Anthropic's Boris Cherny on Cloud Code and the Future of AI-Driven Software Development

Source material

Transcript

Okay, I'm excited to introduce our next speaker.

Show of hands who here uses Cloud Code.

Okay, show of hands who here has Cloud Code psychosis.

Come on guys, okay, it's okay.

My team of lovingly says I have Cloud Code psychosis, which may or may not be true.

We're delighted to have Boris turning with us today.

Boris is the creator, the father of Cloud Code.

And the process of doing that has just had a front row seat to reinventing the mother-in-way of software development.

And we're really grateful to you, Boris.

We're taking the time to speak with us today.

We know that the entirety of software development kind of rests on your shoulders.

So thank you for taking it out of your time to be with us today.

And everyone Boris is Lauren Reader from our team.

Thank you.

Thank you.

Thank you.

Thank you.

Thank you.

Thank you.

You took my opening line as we ask who here uses Cloud Code.

Those are a lot of hands.

It's awesome.

Thank you for joining us, Boris.

It's very special to have you here.

As a room full of builders, I think you are changing building entirely.

And so I'm very curious to explore how you think about the future of software, coding, and what we should spend all of our free time on.

But I'll give them a tiny bit more background on you, so that everyone has a little bit more context.

And I think it's very important to be able to create a cloud code.

Boris is very much an engineer's engineer.

You were writing a lot of code through your whole career, writing textbooks about code, including programming and text script.

And I think last time we chatted, you hadn't written a single line of code in the last year, or at least so far in 2026, which is quite the change.

Is also a little known thing back in middle school.

I wrote a guide about writing basic for TI 83 plus calculators.

I just, I search is actually still on the internet.

It's extremely embarrassing, so please don't search it.

We will definitely be finding that.

So we're going to do, I'm going to start with a few questions here.

Maybe we'll start with a little bit of the history of cloud code, how you started it.

And then we're going to have a lot of audience Q and A for this one.

So we'll start thinking about your questions in the back of your head, and we'd love to turn it over to you all soon.

Yeah.

And also real quick, so for people that use cloud code, do people use this ELI, mostly?

Majority?

Majority desktop?

Majority VS code, or Jeopardy, ID?

Okay.

That's actually not a lot.

Okay.

Other?

I'm like iOS, mostly.

These days.

Yeah.

Okay.

Cool.

Yeah.

So I started cloud code kind of accidentally in a lot of ways.

I joined this team back in late 2024.

It was sort of this incubator within Anthropocode and Thropic Labs.

And the team kind of served its purpose.

We created cloud code, MCP, and the desktop app.

It was a team.

It was just a few of us.

So very much like innovation team.

We built the thing that we wanted to build.

We disbanded the team.

Now the team's actually back together for round two.

My Krieger, who's the chief product officer at Anthropoc, and used to be one of the founders at Instagram.

So he's waiting that right now.

So the kind of the reason that I started to work on coding is we felt like there was this product overhang.

And I'm guessing people here use that word a lot.

But we definitely use this word a lot in kind of within the lab.

There's this idea that the model can do all this stuff that no product has yet captured.

And in late 2024, when we were looking at coding, the way that we did coding, the state of the art at the time was type of head.

Because you open your ID and your press tab then you can like complete like one line out of time.

And that was the thing that's taught it 3.5 enabled for the first time.

But the feeling was we could actually go a lot further than that.

And the model was almost ready for the next big step.

So we don't have to do type of head anymore.

We can just have the agent write all of the code.

And so I built it.

And it just really didn't work for the first six months.

It was like not very good.

It was barely usable.

I wrote it from I used it for maybe 10% of my code or something like that.

And even after we released quadcode initially, it was not a hit.

There's a lot of people that used it.

But it did not have this exponential growth that it has today.

That started with Opus 4 in May.

And I remember that very clearly.

That's like when the exponential goes started and then it kind of Infected with every model of release.

Like it started with Opus 4, then 4.5, then 4.6, now 4.7.

It just kind of keeps inflecting.

But essentially we were trying to build this thing.

That was like pre PMF.

And we knew that it wouldn't have PMF for six months.

Because we were building for the next model.

And that was the idea.

Pretty much the whole time.

