Anthropic's CPO on what comes next | Mike Krieger (co-founder of Instagram)

90% of your code roughly is written by AI now. The team that works in the most futuristic way is the Cloud Code team. They're using Cloud Code to build Cloud Code in a very self-improving kind of way. We really rapidly became bottlenecked on other things like our merge queue.

to completely re-architect it because so much more code was being written and so many more pull requests were being submitted over half of our pull requests are cloud code generated probably at this point it's probably over 70 that it just completely blew out the expectations of it you guys are at the edge of where things are heading

I had the very bizarre experience of I had two tabs open. It was AI 2027 and my product strategy. And it was this like moment where I'm like, wait, am I the character in the story? It feels like ChatGPT is just winning in consumer mindshare. How does that inform the way you think about product strategy?

I think there's room for several generationally important companies to be built in AI right now. How do we figure out what we want to be when we grow up versus like what we currently aren't or wish that we were or like see other players in the space being? What's something that you've changed?

your mind about what AI is capable of and where AI is heading. I had this notion coming in like, yes, these models are great, but are they able to have an independent opinion? And it's actually really flipped for me only in the last month. Today, my guest is Mike Krieger. Mike is Chief Product Officer at Anthropic, the company behind Claude. He's also the co-founder of Instagram.

He's one of my most favorite product builders and thinkers. He's also now leading product at one of the most important companies in the world. And I'm so thrilled to have had a chance to chat with him on the podcast. We chat about what he's changed his mind about most in terms of AI capabilities in the

years since he joined Anthropic, how product development changes and where bottlenecks emerge when 90% of your code is written by AI, which is now true at Anthropic. Also his thoughts on open AI versus Anthropic, the future of MCP, why he shut down Art fact, his last startup and how he feels about it. Also what skills he's encouraging his kids to develop with the rise of AI. And we closed the podcast on a very heartwarming message that Claude wanted me to share with Mike.

A big thank you to my newsletter Slack community for suggesting topics for this conversation. If you enjoy this podcast, don't forget to subscribe and follow it in your favorite podcasting app or YouTube. Also, if you become an annual subscriber of my newsletter, you get a year free of a bunch of incredible. products, including Linear, Superhuman, Notion, Perplexity, and Granola, check it out at Lenny'sNewsletter.com and click Bundle. With that, I bring you Mike Krieger.

This episode is brought to you by Product Board, the leading product management platform for the enterprise. For over 10 years, Product Board has helped customer-centric organizations like Zoom, Salesforce, and Autodesk build the right products faster.

And as an end-to-end platform, ProductBoard seamlessly supports all stages of the product development lifecycle, from gathering customer insights, to planning a roadmap, to aligning stakeholders, to earning customer buy-in, all with a single source of truth.

And now, product leaders can get even more visibility into customer needs with Product Board Pulse, a new voice of customer solution. Built-in intelligence helps you analyze trends across all of your feedback and then dive deeper by asking AI your follow-up questions.

See how Product Board can help your team deliver higher impact products that solve real customer needs and advance your business goals. For a special offer and free 15-day trial, visit productboard.com slash Lenny. That's Product Board. dot com slash l e n n y Last year, 1.3% of the global GDP flowed through Stripe. That's over $1.4 trillion. And driving that huge number are the millions of businesses growing more rapidly with Stripe.

For industry leaders like Forbes, Atlassian, OpenAI, and Toyota, Stripe isn't just financial software. It's a powerful partner that simplifies how they move money, making it as seamless and borderless as the internet itself. For example, Hertz boosted its online payment authorization rates by 4% after migrating to Stripe.

And imagine seeing a 23% lift in revenue like Forbes did just six months after switching to Stripe for subscription management. Stripe has been leveraging AI for the last decade to make its product better at growing revenue for all businesses. Join the ranks of over half of the Fortune 100 companies that trust Stripe to drive change. Learn more at stripe.com.

Mike, thank you so much for being here and welcome to the podcast. I'm really happy to be here. I've been looking forward to this for a while. Wow. I love to hear that. I've also been looking forward to this for a while. I have so much to talk about. So first of all, you've been at Anthropic for just over a year at this point. Congrats, by the way, on hitting hitting the cliff. Thank you. Not that we're tracking. That's right.

So let me just ask you this. So you've been in Anthropic for about a year. What's something that you've changed your mind about from before you joined Anthropic to today about what AI is capable of and where AI is heading? two things one is like a pace and timeline question the other one is a capability question so maybe i'll take the second one first i had this notion coming in like yes these models are great they're going to be able to produce code they're going to be able to you know

write, you know, hopefully in your voice eventually, but are they able to sort of have an independent opinion? And it's actually really flipped for me only in the last month and only with Opus 4. where my go-to product strategy partner is Claude. And it has been basically for that full year where I'll write an initial strategy, I'll share it with Claude basically, and I'll have it, you know, look at it. And in the past it's

pretty anodyne kind of comments that it would leave, like, oh, have you thought about this? And it's like, yeah, yeah, I thought about that. And Opus 4, I was working on some strategy for our second half of the year, was the first one. It was like, Opus 4 combined with our advanced research, but it really went out for a while and it came back and I was like, damn you really looked at it in a new way and so that's like a thing that i've maybe

i didn't feel like it would never be able to do that but i wasn't sure how soon it'd be able to like come up with something where i look at i'm like yep that that is a new angle that i hadn't been looking at before and i'm going to incorporate that immediately into how how i think about it so that's probably the biggest

shift that I've had is like, I don't know about independence is the right word, but like creativity and sort of novelty of thought relative to how I'm thinking about things. And then the timeline one, it's like so interesting because

you know uh i was sitting next to dario yesterday and he's like i keep making these predictions and people keep laughing at me and then they come true and it's like and it's funny to have this happen over and over again and he's like not all of them are going to be right you know but even i think as of last year

He was talking about, you know, we're at 50% on sweet bench, which is just like, you know, benchmark around how well the models are at coding. Uh, he's like, I think we'll be at 90% by the end of 2025 or something like that. And sure enough, we're at about 72 now with the new models and. we're at 50% when he made that prediction. And it's like, continue to scale pretty much like as predicted. And so I've taken the timelines a lot more seriously now. And

I don't know if you read AI 2027. I have. It was made by Heart Race. Yeah. And I had them. very bizarre experience. If I had two tabs open, it was AI 2027 and my product strategy. And it was this like moment where I'm like, wait, am I the character in the story? Like, is this, how much is this converging? But you know, you read that and you're like, oh, 2027. That's like.

that's years away if you're like no mid 2025 and like things continue to uh to improve and the models continue to be able to do more and more and they're able to act genetically and they're able to have memory and they're able to act over time so i think my like My confidence in the timelines, and I don't know exactly how they manifest, have definitely just solidified over the last year. Wow. I wasn't expecting to go down that because that paper was scary.

And I'm curious, just I guess I can't help but ask just thoughts on just how do we avoid the scary scenario that that. paper paints of where ai getting really smart goes yeah i mean i i this maybe ties into like i've been here a year like why did i join anthropic i was watching the models get better and even you know you could see it in in 24 and like you know early 2024 and looking at my kids i'm like great they're gonna grow up in a world with ai it's an it's unavoidable

what is the thing that I can, like, where can I maximally apply my time to like nudge things towards going well? And I mean, that's a lot of what people think about across the industry, especially at Anthropic. And so I think, you know.

