as expose spin up and test work as well as expose spin up and test work as well as expose it to me. When I'm working remotely and it to me. When I'm working remotely and it to me. When I'm working remotely and I have my box set up over Tailscale on I have my box set up over Tailscale on I have my box set up over Tailscale on another machine and I want to see what another machine and I want to see what another machine and I want to see what changes it made in its dev server, I changes it made in its dev server, I changes it made in its dev server, I can't click a local host link when I'm can't click a local host link when I'm can't click a local host link when I'm on an entirely different network. I need on an entirely different network. I need on an entirely different network. I need it hosted through tail scale. So I it hosted through tail scale. So I it hosted through tail scale. So I actually made a lot of changes like actually made a lot of changes like actually made a lot of changes like thousands of lines of code changed in T3

thousands of lines of code changed in T3 thousands of lines of code changed in T3 code to make it easier to run the dev code to make it easier to run the dev code to make it easier to run the dev server over a tail scale environment server over a tail scale environment server over a tail scale environment while also pulling in a readonly while also pulling in a readonly while also pulling in a readonly snapshot of your existing data to make snapshot of your existing data to make snapshot of your existing data to make it a more useful test. These are the it a more useful test. These are the it a more useful test. These are the types of things I have done both to make types of things I have done both to make types of things I have done both to make it easier for me to verify the changes it easier for me to verify the changes it easier for me to verify the changes the agents made as well as for the the agents made as well as for the the agents made as well as for the agents to verify their own work too. In agents to verify their own work too. In agents to verify their own work too. In the future, agents can notice that they the future, agents can notice that they the future, agents can notice that they need these things and unblock themselves need these things and unblock themselves need these things and unblock themselves and make suggestions or even full-on and make suggestions or even full-on and make suggestions or even full-on create a new poll request just to set up create a new poll request just to set up create a new poll request just to set up your repo for them to catch bugs your repo for them to catch bugs your repo for them to catch bugs themselves, which will massively reduce themselves, which will massively reduce themselves, which will massively reduce the number of bugs that they are the number of bugs that they are the number of bugs that they are shipping. But until then, it's our shipping. But until then, it's our shipping. But until then, it's our responsibility and we need to build the responsibility and we need to build the responsibility and we need to build the systems the agents need to verify the systems the agents need to verify the systems the agents need to verify the bugs and we need to let the agents know bugs and we need to let the agents know bugs and we need to let the agents know when the bugs happen. And most when the bugs happen. And most when the bugs happen. And most importantly, we need to check the importantly, we need to check the importantly, we need to check the results, not necessarily the code. results, not necessarily the code. results, not necessarily the code. Because let's be real here, nobody would Because let's be real here, nobody would Because let's be real here, nobody would have caught this bug in code review have caught this bug in code review have caught this bug in code review because the code looks fine. If it because the code looks fine. If it because the code looks fine. If it didn't, the agents would have solved it. didn't, the agents would have solved it. didn't, the agents would have solved it. The era of finding bugs by just reading The era of finding bugs by just reading The era of finding bugs by just reading the code has, let's be real, ended. Any the code has, let's be real, ended. Any the code has, let's be real, ended. Any bug you notice from just reading code bug you notice from just reading code bug you notice from just reading code can almost certainly be noticed by the can almost certainly be noticed by the can almost certainly be noticed by the agents, too, and ideally noticed within agents, too, and ideally noticed within agents, too, and ideally noticed within their own development loops. But you their own development loops. But you their own development loops. But you still can notice a lot from reading the still can notice a lot from reading the still can notice a lot from reading the code, like architectural failures, not code, like architectural failures, not code, like architectural failures, not using something that you should have using something that you should have using something that you should have been, using something you shouldn't have been, using something you shouldn't have been, using something you shouldn't have been, touching a place that shouldn't be been, touching a place that shouldn't be been, touching a place that shouldn't be touched for these changes, writing tests touched for these changes, writing tests touched for these changes, writing tests that aren't necessary, not writing tests that aren't necessary, not writing tests that aren't necessary, not writing tests that are necessary. There's lots of that are necessary. There's lots of that are necessary. There's lots of things you can see in the code, but things you can see in the code, but things you can see in the code, but those aren't bugs in the traditional those aren't bugs in the traditional those aren't bugs in the traditional sense. And the bugs can absolutely be sense. And the bugs can absolutely be sense. And the bugs can absolutely be seen by an agent if the bugs are visible seen by an agent if the bugs are visible seen by an agent if the bugs are visible in the code itself. But sadly, a lot of in the code itself. But sadly, a lot of in the code itself. But sadly, a lot of bugs aren't, like the one we have here.