And you know, for anthropic in general, we've always just been very focused.

We've always cared about business and enterprise and safety and coding.

That's just always been kind of the way that we wanted to build.

And so at some point we kind of knew that we wanted to build a product.

We didn't know exactly one.

So this kind of ended up being the product that.

It's an incredible story, especially that it was an accident.

So you've said on the record that you think coding is solved.

If this is one of the three best philanthropic, can you tell us more about what you mean by that?

And what might still not be solved, or what secondary problems might come?

All right.

I'm going to ask another question for the room.

Who writes a hundred percent of their code by hand?

Who writes a hundred percent of their code using a agent?

Like quad code?

Okay.

Who's somewhere in between?

Okay.

So like 50 percent solved.

For me, it's like, for me, it's a hundred percent.

Like the quad code code base, you know, it leaked.

So, you know, people know.

It's pretty simple.

It's just like typescript and it's react.

Like there's no big secret.

There's nothing really complicated.

The reason we picked typescript and react is it's very on distribution for the model.

So when we started building the code base, the model was not as intelligent as it is today.

So the language and the framework mattered a lot.

Nowadays, you know, it can write whatever.

And it can pick up new languages and frameworks.

It hasn't seen.

But back then, you wanted to something pretty on distribution.

Because of that, I think fairly early, we got to the point where the model just wrote a hundred percent of the code.

And for us, this happened sometime in October, November or last year.

And so for me today, you know, like the model writes a hundred percent of my code.

I write somewhere, you know, usually a few dozen PRs every day.

There was a day last week I did like 150 PRs in a day.

Those are recordos just from kind of push to see how far I can get it.

But yeah, it's like for me, for me, it's just solved.

But this is not the case everywhere.

There's very big complicated code bases.

There's kind of weird languages.

The model's not good at yet.

And you know, as everyone can know, it's getting there.

Usually, the answer is just wait for the next model.

Can you actually tell us about your personal setup?

And you walked us through it the other day.

It is pretty wild.

Yeah.

So I shared my personal setup like six months ago or something on Twitter.

And it's funny.

I actually, I shared it.

I didn't realize that it would be surprising for anyone.

That was just like the way that I coded.

And it's changed.

It's changed.

And so now, actually, most of my work, I do for my phone.

And so, I don't know, like, you guys won't be able to see this.

But I have, so I have like the quad app.

And if you open the quad app on the left hand side, there's this little code tab.

And I just have a bunch of sessions going.

You probably can see it.

How many sessions?

Usually, I have like maybe like five to ten sessions.

And then the sessions usually have a bunch of agents.

So I think currently probably like a few hundred agents going.

Usually every night, I have like a few thousand that are doing kind of deeper work.

There's a few ways to manage it.

One is that you ask Cloud to use a bunch of subagents to do work.

Actually, the thing that I've been finding myself using more and more is loop.

So this is slash loop.

And it's just like the coolest thing.

It's like the simplest thing that works.

All it is is you have Cloud used Cron to schedule a job for some point in the future.

And it's a repeat job.

And it can run every, every minute, every five minutes, every day, kind of, however, often you want to schedule it.

And at this point, I have like dozens of loops that are running for stuff.

So I have one that's babysitting my PRs, like fixing CI auto rebasing.

I have another one that keeps CI healthy.

So like if there's like a flaky tester, whatever, it'll go and fix it.

I have another one that grabs feedback from Twitter and kind of clusters it for me every 30 minutes.

So I just have a bunch of these loops running at any time.

I sort of feel like loops are the future at this point.

If you have an experimented with it, highly recommend it.

And we also just want to routines, which is the same thing, but kind of on the server.

So even if you close your laptop, it keeps going.

So that's your personal setup.

Tell us about what you think teams will look like in the future.

How do you extrapolate from all the work you're doing to keep everyone on the team moving forward, understanding the context, or do you think we need to let go of a lot more to agents to make it work?

I think, you know, it's so hard to make predictions, but I'm here to make predictions.

So I'll try to make some.

I feel like the way that things are going is generally, there's going to be a lot more generalists than there are today.

And today when we talk about generalists, I think largely we're talking about people that are still engineers.

So they're still writing code, but maybe they're kind of product engineers.