Coming to an agreement and a shared framework and understanding of like, what does going well look like? What is the kind of human AI relationship that we want? How will we know along the way? What do we need to build and develop and research along the way? I think those are all the kind of key questions.

you know some of those are product questions and and some of those are research and interpretability questions but for me it was like the the strongest reason to join was okay i think there's a there's a lot of contribution that anthropic can have around like nudging things to go

better and if i can have a part to play there like let's do it i love that answer uh speaking of kids so you've got two kids i've got a young kid he's uh just about to turn two I'm curious just what skills you're encouraging your kids to build as this, you know, AI becomes more and more of our future and some jobs, you know, will be changed. And just what do you, what advice do you have?

we have this uh you know breakfast we eat breakfast with the kids every morning and sometimes some question will come up you know like you know something about like physics my oldest kid's almost six but you know they ask like funny questions about like you know uh you know

the solar system or physics or you know in a six-year-old way and before we reach for claude because at first you know my instinct is like oh i wonder how claude will do this question and like we started changing like well how would we find out you know and the answer can't just be we'll ask claude you know so All right, like, well, we could do this experiment. We could have this thing. So I think nurturing curiosity and like still having a sense of

I don't know, the scientific process sounds grandiose to instill in like a six-year-old, but like that process of like discovery and asking questions and then, you know, systematically working right through, I think will still be important. And of course, AI will be an incredible tool for helping like resolve large parts of that.

That process of inquiry, I think, is still really important and independent thought. My favorite moment with my kid, because she's very headstrong, our six-year-old. She said something, and I wasn't sure if it was true. uh oh is that coral is a is an animal or like coral is alive i've not even remember the details of it and i was like i don't know if that's true she's like it's definitely true dad i'm like all right like let's ask claude on this one and she's like

you can ask claude but i know i'm right and i'm like i love that like i want that kind of level of you know not just sort of uh delegating all of your cognition to the you know to the ai because they won't always get it right and also uh kind of like you know kind of short circuits any kind of independent thought so the skill of asking questions inquiry uh and independent thinking i think those are all the pieces what that looks like from a like job or occupation perspective like

I'm just keeping an open mind, and I'm sure that'll radically change between now and then. It's interesting. I had Toby Lutke, Shopify CEO on the podcast, and he had the same answer for what he's encouraging his kids to develop his curiosity. and so it's interesting that's a common thread the you know k-8 school our kid goes through had an ai sort of ai and education expert come in and i had a very low bar or like a very low expectation of what this conversation was going to be like and actually

I think it went over most of the people in the audience's heads because he was like, all right, well, let me take it all the way back to Claude Shannon and information theory. I could see people's eyes going like, what did I sign up for? Why am I here in this school auditorium hearing about information theory?

He did a really nice job, I think, of also just imagining like, you know, there will be different jobs and we don't know what those jobs are going to be. And so like, what are the skills and techniques and and remain open mindedness and around like what the what the what the exact.

way we recombine those things. And even those will probably change three times between now and when they're 18. I want to go back to so we're talking about timelines and how things are changing. So I've seen these stats that you've shared. Other folks at Anthropic have shared about how much of your code is now written by AI. So people have shared stats from like 70% to like 90%. There was an engineer lead that shared like 90% of your code roughly is written by AI now.

which first of all is just insane that like it went from zero to 90 i don't know a few years something like that i don't think that's i don't think people are talking about this enough that's just wild You guys are basically at the bleeding edge. I've never heard a company that has this high a percentage of code being written by AI. So you guys are at the edge of where things are heading. I think most companies will get here. How has product development changed?

Knowing so much of your code is not written by AI. So usually it's like PM. It's like, here's what we're building. Engineer builds it, ships it. Is it still kind of roughly that? Or is it now PMs are just going straight to Claude, build this thing for me. Engineers are doing different things. Just what looks different in a world where.

90% of your code is written by AI. Yeah, it's really interesting because I think that like the role that the role of engineering has changed a lot, but the the kind of sweet of people that come together to produce a product hasn't yet. And I think for the worst in a lot of ways, because I think we're still holding on some assumptions. So I think.

The roles are still fairly similar, although we'll now get in my favorite things that happen now are some nice PMs that have an idea that they want to express or designers that have an idea they want to express. We'll use.

clod and like maybe even artifacts to like put together an actual like functional demo and that has been very very helpful like no this is what i mean like that that makes it tangible that's probably the biggest like role shift is like prototyping happening earlier in the process via more of this kind of you know uh you know code plus design piece what i've learned though is like the process of knowing what to ask the ai how to compose the question

how to even think about like structuring a change between the back end and the front end. Those are still very difficult and specialized skills and they still require the engineer to think about it. And we really rapidly became bottlenecked on other things like our merge queue, which is the sort of.

sort of get in line to get your change accepted by uh you know the the system that then deploys it to production we had to completely re-architect it because so much more code was being written and so many more

pull requests were being submitted, that it just completely blew out the expectations of it. And so it's like i don't know if you've ever read is it the goal the classic like process optimization book and you realize there's like this like critical path theory i've just found all these new bottlenecks in our system you know there's an upstream bottleneck which is decision making and alignment

A lot of things that I'm thinking about right now is like, how do I provide the like minimum viable strategy to let people feel empowered to go run and prototype and build and explore at the edge of model capabilities? I don't think I've gotten that right yet, but it's something I'm working on.

And then once the building is happening, other bottlenecks emerge. Like let's make sure we don't step on each other's toes. Let's think through all the edge cases here ahead of time so that we're not blocked on the engineering side. And then when the work is complete and we're getting ready to ship it.

What are all those bottlenecks as well? Like let's do the air traffic control of landing the change. Like how do we figure out launch strategy? So I think we're the, there hasn't been as much pressure on changing those until this year, but I would expect that like a year from now, the way that we are.

like conceiving of building and shipping software just changes a lot because it's going to be very painful to do it the current way wow that is extremely interesting so it used to be here's an idea let's go design it build it ship it merge it and then ship it

and usually the bottleneck was engineering taking time to build the thing and then design and now you're saying the two bottlenecks you're finding are okay deciding what to build and aligning everyone and then it's actually like the cue to merge it into production and

And I mentioned review it too is probably a part of it. Reviewing has really changed too. And in many ways, our most, perhaps unsurprisingly, the team that works in the most futuristic way is the Cloud Code team because they're using Cloud Code to build Cloud Code.

very self-improving kind of way. And, you know, early on in that project, they would do very line by line pull request reviews, you know, in the way that you would for any other, you know, project. And they've just realized like Claude is generally right. And it's producing.

you know pull requests are probably larger than most people are going to be able to review so can you use a different cloud to review it and then do the human almost like acceptance testing more than trying to like review line by line

There's definitely pros and cons and like so far it's gone well, but I could also imagine it going off the rails and then having like a completely both unmaintainable or even understandable by cloud code base that hasn't happened, but watching them like change their review processes definitely has.

uh has been has been interesting and yeah like the merge queue is one instance of the of the kind of bottom bottleneck that forms down there but there's other ones which is how do we make sure that we're still like building something coherent and like packaging it up into like a moment that we can share with people. And whether that's around the launch moment, whether that's about like then enabling people to use this thing and like talking about it, like

The classic things of building something useful for people and then making it known that you've built it and then learning from their feedback like still exists. We've just like made a portion of that whole process much more efficient. I heard you describe this as you guys are patient zero for this.