bugs aren't, like the one we have here. bugs aren't, like the one we have here. What that means is we need to be What that means is we need to be What that means is we need to be actually using the code or agents, actually using the code or agents, actually using the code or agents, right? We need to pull it down on our right? We need to pull it down on our right? We need to pull it down on our machines and test it and check it and machines and test it and check it and machines and test it and check it and make sure it solves the problem it's make sure it solves the problem it's make sure it solves the problem it's intended to at the absolute least we intended to at the absolute least we intended to at the absolute least we need the agent to show us that it did need the agent to show us that it did need the agent to show us that it did that itself. And until the agents can do that itself. And until the agents can do that itself. And until the agents can do that whole loop themselves, bugs are that whole loop themselves, bugs are that whole loop themselves, bugs are definitely not solved. So hopefully you definitely not solved. So hopefully you definitely not solved. So hopefully you now understand my stance on this and now understand my stance on this and now understand my stance on this and what I think Boris was saying. So let's what I think Boris was saying. So let's what I think Boris was saying. So let's wrap up by going through what Matt said wrap up by going through what Matt said wrap up by going through what Matt said as well as Boris's responses. Matt as well as Boris's responses. Matt as well as Boris's responses. Matt saying that this post reads like a saying that this post reads like a saying that this post reads like a vanilla ice cream of VC funding stirred vanilla ice cream of VC funding stirred vanilla ice cream of VC funding stirred with a little pinch of turd. I think with a little pinch of turd. I think with a little pinch of turd. I think this is a totally reasonable read of this is a totally reasonable read of this is a totally reasonable read of what Boris said because he said it in a what Boris said because he said it in a what Boris said because he said it in a in a way meant to ruffle feathers. in a way meant to ruffle feathers. in a way meant to ruffle feathers. That's what the whole coding is solved That's what the whole coding is solved That's what the whole coding is solved thing does. Especially if you have thing does. Especially if you have thing does. Especially if you have different definitions of coding. If one different definitions of coding. If one different definitions of coding. If one of these people is using coding as a of these people is using coding as a of these people is using coding as a term for what they're doing on the term for what they're doing on the term for what they're doing on the keyboard and the other is using it for keyboard and the other is using it for keyboard and the other is using it for the entire software development life the entire software development life the entire software development life cycle, they can't agree because they're cycle, they can't agree because they're cycle, they can't agree because they're arguing the same term with different arguing the same term with different arguing the same term with different meanings. But Boris didn't offer any meanings. But Boris didn't offer any meanings. But Boris didn't offer any clarity in his post here. So, it's a clarity in his post here. So, it's a clarity in his post here. So, it's a totally reasonable way to read it if you totally reasonable way to read it if you totally reasonable way to read it if you use coding as a way of describing the use coding as a way of describing the use coding as a way of describing the whole life cycle. Boris replied, "TBH, whole life cycle. Boris replied, "TBH, whole life cycle. Boris replied, "TBH, this is a good debate to have. Here's this is a good debate to have. Here's this is a good debate to have. Here's what the timeline of the near past and what the timeline of the near past and what the timeline of the near past and future looks like to him. One, models future looks like to him. One, models future looks like to him. One, models are able to code better than he can.