So maybe when we say generalists, it's like a, you know, they do iOS and web and server, for example.

That's like a generalist and engineering.

But I think the thing that we're going to start to see a lot more of is generalists that are cross disciplinary.

So this is engineers that are really good at product engineering, but also really great at design or really great at product and data science and engineering.

I don't know, is something that we're starting to see on our team.

So actually like a lot of people on the quad code team are generalists across disciplines, everyone on our team code.

So like our engineering manager or product manager or designers or data scientists or finance guy or user researcher, every single person on our team writes code.

And so, you know, like there's specialists in something, but now also everyone's just coding.

And, you know, I'm seeing some nods, but I bet also it's actually not that surprising to people in this room because I bet you're seeing the same things.

One more third of questions and we'll open up the audience.

So we talked a bit about what's changing with coding.

I'm curious about what you see changing in the world of software or software products.

I think as we see AI making writing code 10 or 100x cheaper.

What happens to the value of the products that are produced with software?

Do we have a SaaS apocalypse on our hands?

How do you think this plays out?

And again, you're going to have to make another prediction.

The SaaS apocalypse question is my favorite question then.

I think there's two things that are going to happen.

And I don't think either of them is the thing that people have been talking about.

I think one is, is anyone here an acquired listener?

Like the acquired podcast?

Yeah, it's like the best podcast.

I actually, I got to do a unplugged with them the other week.

And I just, I felt like I got to meet my heroes because they're just like the hosts are the best.

So they have this idea of seven powers.

And this is like Hamilton, he kind of wrote a book about this.

And this is kind of the seven modes in business.

And I think what's going to happen is because of AI, some of these modes are going to get more important.

And some are going to get less important.

And so like for example, one that gets less important is switching costs because you can just use the model.

And you can kind of port from one thing to a different thing.

Another one that gets less important is process power.

Because for companies whose mode is like workloads and process and things like this, Cloud is getting really good at figuring out process.

And especially with 4.7, it can just help climb anything.

So if you give it a target and you tell it to iterate until it's done, it will just do it.

I think this is the first model like that.

So I think these are going to get less important.

But I think the previous modes actually still matter.

So this is like network effects, scale economy, cornered resources, things like that.

These are not really changing with AI.

I think the second thing is if you look at the numbers startups today, or maybe in the next, you know, the past 10 years, I think the number of startups in the next 10 years that are just going to like disrupt everything, is going to increase like 10x.

Because right now you can be a tiny startup.

You could build a thing that's as valuable as a large company.

And you can actually compete head-to-head.

Because the large company has to evolve their business process.

They have to evolve the way they work.

They have to retrain everyone to technology.

They're going to face a lot of internal resistance to that.

But, you know, no one here has that problem.

If you're starting fresh, then you can kind of build with AI natively from the ground up.

So I don't know.

I think it's the best time to build.

It's the best time to be a startup.

There's so much disruption coming.

So there is hope for us after all.

Thank you, Boris.

I would love to open up to audience questions if anyone has anything they would like to ask.

Dan.

Hi.

Yeah, I'm curious.

You said that you built six months before there is product market fit.

But now, given that the models are good enough, how much do you treat the success of cloud code to the model versus like product decisions?

Oh, like, feel the product.

I think it's probably a mix.

Yeah, I think it's a mix.

I think if you asked maybe a year ago, the ratio was maybe something like 50-50.

Maybe, I don't know, if you asked me six months ago, the mix would be 50-50.

What about in two years?

Oh, two, I don't know.

Do we plan on like, when we plan one week?

Six months, some time in the future.

By the way, I think the reason was 50-50 is, you know, I did YC back in the day.

I was like the first hire at a YC company, and I did a bunch of startups.

And it started up like the thing that they drew into, and especially in YC over and over, is build something people love.

And so it doesn't matter what the product is.

It doesn't matter like the model and all the stuff.

You still in the end have to build a thing that people love.

And I think that's why the product matters.

We pay so much attention to the little details, so that as you use it all day, it's a really great experience.

I think as the model's gotten better, the harness kind of gets less important.

And I think like, I think that we're thinking about it.

And I was like, how do we evolve the harness?

So like, how do we make loops more of a first-class thing?

How do we make it easier to run a lot of agents?