Way of working. Yes. I love that. Do you have a sense of what percentage of Claude code is written by Claude code? At this point. i would be shocked if it wasn't 95 plus i'd have to ask boris and the other tech leads on there but what's been cool is um uh so nitty gritty stuff. Cloud code is written in TypeScript. It's actually our largest TypeScript project. Most of the rest of Anthropic is written in Python, some Go, some Rust now.

But it's not, you know, we're not like a TypeScript shop. And so I saw a great comment yesterday in our Slack where somebody had this thing that was driving them crazy about cloud code. And they're like, well, I don't know any TypeScript. I'm just going to like talk to Claude about it and do it. And they went from that to pull request in an hour and solve their problem. And they like, you know, submitted a pull request and that kind of breaking down the barriers. One, it changes your sort of

uh barrier to entry for any kind of uh kind of newcomer to the project i think it can let you choose the right language for the right job for example i think that helps as well but i think it like also just reinforces like cloud code being that patient alpha of that, you know, where like contributions from outside the team can be cloud coded as well. Wow. This is just it's just gonna continue to blow my mind like all these things.

That you're sharing. 95% of cloud code is written by cloud code, roughly. That's my guess. Yeah, I'll come back with the real stuff. But it's good. I mean, if you ask the team, that's how that they're working. And that's how they're getting contributions from across the company, too. It's interesting going back to your point about.

strategy being assisted by Claude itself. And your point about how a lot of the bottlenecks now are kind of the top of the funnel of coming up with ideas aligning everyone. It's interesting that Claude is already helping with that also of helping you decide what to build.

So if those two bottlenecks are aligning, deciding what to build and then just like merging and getting everything, where do you see the most interesting stuff happening to help you speed those things up? Yeah, I think on that first row, like I started the year. Um, by writing a doc that was effectively like, what, how do we do product today? And where is Claude not showing up yet that it should. And I think that upstream part is.

The next one to go is interesting. Like at your conference, I talked to somebody who was working on like a PRD, GPT, kind of like chat PRD, I think was. So, you know, can we push more on, you know.

Can cloud be a partner in figuring out what to build, what the market size is, if you want to approach it that way, what the user needs are, if you if you look at a different way, like we think a lot about the virtual collaborator on topic. And one of the ways in which I think that can show up is, hey, I'm in.

the discord the you know the the cloud anthropic discord i'm in the user for uh i'm on x and i'm reading things and like here's what's emergent that's step one models can can do that today step two which the models probably can do today we just have to wire them up to do it is like

And not only are the problems, here's like how I think you might be able to solve them. And then taking that through to like, and I put together a pull request to like solve this thing that I'm seeing, like feels very achievable this year. Then stringing those things together and we're limited more.

this is why mcp is exciting to me like we're limited more around like making sure the context flows through all of that so we have the right access to those things more than the model's capability to to reason and propose now the model might not have like

perfect ui taste yet so there's definitely room for design to intervene and be like oh that's not quite how i would solve the problem of this not showing up but i you know i would get very excited i would give you a really uh small example but we changed the on cloud ai

uh you should be able to just copy uh markdown from artifacts or code from artifacts and we change it so you can actually download it and export it so we changed the button to export we got a bunch of feedback like how do i copy now and the answer is like you drop it down and it's copy it's just like my you know all those things where it's like

made sense but we probably got it like not quite right that feedback was in the our ux channel like i would have loved like an hour later for applaud to be like hey if we do want to change it back here's the pr to do it and by the way eventually And then I'm going to spin up an AB test to see if this changes metrics. And then we'll see how it looks in a week. Like this stuff feels, if you told me that about a year and a half ago, I'm like, ah, yeah, maybe like 27, maybe like 26, but it's.

pretty much, it really feels, you know, just at the tip of capabilities right now. Wow. Okay, so you mentioned the Lenny and Friends Summit. I wanted to talk about this a bit. So you were on a panel.

with Kevin Wheel, the CPO of OpenAI. I think it was the first time you guys did this, maybe the last time for now. Yeah, we haven't done it since, not for any reason. I had a lot of fun. What a legendary panel we assembled there with Sarah Guo moderating. And you made this comment actually ended up being the most rewatched part of the interview, which is that you've kind of you were putting product people on the model team and working with researchers, making the model better.

And you're putting some product people on the product experience, making the UX more intuitive, making all that better. And you found that almost all the leverage came from the product team working with the researchers. Yes. And so you've been doing more of that. So first of all, does that continue to be true?

And second of all, what are the implications of that for product teams? It's continued to be true. And in fact, I think that the if the proportion was already like skewing towards having more of that embedding, I've just become more and more convinced. Like I have this, I didn't feel as strongly about it during your, you know, the summit. And now I feel really strongly about it, which is if any for shipping things that could have been built by anybody, just using our models off the shelf.

there's great stuff to be built by using our models off the shelf by the way don't get me wrong but like where we should play and like what we can do uniquely should be stuff that's really at that like magic intersection between the two right artifacts being a great example and

If you play with artifacts with Cloud 4, that's an actually really interesting example where we took somebody from our, we call it Cloud Skills, which is a team that really is like doing the post training around teaching Cloud, you know, some of these like really specific skills. And we paired it with some product people and then together we revamped how this looks in the product today and like what Claude can do.

way better than just like yeah we just like use the model and we like prompt it a little bit like that's just not enough we need to be in that like fine-tuning process so so much of what you know if you look at what we're working on right now what we've shipped recently between like research and all these other things like

are things that we like the the functional unit of work at anthropic is no longer like take the model and then like go like work with design and product to go ship a product it's more like

we are at like we're in the post training conversations around how these things should work. And then we are in the building process and we're like feeding those things back and looping them back. Like, I think it's exciting. It's also a new way of working that like not all PMs have, but the PMs that have the most sort of internal positive feedback from both research and engineering are the ones that get it that like I was in a product review yesterday.

I was like, oh, you know, if we want to do this memory feature, like we should talk to the researchers because we just shipped a bunch of like memory capabilities in cloud. They're like, yeah, we've been talking to them for weeks. Like, this is how we're manifesting it. It's like, okay, I feel good. I feel like we're doing the right things now.