are able to code better than he can. are able to code better than he can. Two, models are able to do coding Two, models are able to do coding Two, models are able to do coding adjacent engineering work better than he adjacent engineering work better than he adjacent engineering work better than he can, like debugging, profiling, can, like debugging, profiling, can, like debugging, profiling, optimizing, bug fixing, system design, optimizing, bug fixing, system design, optimizing, bug fixing, system design, abstraction design, UI design, idea abstraction design, UI design, idea abstraction design, UI design, idea generation, etc. And eventually models generation, etc. And eventually models generation, etc. And eventually models are able to do most things that can be are able to do most things that can be are able to do most things that can be done on a computer better than most done on a computer better than most done on a computer better than most people. For the types of coding work people. For the types of coding work people. For the types of coding work that Boris does, Claude has achieved the that Boris does, Claude has achieved the that Boris does, Claude has achieved the first, which is that models are coding first, which is that models are coding first, which is that models are coding better than he does and some, but not better than he does and some, but not better than he does and some, but not all of two, which is that they can do all of two, which is that they can do all of two, which is that they can do coding adjacent things like system coding adjacent things like system coding adjacent things like system design, bug fixing, optimizing, design, bug fixing, optimizing, design, bug fixing, optimizing, profiling, debugging, etc. But it's only profiling, debugging, etc. But it's only profiling, debugging, etc. But it's only starting to show early signs of three, starting to show early signs of three, starting to show early signs of three, which is doing most things doable on which is doing most things doable on which is doing most things doable on computers better than people. This is computers better than people. This is computers better than people. This is not the case for all of coding yet. If not the case for all of coding yet. If not the case for all of coding yet. If you're Andarus Hellsburg and are a you're Andarus Hellsburg and are a you're Andarus Hellsburg and are a worldclass expert in compilers and type worldclass expert in compilers and type worldclass expert in compilers and type systems, Claude might not be at one yet. systems, Claude might not be at one yet. systems, Claude might not be at one yet. Boris is betting that it will get there Boris is betting that it will get there Boris is betting that it will get there quite soon while at the same time quite soon while at the same time quite soon while at the same time pushing further into two to three pushing further into two to three pushing further into two to three territory for the rest of the world. I territory for the rest of the world. I territory for the rest of the world. I would argue that we are actually would argue that we are actually would argue that we are actually surprisingly far into one for those surprisingly far into one for those surprisingly far into one for those types of god engineers. I know that for types of god engineers. I know that for types of god engineers. I know that for example Ryan Carneato has been going example Ryan Carneato has been going example Ryan Carneato has been going more and more deep into fable and more and more deep into fable and more and more deep into fable and realizing that he can use it not just to realizing that he can use it not just to realizing that he can use it not just to like make small changes to the framework like make small changes to the framework like make small changes to the framework he built solid.js s but to actually talk he built solid.js s but to actually talk he built solid.js s but to actually talk out complex ideas and test theories that out complex ideas and test theories that out complex ideas and test theories that would have been too timeconuming for him would have been too timeconuming for him would have been too timeconuming for him to do. So I am seeing more and more of to do. So I am seeing more and more of to do. So I am seeing more and more of like the top upper echelon best like the top upper echelon best like the top upper echelon best engineers in the world realizing that engineers in the world realizing that engineers in the world realizing that they can utilize these agents to do a they can utilize these agents to do a they can utilize these agents to do a lot of coding work not like as lot of coding work not like as lot of coding work not like as incredible as them but close enough to incredible as them but close enough to incredible as them but close enough to it with a lot more parallelism that lets it with a lot more parallelism that lets it with a lot more parallelism that lets them test things that they would not them test things that they would not them test things that they would not have been able to otherwise. Back to have been able to otherwise. Back to have been able to otherwise. Back to what Boris said here. You can think of what Boris said here. You can think of what Boris said here. You can think of model capabilities as capturing the