You know, besides, you know, these agents is one idea.

There's a bunch more stuff that we're cooking.

But I think in a year, the model will be much better aligned.

And so all the safety mechanisms that we have today around prompt injection and kind of static verification of commands and permission modes, human and the loop, all this kind of stuff is just going to be less important because the model will just do the right thing.

So yeah, that's my prediction.

Thanks.

You want to toss the box down?

Great.

To zoom out a little bit from software, I think Claude Cod did a cultural change a few months ago where it democratized building software.

You can see shop owners building their own software for themselves or even programming microcontrollers to control the light when someone opens it.

Do you see in the future building software becoming a skill like I know a Microsoft office?

So it's a thing that everybody can do, not just people in the tech industry.

Oh my god, yes, yes, yes.

I think it's going to be even more than that.

I think it's going to be, I don't know, it's going to be a skill like yeah, like I know how to send a text message.

I think I read my two genres or essentially sci-fi in tech history.

This is what I read a lot of.

I think in tech history there's one thing which I think to me is the clearest parallel for what's happening right now.

And this is in the 1400s, the printing press in Europe.

And what happened was before the printing press, essentially 10% of the European population was literate.

They knew how to read and write.

They were often employed by like kings and wards that were not literate.

And they're jobless to read and write.

And this is not something that everyone knew how to do.

The printing press was invented, then there were two more presses.

And in the 50 years after the first printing press, there was more literature published in Europe than in the 1000 years before.

And over the same period, the cost of literature, the cost of a book went down like 100x.

And then it took a couple hundred years because we're going to read and write as hard.

You need education systems and government and everyone can't be working on farms and so on.

But over the next few hundred years, literacy globally went up to 70%.

And so now we can all read and write.

And you don't need a degree in reading and writing to not have to read and write.

Although still there are professional writers and that is the thing that you can do.

So I think the thing that's about to happen and it's going to be much faster than 50 years is software will be a thing that is fully democratized that anyone can do.

And there's a lot of core areas to this.

So for example, what's your writing accounting software?

The best person to write accounting software, I think maybe even today is not an engineer.

It's a really good accountant.

Because they know the domain really well and coding is the easy part.

It's knowing the domain that's the hard part.

And I think this is just obviously the future.

So one of the things Greg said was that you guys are living in the future a little bit because you get to have access to the models and the agents.

Code code is an internal tool before you release it.

Is the gap between where you guys are and engineering and the rest of the world?

Is that a month?

Is it three months?

Is that gap getting bigger or smaller over time?

Yeah.

So internally we use the same models everyone else does.

For us, the dog fooding is really, really important.

So we use the thing that everyone else here does.

We use like a little bit of mythos to try it and then we use a lot of opus 4.7 to dog food it and to write most of our code.

I think on the model side, there isn't really gap.

It's pretty much mythos and that will become some version of some dissentant of that will become available at some point to everyone.

I think on the product side, there's probably a far larger gap.

And that's just related to us changing all of our processes.

Like if you talk to people at anthropic, we use code for a literary everything.

And our cloths are talking all day, like as I'm coding, as my cloths are coding in a loop, they will communicate over slack to talk to other people's cloths that are also running in a loop to kind of figure out unknowns.

We have no more menu we written code anywhere at the company.

All of the SQL is written by models.

Everything is just built by the models.

So I think actually the place that we're head is not that technology, because the same technology available to us is available to everyone here because fundamentally we are building a platform.

And so for us, it's really important that developers can use the same thing that we're using and that we dog food everything that we put out there.

But I think there's actually a far bigger way in kind of the organizational structure and organizational process.

And this is a place where, you know, hopefully we can talk about it in places like this and everyone can kind of learn from it and also evolve.

Yeah, and I think that's one of the advantages to start up, it's so much easier to start there.

Jurn.

Yeah, last time we talked, I think you mentioned, we talked a little bit about multi agent and I was very encoded at the time at a prior square event.

And you mentioned that there were some things going on the pipeline, there's a thing you're talking, you're thinking about.

Now obviously there's slash batch, there's slash loop, there's sub teams, you speak some to either at the model level and at the harness level, how you're injecting priors and the horse level, how the objective functions change in the model level, to kind of make this experience around delegating work, spinning up agents better, because so much of the work is paralysable.