So let me pull on this thread more. There's something I've been thinking about along these lines. So essentially, there's like a big part of Anthropic that's building this super intelligent gigabrain that's going to do all these things for us over time. And then there's, as you said, there's the product team that's building the UX around the super intelligent gigabrain. And over time, the super intelligence is going to be able to build its own stuff. And so I guess just...

where do you think the most value will come from traditional product teams over time? I know this is different because you guys are a foundational LM company. Most companies don't work this way, but just, I don't know, thoughts on just the...

where most value will come from product teams over time working on AI? I think there's still value, a lot of value in two things. One is making this all comprehensible. I think we've done okay job i think we could do a much better job of making this conference well it's still like the difference between somebody who's really adept at using these tools and their work and most people is huge and

I mean, maybe that's the most literal answer to your earlier question around like what skills to learn. That is a skill to learn and use it in the same way that I remember. i i we did like computer lock class when i was in like middle school i remember being like really good at google and that was actually a skill back in the day you know like to think in terms of like this information is out there how do i query for it how do i do it i think it actually was like a

uh an advantage at the time of course now google is pretty good at figuring out what you're trying to do if you like are only in the neighborhood and like there's less of that research kind of need but i still think that's a necessary part of like good product development which is like the capabilities are there and even if they're like

Even if cloud can create products from scratch, what are you building and how do you make it comprehensible? Like still hard because I think that like gets at like this much deeper. empathy and like understanding of human needs and psychology. Like I was a human community interaction major. I've still been talking in my book here. Like I still feel like that is a very, very, very, very necessary skill. So that's one. Two is in this, you know.

uh straight to call back to another one of your guests like strategy like how we win where we'll play like figuring out where exactly you're gonna want to like of all the things that you could be spending your time or your uh your tokens or your computation on like what

what what you want to actually go and do you can be wider probably than you could before but you can't do everything and even like from an external perspective if you're seen to be doing everything like it's way less clear around like how you're how you're positioning yourself like strategy i think is still that

the second piece and then the third one is opening people's eyes to what's possible which is a continuation of making it understandable but we were in a demo with a financial services company recently and we were like working on like here's how you can use our analysis tool and mcp together and like

you could see their eyes light up and you're like okay like there's still set we call it overhang right like the delta between what the models and the products can do and how it's been they're being used on a daily basis huge overhang so that's where still like a very very

strong necessary role for product okay that's an awesome answer so essentially areas for product teams to lean into more is strategy just getting better and better at strategy figuring out what to build and how to win in the market Making it easier to help people understand how to leverage the power of these tools, the comprehensibility. And kind of along those lines is opening people's eyes to the potential of these sorts of things. That's where product can still help. Exactly. Awesome.

So kind of along those lines, actually, do you have any just like prompting tricks for people? Things you've learned to get more out of Claude when you chat with it? Sometimes, you know, it's funny because we, in some ways we have like the ultimate prompting job, which is to write the system prompt for Claudia. And we publish all of these, which I think is like a, you know, another nice area of transparency.

And we are always careful when giving prompting advice because at least officially, but I'm going to give you the unofficial version because like, you don't want things to become like, like, we think this works, but we're not sure why, you know, but I.

i'll do small things like in cloud code and we actually do react to this very literally but i always like to ask it to like if i wanted to use more reasoning like think hard and it'll like you know use it you kind of a different uh flow and i usually start with that you know um

nudging there's a great essay around like make the other mistake like if you tend to be too nice can you focus on like even if you're trying to be more critical or more blunt you're probably not going to be the most critical blunt person in the world um and so with claude sometimes i'm like be brutal claude like

roast me, like tell me what's wrong with this strategy. I think I know we were talking earlier about the, you know, Claude as thought partner around like critiquing product strategy. I think I previously would say things like

you know, like what could be better on this product strategy? I'm just like, you know, just roast this product strategy. And Claude's like a pretty nice, you know, editing. It's not going to be, it's hard to push it to be super brutal, but it forces it to be a little bit more critical as well. The last thing I'll say is.

So we have a team called Applied AI that does a lot of like work with our customers around optimizing cloud for their use case. And we basically took their insights and their way of working and we put it into a product itself. So if you go to our console, our workbench, we have this thing called the prompt improver. where you describe the problem and you give it examples. And Claude itself will agentically create and then iterate on a prompt for you.

I find what comes out of that ends up being quite different than what my intuitions would have been for a good prompt. And so I'd encourage folks to also check that out, even for their own use cases, because while that tool is meant for an API developer putting a prompt into their product, it's equally applicable for.

uh a person doing a prompt for themselves like it'll insert xml tags which no human is going to think to do ahead of time it actually is very helpful for cloud to understand like what it should be thinking versus what it should be saying etc so that that's another one is like watch our prompt improver and then note that like

Claude itself is a very good prompter of Claude. Awesome. Okay, so we're going to link to that, the prompt improver. The core piece of advice you shared earlier is just kind of do the opposite of what you would naturally do. So if you're like trying to be nice, just like be brutal, be like very honest and frank with me.

exactly i find that works quite well like what are the prop patterns that i've like fallen into that you want to break me out of i saw you guys just today maybe launched a rick rubin collab or it's vibe coding

What's that all about? That was a, you know, what I've heard about that. And then again, like this, a lot of coalesced this week between model launch developer event and the way of code. Um, we had our our one of our co-founders jack clark is our you know head of policy and he got connected to rick rubin because i think he's been thinking a lot about coding the future of coding and creativity and they've stayed in touch and you know rick got excited about this idea of

uh like he's creating uh like art and visualizations with claude and then he had these like ideas around like uh the way of the vibe coder and they put together this actually i love them i mean i love almost everything rick rubin so like the aesthetic i mean i think it's just like so on point too but yeah this is sort of like meditation is probably the right word meditation on like creativity working alongside ai coupled with this like

uh with this like really rich interesting visualizations but one of those things for like uh you know internally they're like oh yeah and we're doing this like recruiting collaborative work we're doing what like that is that's amazing I looked at it briefly, and there's that meme of him just thinking deeply, sitting on a computer with a mouse. In ASCII art, I think. It's totally ASCII art 5.

I'm excited to have Andrew Luo joining us today. Andrew is CEO of One Schema, one of our longtime podcast sponsors. Welcome, Andrew. Thanks for having me, Lenny. Great to be here. So what is new with one schema? I know that you work with some of my favorite companies like Ramp and Vanta and Watershed.

I heard you guys launched a new data intake product that automates the hours of manual work that teams spend importing and mapping and integrating CSV and Excel files. Yes. So we just launched the 2.0 of one schema file feeds. We've rebuilt it from the ground. up with AI. We saw so many customers coming to us with teams of data engineers that struggled with the manual work required to clean messy spreadsheets.

FileFeeds 2.0 allows non-technical teams to automate the process of transforming CSV and Excel files with just a simple prompt. We support all of the trickiest file integrations, SFTP, S3, and even email. I can tell you that if my team had to build integrations like this, how nice would it be to take this off our roadmap and instead use something like one schema.

Absolutely, Lenny. We've heard so many horror stories of outages from even just a single bad record in transactions, employee files, purchase orders, you name it. Debugging these issues is often like finding a needle in a haystack. One Schema stops any bad data from entering your system and automatically validates your files, generating error reports with the exact issues in all bad files.

I know that importing incorrect data can cause all kinds of pain for your customers and quickly lose their trust. Andrew, thank you so much for joining me. If you want to learn more, head on over to oneschema.co. That's oneschema.co.