model capabilities as capturing the model capabilities as capturing the distribution of human ability. I distribution of human ability. I distribution of human ability. I consider myself an average programmer. consider myself an average programmer. consider myself an average programmer. So Claude has already surpassed me. The So Claude has already surpassed me. The So Claude has already surpassed me. The same is not yet true for everyone. Back same is not yet true for everyone. Back same is not yet true for everyone. Back in November last year, Boris fully in November last year, Boris fully in November last year, Boris fully stopped writing code by hand. Though he stopped writing code by hand. Though he stopped writing code by hand. Though he continues to code using agents every continues to code using agents every continues to code using agents every day. That's the point where for him and day. That's the point where for him and day. That's the point where for him and many others around him, it felt fair to many others around him, it felt fair to many others around him, it felt fair to say that coding is solved. But say that coding is solved. But say that coding is solved. But engineering is more than coding. engineering is more than coding. engineering is more than coding. Claude's code is not perfect. It has Claude's code is not perfect. It has Claude's code is not perfect. It has bugs and inefficiencies. Bod can code, bugs and inefficiencies. Bod can code, bugs and inefficiencies. Bod can code, but it cannot yet do everything that but it cannot yet do everything that but it cannot yet do everything that goes into engineering. I swear I did not goes into engineering. I swear I did not goes into engineering. I swear I did not read this before deciding to make this read this before deciding to make this read this before deciding to make this video or filming the section before. video or filming the section before. video or filming the section before. It's funny that he makes the same It's funny that he makes the same It's funny that he makes the same distinction, but again, I had a feeling distinction, but again, I had a feeling distinction, but again, I had a feeling that's what he meant. Opus 48 was the that's what he meant. Opus 48 was the that's what he meant. Opus 48 was the first model that felt like it could be first model that felt like it could be first model that felt like it could be better than he was. Babel now routinely better than he was. Babel now routinely better than he was. Babel now routinely finds optimizations and debugs issues finds optimizations and debugs issues finds optimizations and debugs issues that would have not been able to be that would have not been able to be that would have not been able to be found by Boris himself. And with each found by Boris himself. And with each found by Boris himself. And with each generation, the code the model produces generation, the code the model produces generation, the code the model produces continues to improve and the model's continues to improve and the model's continues to improve and the model's able to do more of the non-coding parts able to do more of the non-coding parts able to do more of the non-coding parts of engineering. Similar to how I had of engineering. Similar to how I had of engineering. Similar to how I had pushed back on Boris earlier with his pushed back on Boris earlier with his pushed back on Boris earlier with his definition of bug, because he said that definition of bug, because he said that definition of bug, because he said that it wasn't wasn't a bug, it was a UX it wasn't wasn't a bug, it was a UX it wasn't wasn't a bug, it was a UX issue. Matt's asking for his definition issue. Matt's asking for his definition issue. Matt's asking for his definition of coding. He cites John Asterhout's of coding. He cites John Asterhout's of coding. He cites John Asterhout's definition of tactical versus strategic definition of tactical versus strategic definition of tactical versus strategic programming. Tactical is the on the programming. Tactical is the on the programming. Tactical is the on the ground day-to-day aspects of coding, and ground day-to-day aspects of coding, and ground day-to-day aspects of coding, and strategic is the long-term stuff like strategic is the long-term stuff like strategic is the long-term stuff like codebased health, architectural design, codebased health, architectural design, codebased health, architectural design, making the right decisions. Matt agrees making the right decisions. Matt agrees making the right decisions. Matt agrees that AI's largely solved tactical that AI's largely solved tactical that AI's largely solved tactical programming, but he has seen no evidence programming, but he has seen no evidence programming, but he has seen no evidence that it can think strategically.