You can do so many things so much faster and I feel like I have to overlay my own intuition for when to paralyze things rather than the model kind of understanding that you can spin up tens of agents or something.

Yeah, I mean on the product side, it really just comes down to prompting.

That's how it is.

We tweak prompts to kind of help the model, do stuff in parallel more.

But it also honestly, as the model gets better, it just naturally does this.

And so something like loop, I found actually 4.7, it just starts doing, which is really cool.

It's like, it does something like, you know, I'll tell a goal, pull this data query, and it's like, hey, I noticed that the data is changing over time.

I'll start a loop, and I'll give you a report every 30 minutes.

And I'm like, can you send it to me over Spark?

And then it uses this VACMCP to do that.

So I think actually over time, it's not on users to figure out how to hold the tools better.

And if that's the case, it's actually a product design problem, and like, I'm not doing a good job.

It's really on the model to do this stuff better, and on us kind of prompting it, so it naturally does this.

So right now, it seems like a lot of us use, like, cloud or codex or these tools in the cloud to do a lot of our computing, but then there are some very vocal advocates of, have your AI be local, and I could imagine over time, as open-way models and other things catch up, that this could be more of a possibility for people to get really high quality coding assistance.

So I'm curious your vision of, say over the next, like, years or something like that, do you see the trajectory of everyone still really relying on the, like, cloud centralized compute, or is there a pivot to, oh, we all just have our local agents that we can rely on, and they don't get throttled in other benefits.

Yeah, I think it, I don't know, there's maybe a few ways to answer that.

I think maybe the most fundamental way to answer that is it doesn't matter, because I think now we're getting to the point where the models just able to figure it out.

So I think like, by a couple years or so, the models just can be doing all the code is it's going to be starting the agents, it's going to be building the environments.

And so like if it decides, like actual use like local models to do this, you know, that's what it'll do.

I don't think these will be decisions that we are making as engineers anymore.

We have time for a couple more questions, so I can toss this out.

Jamie?

Mr. Thank you.

It feels like one of the great decisions with Cloud Code was making use of the fact that a lot of developers, tools and workflows are local.

But that isn't necessarily always the case for sort of general knowledge work with, you know, cloud tools.

I'm curious how you're thinking about this with co-work of how do you give co-work enough access to the tools that we use to be powerful the same way the cloud code is for developers.

Yeah, that's a really great question.

I know when I was at a big company, we took like five years moving all the environments to promote.

It's just like so much work, especially out of big scale.

But for knowledge work largely, it's there already with a sales force and docs and things like that.

For us, it's always just the simplest answer.

It's just MCP.

So the same MCP connector that you have in Claudia, you hook up like sales force, you hook up Google Docs, Google Calendar.

And then co-work and use that QuadsayLike and use it, quadcode everywhere can use it.

For the systems that don't have MCP, do you think that's where computer use is going to be a big opportunity?

Yeah, I think computer use is kind of a catch-all.

So I think currently, as far as I know, I think anthropic is like pretty far ahead on computers, and so if you use it through co-work, it's quite good.

So it's able to use pretty much any piece of software that you have on your computer.

It's very slow, but it does quite well now, especially with 4.7.

Yeah, but I think otherwise, like MCP is kind of the answer.

And all this stuff just doesn't matter.

That much, it could be MCP, CLIs, APIs, just some sort of programmatic access because the model doesn't care, is to the model is just tokens.

All right, we have time for one more question.

Ryan, Sean, do you want to pass the question?

Thank you.

You've kind of alluded to this, but if like some time ago, you saw the product overhang and thought to build a product that would then become more interesting, once the model's got better, can you just talk even in vague terms about the shape of a product you built today that you think could become so much more interesting as models get better in six months or two years?

Yeah, cloud design.

I think is a really good example.

It's pretty good today.

It's going to get a lot better.

There's also a few things that we're cooking out for cloud code that are going to be landing over the coming weeks.

We'll see those.

And then I think I think loop and batch and things like this around massively paralyzing agents that's going to get better.

I think computer use is another good one.

All right, Boris.

Thank you so much for joining us.

I think we'll be here for the longer, if anyone's question.

Thanks, guys.