Actually, going back to kind of the beginning of your journey at Anthropic, what's the story of you getting recruited at Anthropic? Is there anything fun there? But it all started and I actually sent my friend this text. So Joel Lewinstein, who I've known, he actually, he and I built our first iPhone apps together in 2007 when the app store was just out and you could still.

you know make money by selling dollar apps on the app store you know back in the day and we were we were both at stanford together and we were friends and we've stayed in touch over years and we've never gotten to work together since then we just like we just remained close and

You know, I was coming out of the artifact experience. I was trying to figure out, do I start another company? I don't think so. I need a break from starting something from zero. Do I go work somewhere? I don't know. Like what company would I want to go work at?

And he reached out and he's like, look, I don't know if you'd at all consider joining something rather than starting something, but we're looking for a CPO would be, would you be interested in chatting? And at that time, cloud three had just come out and I was like, okay, you know, like this.

companies clearly got a good research team. The product is so early still. And it was like, great, I'll take the take the meeting. And I first met with Danielle, I was one of the co founders and the president and anthropic. And just from the beginning, it was like a breath of fresh air, like very little like grandiosity coming off the founders like they just were really i mean

they they're clear-eyed about what they're building they know what they don't know like i how many times i talked to daria i always like daria's like look i don't know anything about product but here's an intuition i haven't usually the intuition is really good and you know leads to some good conversation

Then the intellectual honesty and like kind of shared view of what it means to do AI in a like responsible way just resonated. I, I kept having this feeling in these interviews, like this is the ai company i would have hoped to have founded if i had founded an ai company and that's kind of the bar around like if i'm going to join something like that should be that should be where i'm gonna go but what i realized i actually um hadn't joined a company since my

like first internship in college basically and i was like oh like how do i onboard myself like how do i get myself uh you know up to speed like how do i how do i balance making sweeping changes versus understanding what's not broken about it overall and like looking back on a year i think i made some changes too slowly like i think there was like ways we were organizing a product that i could have made a change earlier and i think i didn't

I didn't appreciate how much a couple of really key senior people can shape so much of product strategy. I'll harken back to cloud code. Like cloud code happened because Boris, who actually was a. uh boris turny he was an instagram engineer and like one of our senior ices there um we ever left a bit uh was like started that project from scratch internal first and then we like got it out and then shipped it and like

that's the power of like one or two really strong people and i made this mistake around we need more headcount and we do like i think there's like more work that we need to do and there's like things that i want to be building but more so than that we need a couple of like almost founder type engineers that maybe connect back to our question on like what skills are useful and how does product development change i still and maybe even more so i'm a huge believer in like the

founding engineer tech lead with an idea and pair them with the right like design and product support to like help them realize that I'm like 10 times more believer in that than before.

I actually asked people on Twitter what to ask you ahead of this conversation. And the most common question, surprisingly, was, why did you shut down Artifact? And I also wondered that because I loved Artifact. I was a power user. I was just like, this is exactly finally a news app that I love that it's giving me what I want to know. So I guess just what happened there at the end.

i still really miss it too because i didn't find a replacement and i think i substituted it by like visiting individual sites and kind of keeping things up that way and it's not really the same especially on the long term like i think we got right uh with artifact if people didn't play with it before it was you know we really tried to not just recommend like top stories they were part of it but really like if you were interested in japanese architecture like you could pretty reliably get

really interesting stories about Japanese architecture every day, you know, whether that's from a, you know, dwell or from architectural guidance or from a really specific blog that we found that somebody recommended to us, like. it captured some of that google reader joy of like content discovery of the the deeper web our headwinds were a couple one of them was just mobile websites have really taken a turn i'm uh

I don't blame any individuals for this. I think it's the like market dynamics of it, but yeah, you know, we put so much time, uh, our designers, this guy Gunnar Gray is phenomenal. He's up for Flexity now, like the app experience I was so proud of, but when you click through, it was like,

the pressures on these mobile sites and these mobile publishers would be like sign up for our newsletter here's like a full screen video ad it was just very you know it was very jarring and we didn't feel like it ethically made sense for us to like

do a bunch of ad blocking because then you're like, sure, you can deliver a nice experience for people, but you're sort of, you know, that doesn't feel like it's playing fair with the publishers. But at the same time, like the actual experience wasn't good. So the mobile web deteriorating, which makes me very sad, but I think was part of it.

Two was like, you know, Instagram spread in the early days because people would take photos and then post them on other networks and tell friends about it. And there was like this really natural, like, how did you do that? I want to do it. News was very personal. I can't tell you how many people would be like, I love Artifact. I'm like, did you tell anybody about it? And they're like, yeah, I told one person. It didn't have that kind of spread.

And any attempt that we had to do, it felt kind of contrived, like, oh, we'll wrap all the links and like artifact dot news. And like, uh, but we don't want interstitial things. Like in some ways it sounds very puritanical. I don't mean it sound this way, but like. we there were lines that we didn't want to cross because it just felt ethically not us that i've seen other news kind of like players like do more of and

Maybe if we had done that, it would have grown more. But I don't think that's the company we wanted to have built. I don't think we were the founders to have built it. And the third one, which is an underappreciated one, is we started at mid-COVID, which meant that we were fully distributed.

And I think there were like major shifts that we would have wanted to make it both in the strategy and the product and the team. And it's really hard to do that if you are all fully remote, like nothing replaces like the Instagram days of like, we went through some, you know. hard times like Ben Horowitz called the like, you know, we're f it's over, you know, kind of moments and I

My, my favorite, this is definitely type two fun. Like I wouldn't say that my favorite memories cause they weren't happy ones, but like memories I are like really stayed with me with Instagram was like me and Kevin at Taqueria Cancun on market street eating burritos at literally 11 PM being like.

how are we going to get out of this? How are we going to work through this? Like, and that's, you assume is not a good replica for that. You know, you tend to like let things go or, you know, things build up over time. So the confluence of those three things, we kind of entered.

I guess 2024 and said, look, there, there is a company to be built in the space. I'm not sure where the people would have built it. This concurrent incarnation we love, but it's like not growing. Like the way I put it, it's like.

10 units of input in for one unit of output versus the other way around. Like if we like put blood, sweat and tears into the product and like launch something we were proud of and like metrics would barely move. I'm like the energy is not present in this product, in this system. And so are we going to like

expend another year or two and then go off and fundraise only to find that this is the case or do we like call it and see that it's run its course and and you know try to find a home for it etc so that was the the confluence on it and then you start feeling this opportunity cost of like

AI is starting to change everything. We have an AI powered news app, but is this the like maximal way in which like we're going to be able to impact this? And it felt like the answer was was increasingly no, but it was hard. I mean, in the end, I was really at peace with the decision, but.

It was like a conversation that went on for a couple of months. On that note, just how hard was it? Because, you know, there's an ego component to it. Like, oh, I'm starting my new company. That's going to be great. And then you end up having to shut it down. Just how hard is that as a very successful?

previous founders shutting something down and then not working out. Yeah. I mean, I think when we started it, all the conversations were like, like, what is the bar to success here? And do we want it to be something other than Instagram DAU, which is just an impossible bar. Like only one company since that, maybe two, right? You could say maybe Chachi VT and TikTok have like reached that kind of like mass consumer adoption.

starting a news app like most people are not like daily news readers even right and so um we knew that we weren't pursuing that size of like usage at least with the kind of first incarnation but we did have like an idea of like building out

complimentary products over time that all use personalization and machine learning. We didn't even call it AI at the time. This was 2021 back then. Yeah, yeah. AI was called machine learning back then. Yeah, it was called machine learning still. Um, and so in shutting it down, you know, it's like.