that it can think strategically. that it can think strategically. Asterout talks about some employees as Asterout talks about some employees as Asterout talks about some employees as tactical tornadoes, able to churn out tactical tornadoes, able to churn out tactical tornadoes, able to churn out astonishing amounts of work with zero astonishing amounts of work with zero astonishing amounts of work with zero high for the future, and that's how high for the future, and that's how high for the future, and that's how agents feel to him right now. I largely agents feel to him right now. I largely agents feel to him right now. I largely agree. I don't think agents will agree. I don't think agents will agree. I don't think agents will preemptively, proactively do good with preemptively, proactively do good with preemptively, proactively do good with strategic planning of codebase health strategic planning of codebase health strategic planning of codebase health and architecture over time, but I do and architecture over time, but I do and architecture over time, but I do think they can be useful resources think they can be useful resources think they can be useful resources during that workflow. If you ask agents during that workflow. If you ask agents during that workflow. If you ask agents to look into these things and give you to look into these things and give you to look into these things and give you feedback on how your architecture looks feedback on how your architecture looks feedback on how your architecture looks or what changes you're planning on or what changes you're planning on or what changes you're planning on making and you can even have it making and you can even have it making and you can even have it investigate theories to prove ideas you investigate theories to prove ideas you investigate theories to prove ideas you have out too. There's a lot of power to have out too. There's a lot of power to have out too. There's a lot of power to be had with agents helping you as be had with agents helping you as be had with agents helping you as consultants when you plan your strategy. consultants when you plan your strategy. consultants when you plan your strategy. And then once you've done all of the And then once you've done all of the And then once you've done all of the strategizing and you have a plan you're strategizing and you have a plan you're strategizing and you have a plan you're confident in and you give your agents confident in and you give your agents confident in and you give your agents the things they need to verify their the things they need to verify their the things they need to verify their outputs, all of a sudden they can go outputs, all of a sudden they can go outputs, all of a sudden they can go execute a crazy bold plan in time that execute a crazy bold plan in time that execute a crazy bold plan in time that makes no sense at all. It's truly makes no sense at all. It's truly makes no sense at all. It's truly unbelievable how fast these agents can unbelievable how fast these agents can unbelievable how fast these agents can work if you set them up for success, work if you set them up for success, work if you set them up for success, which uh spoiler has almost always been which uh spoiler has almost always been which uh spoiler has almost always been the case with engineering. If you set up the case with engineering. If you set up the case with engineering. If you set up your systems in a way where everyone at your systems in a way where everyone at your systems in a way where everyone at the company could easily pull down the company could easily pull down the company could easily pull down someone else's changes and verify that someone else's changes and verify that someone else's changes and verify that they fix the issues they have, where they fix the issues they have, where they fix the issues they have, where it's easy to make those changes and find it's easy to make those changes and find it's easy to make those changes and find where in the code base is relevant to where in the code base is relevant to where in the code base is relevant to the stuff that you're doing, making it the stuff that you're doing, making it the stuff that you're doing, making it easy to actually put the code up for easy to actually put the code up for easy to actually put the code up for review and to get it approved and review and to get it approved and review and to get it approved and shipped and rolled back if it does break shipped and rolled back if it does break shipped and rolled back if it does break things. All of these decisions you make things. All of these decisions you make things. All of these decisions you make around how the day-to-day works in your around how the day-to-day works in your around how the day-to-day works in your codebase would have made engineers more codebase would have made engineers more codebase would have made engineers more effective when you brought them in. And

effective when you brought them in. And effective when you brought them in. And you can bet your ass they're going to you can bet your ass they're going to you can bet your ass they're going to make the agents more effective, too. make the agents more effective, too. make the agents more effective, too. It's actually really funny reading all It's actually really funny reading all It's actually really funny reading all of this because I swear I had the whole of this because I swear I had the whole of this because I swear I had the whole video planned before I did and they were video planned before I did and they were video planned before I did and they were doing this back and forth right now. But doing this back and forth right now. But doing this back and forth right now. But it really does line up with what I was it really does line up with what I was it really does line up with what I was saying there where Boris splits coding saying there where Boris