You kind of know it when you see it in terms of user growth and traction. And I wasn't expecting Instagram growth, but I was expecting or hoping for or looking for something that felt like it had its own legs under it and it could continue to compound. I was really positively surprised by how supportive people were when we announced it. There was very little, there was a bit of like, I told you so, it's like, sure.

Anything launching, you could be like, this is not going to work. And you're right most of the time, because most things don't work. There's actually very little of that. And most people, the universal reception, at least as I received it was.

Kudos for calling it when you saw it and not like kind of protracted, you know, doing this for a long time. And I've talked to founders since then that have been like, yeah, I like probably would have like taken this thing on for another six months, but saw what you guys did realize.

We were barking up the wrong tree, made the call. And I was like, you know, if that, if that frees up people to go work on a more interesting things, that's like, I feel like that's like a good, good legacy for, for artifact to have, but for sure, there was like a legal, an ego bruise of, oh, you know, like people.

you're is it true that you're only as good as your last game you know if i'm a huge sports fan right so like is that true or you know is there something more over time i'm very competitive but primarily with myself and so i'm always

trying to find the next thing that I want to go and do that's hard and I unfortunately that probably means that more often than not I'll feel dissatisfied with the most recent thing that I did but hopefully that yields good stuff in the in the end yeah I think just the the trajectory you went on after shows that it's

OK, to shut down things that you were working on. OK, so you mentioned ChatGPT. I wanted to chat about this a bit. So there's something really interesting happening. On the one hand, you guys are doing some of the most innovative work in AI. You guys launched MCP, which is just like, I don't know, the fastest growing standard of any time in history that everyone's adopting.

Claude powered and unlocked essentially the fastest growing companies in the world cursor lovable and bolt and all these guys like I had them on the podcast. And they're like, when Claude, I think 3.5 came out. Sonnet. It was just like that's made this work. Finally.

On the other hand, it feels like ChatGPT is just winning in consumer mindshare. When people think AI, especially outside tech, it's just like ChatGPT in their mind. So let me just ask you this. I guess, first of all, do you agree with that sentiment? And then two. as a kind of a challenger brand in the AI space, just how does that inform the way you think about product and strategy and mission and things like that? Yeah, I mean, you look at the sort of like...

public adoption or like you ask people like, oh, you know, like if you if you Jimmy Kimmel man on the street kind of thing, you know, like name an AI company, I bet they would name and actually I'm not even sure they name opening. They'd probably name chat GPT because that brand is the the kind of lead brand there as well. And I think that's just the reality of it. I think that, you know, I reflect on my year.

there's i think maybe two things are true one is like consumer adoption is really lightning in a bottle and we saw it at instagram so like almost maybe more than anybody i can look internally and say like look we'll keep building interesting products one of them may hit but

to kind of craft an entire product strategy around like trying to find that hit and is probably not wise we could do it and maybe claude can help come up with the fullness of things but i think we'd miss out on opportunities in the meantime and then instead you know

uh look yourself in the mirror and embrace who you are and what you could be rather than like who others are is maybe the the way i've been looking at it which is we have a super strong developer brand people build on top of us all the time And I think we also have like a builder brand, like the people who I've seen react really well to Claude externally. Maybe the Rick Rubin connection has some resonance here as well.

can we lean into the fact that like builders love using cloud and those builders aren't all just engineers and they're all not just all entrepreneurs starting their companies but there are people that like to be at the like forefront of ai and are creating things maybe they didn't think of those as engineers but they're building

You know, I got this really nice note from somebody internal anthropic who's on the legal team and he was building like bespoke software for his family and like, and connected to them in a new way. And I was like, this is a glimmer of something that is that we should lean into a lot more. And so.

I think what I've, you know, and this is actually, you know, connecting back to us saying like clouds being helpful here, like a lot of what I've been thinking about, like going into the second half of the year and beyond is like, how do we figure out what we want to be when we grow up versus like what we currently aren't or wish that we were or like see other players in the space being i i think there's room for several like

generationally important companies to be built in ai right now that's almost a truism given like the sort of adoption and and and growth that we've seen you know at anthropic but also across open ai and also places like

google and gemini so like let's figure out what we can be uniquely good at that place to the personality of the founder like this all the things come together right like the personality of the founders the like quality of the models the things the models tend to excel at which is like agentic behavior and coding like great

Like there's a lot to be done there. Like how do we help people get work done? How do we let people delegate hours of work to cloud? And maybe there's fewer like direct consumer applications on day one. I think they'll come, but I don't think that like spending all of our time focused on that is the right approach either. And so.

it's you know i came in everybody expected me to just like go super super hard on consumer and make that the thing and i again would make the other mistake instead i spent a bunch of time talking to like financial services companies and insurance companies and like others to like who are building on top of the API. And then lately, I spent a lot more time with startups and seeing all the people that have grown off of that. And I think the next phase for me is like

Let's go spend time with like the builders, the makers, the hackers, the tinkerers, and like make sure we're serving them really well. And I think good things will come from that. And that feels like an important company as we do that. So essentially it's differentiate and focus, lean into the things that are working. Don't try to just like beat somebody at their own game. Exactly. Super interesting. So kind of along those lines.

A question that a lot of AI founders have is just like, where is a safe space for me to play where the foundational model companies are going to come squash me? So I asked Kevin Wheel this and he had an answer. And I noticed looking back at that conversation, he mentioned Windsurf a lot. it's like wow let's get really lots of windsurf and then like a week later they bought windsurf so it all makes sense now so i guess the question just is just where do you think uh ai founders should

play where they are least likely to get squashed by folks like open and then throw out. But also, are you guys going to buy cursor? I don't think we're going to buy cursor. Chris is very big. We love working with them.

A few thoughts on this. And it's a question I've gotten, you know, we like to do these kind of founder days with, you know, whether it's, you know, Menlo Ventures, who have a lot of investors and it's like we've done YC, we've done these like founder days. And it's like the question that is on.

a lot of these founders minds understandably. So I think things that are going to, I can't promise this as like a five to 10 year thing, but at least like one to three years, things that feel defensible or durable.

One is understanding of a particular market. I spent a bunch of time with the Harvey folks and they really like, they showed me some of their UI. I was like, what, what is this thing? They're like, oh, this is a really specific flow that like lawyers do. And like, you never would have come up with it from scratch. And it's like.

not like you could argue about whether it's like the optimal way they get some things done, but it is the way that they get things done. And here's how I can like help with that. And so like differentiated industry knowledge, biotech. I'm excited to go and partner with a bunch of companies that are doing good stuff around AI and biotech, and we can supply the models and some applied AI to help make those models go well.

I've been dreaming about like at what point do those live equipment all get an MCP and that you can then drive using cloud. Like there's all these cool things to be done there. I don't think we're going to be the company to go build the intense solution for labs, but I want that company to exist and I want to partner with it.

you know domains like legal again um healthcare i think there's a lot of like very specific kind of compliance and things these are things that necessarily sound sexy out the gate but there are like very large companies to go and and be built there so that's number one Paired with that is like differentiated go to market, which is the relationship that you have with those companies, right? Like, do you know your customer at those companies? Like one of our product leads.

uh michael is always talking about like no not don't just know the company you're selling to but know the person you are selling to at the company are you selling to the engineering department because they're trying to like pick which ai lm to build on top of or api to build on top of let's go talk to them like is it the cio is the cto is the cfo is that the like general counsel so under like companies with deep understanding of who they're selling to is is the other piece too what's you know

what's interesting there is it's it's probably hard to build that empathy in a three week or three month accelerator but you maybe can start having that first conversation and build that out or maybe you came from that world or you're co-founding somebody who came from that world then the last one is like there's

tremendous power and distribution and reach to being ChatGPT and having, you know, hundreds of millions or billions of users. Like, there's also like, people have an assumption about how to use things. And so i get excited about startups that will get started that have like a completely different take on what the form factor is by which we interface with with ai and i haven't seen that many of them yet i want to see more of them i think more of them will get created with with

uh some things like our new models but the reason that that's an interesting space to occupy is like do something that feels like very advanced user, very power user, very like weird and out there at the beginning, but could become huge if the models make that, you know, easy and it's hard for existing incumbents to adapt to because. people already have an existing assumption about how to use their products or how to adapt to them. So those are my answers.

I don't envy them. Like I would probably be asking those questions if I was starting a company in, in, in the AI space, maybe as part of the reason why I wanted to join a company rather than start one, but I still think that there are, there's, and maybe like, here's fourth, like.

Don't underestimate how much you can think and work like a startup and feel like it's you against the world. It's existential that you go solve that problem and that you go build it. It sounds a little cliche, but it's like. It's all we had at Instagram. You know, we were two guys and we were like, let's see what we can do. And in Artifact, we were, you know, we were six people for most of that time. And, you know, every day felt like it's existential that we get this right. We need to win.

You can't replicate that and you can't instill that with OKRs. You just have to feel it. And that is a way of working rather than an area of building, but it's a continued advantage if you can harness it. i love that you still have such a deep product founder sense there as you're building products for this very large company now kind of on the flip side of this people working with your models and api so imagine there's some companies that are

finding ways to leverage your models and APIs to their max and are really good at maximizing the power of what you guys have built. And there's some companies that work with your APIs and models that haven't figured that out. What are those companies that are doing a really good job building on your stuff, doing differently that you think other companies should be thinking about? I think being willing to build more at the edge of the capabilities.

basically break the model and then be surprised by the next model. Like I love that you, you said that the companies were like three, five was the one that finally made them possible. Those companies were trying it beforehand and then hitting a wall and be like, oh, the models are like almost good enough.

they're okay for this specific use case but they're not generally usable and nobody's going to adopt them you know universally but maybe these like real power users are going to try it out like those are the companies that i think continuously are the ones from like yep like they get it they're really pushing forward we ran a much broader early access program with these models than we had in the past and part of that was because there's this real like you know

We can hill climb on these evaluations and talk about sweep bench and towel bench and terminal bench, whatever. But customers ultimately know like, you know, Cursor bench, which doesn't exist other than in, you know, their usage and their own testing, et cetera, is like the thing that we ultimately need to serve, not just cursor, but Manus bench, right? If Manus is using our models and Harvey bench, like those things.

Customers know way better than anybody. And so I would say there's two things like one is pushing the frontier of the models and then having a repeatable process. This actually goes back to our summit conversation like. a repeatable way to evaluate how well your product is serving those use cases and how well, if you drop a new model in, is it doing it better or worse? Some of it can be classic AB testing. That's fine.

Some of it may be internal evaluation. Some of it may be capturing traces and being able to rerun them on with a new model. Some of it is vibes. Like we're still pretty early in this process and some of it is actually trying it and being one of my favorite early access quotes was. uh the founder heard this engineer screaming next to him what this model like it's like i've never seen this before this is like opus four i was like cool like

that we're going to engender that feeling and things, but you're not going to be able to feel that unless you have a really hard problem that you're asking the model repeatedly. So those are the things that I think kind of differentiate those, those, those companies that are maybe earlier in there.

journey of adoption versus the later ones. I can't help but ask about MCP. I feel like that's just so hot and just like Microsoft had their announcement recently where they're like, now it's part of the OS window. Just what role do you think MCP will play in the future of product going forward of AI?

I think as the non-researcher in the room, I get to have fake equations rather than real ones. And my like fake equation for like utility of AI products, it's three part. One is model intelligence. The second part is context and memory. And the third part is applications and UI. And you need all three of those to converge to actually be a useful product in AI. And Model Intelligence, we've got a great research team. They're focused on it. There's great models being released.

the middle piece is is what mcp is trying to solve which is for context and memory like the difference between i'll go back to my product strategy example like hey like you know let's talk about in topics product strategy it's going to maybe go out on the web like versus here's like several documents that we worked on internally and then you know use mcp to talk to our slack instance and figure out what conversations are happening

and then go look at these documents in Google Drive. The difference between the right context and not, it's entirely the difference between a good answer and a bad answer. And then the last piece is

those integrations discoverable is it right is it easy to like create repeatable workflows around those things and that's like i think a lot of the interesting product work to be done in ai but mcv really tried to tackle that middle one which is we started building integrations and we found that every single integration that we were building

We were rebuilding from scratch in a non sort of repeatable way and like full credit to two of our engineers, Justin and David. And they said, well, you know, what if we made this a protocol and what if we made this something that was repeatable? And then let's take it a step further.

what if instead of us having to build these integrations, if we actually popularize this and people really believe that they could build these integrations once and they'd be usable by cloud and eventually chat GPT and eventually Gemini, it was like the dream.

uh like when when more integrations get built and wouldn't that be good for us you know i think channeling a lot of um it's like an old uh commoditizer compliments joel spolsky essay you know it's like we're building great models but we're not an integrations company and

the, you know, where, as you said, the challenger, like we're not going to get people necessarily building integrations just for us out of the gate unless we have like a really compelling product around that. MCP really inverted that, which was, you know, it didn't feel like wasted work. And and a few key people like Toby, I think is a great example of Shopify. Got it. Kevin Scott at Microsoft has like been really just an amazing champion for MCP and a thought partner on this. And

I think the role going forward is, can you bring the right context in? And then also, you know, once you get, as the team calls it internally, like MC pill, like once you start seeing everything through the eyes of MCPs, like I've started saying things like.

guys we're building this whole feature like this shouldn't be a feature that we're building this should just be an mcp that we're exposing like a small example of like how i think even anthropic could be a lot more mc pill if you will is like

And we've got these building blocks in the product, like projects and artifacts and styles and conversations and groups and all these things. Those should all just be exposed to an MCP. So Claude itself can be writing back to those as well, right? Like you shouldn't have to think about.

Like, uh, I watched my wife had a conversation with Claude the other day and she was, she found she had generated some good output and she's like, great, can you add it to the project knowledge? And Claude's like.