splits coding saying there where Boris splits coding and programming up as the act of writing and programming up as the act of writing and programming up as the act of writing code and engineering as everything else code and engineering as everything else code and engineering as everything else in addition to that. Tactical and in addition to that. Tactical and in addition to that. Tactical and strategic is another reasonable split. strategic is another reasonable split. strategic is another reasonable split. He does see some parts of strategic He does see some parts of strategic He does see some parts of strategic coding being automated like when they're coding being automated like when they're coding being automated like when they're starting to automatically maintain apps starting to automatically maintain apps starting to automatically maintain apps at Anthropic. Recently a number of the at Anthropic. Recently a number of the at Anthropic. Recently a number of the customers are too. We haven't bit this customers are too. We haven't bit this customers are too. We haven't bit this bullet quite yet at T3 Code. I'll still bullet quite yet at T3 Code. I'll still bullet quite yet at T3 Code. I'll still screenshot the tweet and go post it into screenshot the tweet and go post it into screenshot the tweet and go post it into T3 Code myself. I won't have the agents T3 Code myself. I won't have the agents T3 Code myself. I won't have the agents propose fixes based on what people are propose fixes based on what people are propose fixes based on what people are tweeting yet. Matt calls out that he tweeting yet. Matt calls out that he tweeting yet. Matt calls out that he agrees partially on the strategic coding agrees partially on the strategic coding agrees partially on the strategic coding being automated thing, saying that being automated thing, saying that being automated thing, saying that people are building pipelines like bug people are building pipelines like bug people are building pipelines like bug report to repro to fix feature request report to repro to fix feature request report to repro to fix feature request to prototype or cron to codebase to prototype or cron to codebase to prototype or cron to codebase architecture RFC to refactor. Managing architecture RFC to refactor. Managing architecture RFC to refactor. Managing these pipelines is very much a strategic these pipelines is very much a strategic these pipelines is very much a strategic concern, one that a human needs to apply concern, one that a human needs to apply concern, one that a human needs to apply their judgment to. Absolutely agree. In their judgment to. Absolutely agree. In their judgment to. Absolutely agree. In order to make your agents act more order to make your agents act more order to make your agents act more strategic and act more like engineers, strategic and act more like engineers, strategic and act more like engineers, you have to do the engineering upfront you have to do the engineering upfront you have to do the engineering upfront yourself. The agents can help you as you yourself. The agents can help you as you yourself. The agents can help you as you do it, but if you want the agents to be do it, but if you want the agents to be do it, but if you want the agents to be able to do these awesome things, you able to do these awesome things, you able to do these awesome things, you have to set them up for success. Man, I have to set them up for success. Man, I have to set them up for success. Man, I thought this was going to be a quick thought this was going to be a quick thought this was going to be a quick 15-minute video, and I'm looking at the 15-minute video, and I'm looking at the 15-minute video, and I'm looking at the timer and realizing it wasn't.

timer and realizing it wasn't. timer and realizing it wasn't. Thankfully, I filmed this offline for Thankfully, I filmed this offline for Thankfully, I filmed this offline for once. I know usually my videos are done once. I know usually my videos are done once. I know usually my videos are done on stream, but uh cast. Okay, I didn't on stream, but uh cast. Okay, I didn't on stream, but uh cast. Okay, I didn't feel like going live today and just feel like going live today and just feel like going live today and just wanted to talk about the stuff that was wanted to talk about the stuff that was wanted to talk about the stuff that was interesting to me. And I hope you interesting to me. And I hope you interesting to me. And I hope you enjoyed it. This is quite a fun deep enjoyed it. This is quite a fun deep enjoyed it. This is quite a fun deep dive into all these things that I've dive into all these things that I've dive into all these things that I've already been thinking about and I love already been thinking about and I love already been thinking about and I love the excuse that both Boris and Matt gave the excuse that both Boris and Matt gave the excuse that both Boris and Matt gave me to talk more about it. I'm curious me to talk more about it. I'm curious me to talk more about it. I'm curious how y'all feel. Am I being crazy saying how y'all feel. Am I being crazy saying how y'all feel. Am I being crazy saying that engineering is still unsolved and that engineering is still unsolved and that engineering is still unsolved and coding is solved? Am I going too far by coding is solved? Am I going too far by coding is solved? Am I going too far by saying coding is solved? Or am I not saying coding is solved? Or am I not saying coding is solved? Or am I not going far enough by saying engineering going far enough by saying engineering going far enough by saying engineering is still largely a human task? Let me is still largely a human task? Let me is still largely a human task? Let me know how you feel and where you guys are know how you feel and where you guys are know how you feel and where you guys are at in your real world work.