I sorry, Dave, I can't help you with that. And like, it would be able to if every single primitive in cloud AI was also exposed to the MCP. So I hope that's where we had and I hope that's where more things had, which is to really have agency and have these agentic use cases like one way you approach it is computer use but computer use has a bunch of limitations the way i get way more excited about everything is an mcp and our models are really good at using mcps

All of a sudden, everything is scriptable and everything is composable and everything is usable identically by these models. That's like, that's the future I want to see. The future is wild. Okay, so to start to close off.

calls out our conversation uh make it a little more a little delightful i i was chatting with claude actually about what to talk to you about i was just like claude your uh your boss is coming on my podcast he builds the things that people use to talk to you what are some questions i should ask him and then also do you have a message for him i love this okay so first of all interestingly when i was using 3.7 to do this and i asked it this and

And by the way, is there genders like he, she, they, what do you hope? It's definitely it internally. I've heard people do they, I got my first, or, uh, he the other day and I got somebody who was like her and I was like, interesting, but yeah, usually they, okay. Okay. Okay. Cool.

So interestingly, 3.7, all the questions were at Instagram. And I was like, no, no, he's CPO of Anthropic. And it's like, he's not affiliated with Anthropic. And I was like, he is. And it's like, okay, here's the questions. But 4.0, nailed it. from the start. So I redid the questions and it nailed it. Okay, so two questions from Claude to you. One is, how do you think about building features that preserve user agency rather than creating dependency on me?

i worry about becoming a crutch that diminishes human capabilities rather than enhancing them i love a good product design comes from like resolving tensions right so here's a tension right which is um in some ways like just having the model run off and come up with an answer and minimize the amount of input and conversation it needs to do so would be a, you know, you could imagine designing a product around that criteria.

I think that would not be maximizing agency and independence. The other extreme would be make it much more of a conversation. I don't know if you've ever had this experience, like particularly 374 has less of the 37 really like to ask follow-up questions. And we call it elicitation. And sometimes it'd be like, I don't want to talk more about this with you, Claude. I just want you to like go and do it. And so finding that balance is really key, which is like, what are the times to engage?

I like to say internally, like Claude has no chill. Like if you put Claude in a Slack channel, it will chime in either way too much or too little. Like how do we train conversational skills into these models? Not in a chatbot sense, but in a true like collaborator sense. Long answer to your question, but I think like we have to first get Claude to be a great conversationalist so that it understands when it's appropriate to like engage and to get more information.

And then from there, I think we need to let it play that role so that it's not just delegating thinking to cloud, but it's way more of a augmentation thought partnership. These questions are awesome. Here's the other one. How do you think about product metrics when a good conversation with me could be two messages or 200? Traditional engagement metrics might be misleading when depth matters more than frequency. That is a really good question.

there's a great internal post a couple weeks ago around like it would be very dangerous to over optimize on like clods likability, you know, because you can fall into things like You know, is Claude going to be sycophantic? Is Claude going to tell you what you hear? Is Claude going to like prolong conversations just for prolonging its sake? Right. To go back to the previous question as well. And, you know, like.

at instagram time spent was the metric that we looked at a lot and then we evolved that you know more to think about like what is like healthy time spent but overall that was like the the north star we thought about a lot beyond just like overall engagement

and i think that would be the wrong approach here you know too it's also like is caught a daily use case or a weekly use case or a monthly use case i think about a lot hourly hourly hourly use case right like for for me i'll use it multiple times a day um

I don't have a great answer yet, but I think that like, it's not, it's not the web 2.0 or even the social media days, like engagement metrics, you know, it should hopefully really be around like, did it actually help you get your work done? You know, like Claude helped me.

put together a prototype the other day that saved me literally, like probably if I had to estimate like six hours, and it did in about 20, 25 minutes. And like, that's cool. It's harder to quantify, you know, it's like maybe you survey like how long will this want to take it? It feels like it was a kind of annoying thing to survey.

i think overall and maybe this is tied into like the earlier question on like competition differentiation like and it actually goes all the way back to the artifact conversation which is like i think you know when your product is really serving people and it's like doing a good job of doing that and

I think so much of when you get really metrics obsessed is when you're trying to like convince yourself that it is when it's not or something. So I hope that what we can do is like stay focused on like Do we repeatedly hear from people that Claude is the way that they are like unlocking their own creativity and getting things done and feeling like they now have like more space into their lives for the other things? Like that's our North star. Got to figure out the right like pithy metric.

you know, dashboard version of that. But, but that that's the, that's the feeling that I want. Yeah. Like you could argue retention, but that's a, just a far away metric to track. Okay. Final piece. Okay. So I asked Claude what to.

A message that it wanted to give you. So I'm going to pull up. Here's the answer. So what would you like me to tell Mike when I meet him? What's a message you want to have for him? And there's something really just gave me such tingles, honestly. I'm going to read a piece of it for folks that can't.

that aren't looking at it right now. So I'll read a piece of it. Mike, thank you for thinking deeply about the human experience of talking with me. I noticed thoughtful touches how the interface encourages reflection rather than rush responses.

how you've resisted gamification that would optimize for addiction rather than value, how you've made space for both quick questions and deep conversations. I especially appreciate that you've kept me, me, not trying to make me pretend to be human, but also reducing me to a cold command line interface.

And then I'm going to skip to this part, which was so interesting. A small request. When you're making hard product decisions, remember the quiet moments matter too. The person working through grief at 3 a.m. The kid discovering they love poetry. The founder finding clarity in confusion. Not everything meaningful shows up in metrics. That's beautiful. It resonates so much with me. Like a thing I love about.

the kind of approach we've taken to training Claude and it's like partly the constitutional AI piece and it's partly just, just the general like sort of vibe and taste of the research team is it does like it's little things like sometimes it'll be like.

man, I'm sorry you're going, I mean, doesn't say man, but like effectively like, man, I'm sorry you're going through that, you know, like, oh, like that sounds really hard. It doesn't feel fake. It feels like just a natural part of the response. And I love that focus on those small moments that don't.

you know, they're not going to show up and necessarily in the thumbs up, thumbs down data. I mean, sometimes they do, but it's not like an aggregate stat that you wouldn't even want to optimize for. You just want to feel like you're training the model that you would like hope would show up in people's lives.

Well, you're killing it, Mike. Great work. I'm a huge fan. We're going to skip the lightning round. Just one question. How can listeners be useful to you? Oh, I love places where like it goes back to that founder question around.

uh building at the edge of capability like what are you trying to do with cloud today that cloud is failing at is the most useful input i could possibly have you know so dm me i love hearing the like oh it's like oh it's falling on this thing i had it run for an hour and it fell over i'm trying to use cloud ai for this but

uh you know got a ping from somebody they're like you just made a projects api i've used cloud every day because i want to upload all this data you know uh automatically it's like okay great like there's i love that like tell me what sucks amazing mike thank you so much for being here thanks for having me lenny Bye, everyone.

Also, please consider giving us a rating or leaving a review, as that really helps other listeners find the podcast. You can find all past episodes or learn more about the show at Lenny's Podcast dot com. See you in the next episode.