Peter Steinberger: "Fun Is Velocity"

Last November, Peter Steinberger was annoyed that there was no good way to talk to his coding agents from his phone, so he built one himself. A few months later, OpenClaw had exploded into one of the biggest open source AI projects in the world, with nearly 3,000 contributors and a peak of 4.7 million weekly downloads. At Startup School 2026, Peter tells the story of what happened when OpenClaw took off, what he got wrong as it grew, and how he eventually stopped using the product he had built for himself. He shares why the best products often start with something that annoys you, why focus matters more as building gets easier, and why, in his words, “fun is velocity.”Transcript: https://www.ycrootaccess.com/p/peter-steinberger-what-happens-when

• 0:07Speaker 00

  Six months ago, I was the future. These days, the polls say I got mocked by an anime girl. You know, I get questions like this almost every day. Usually I ignore it, or I give the media answer. Today, you get some real ones. It's gonna be five questions, 40 minutes. And I know what you might all came for. You came for loops, graphs, making codecs go "brew". This is free on my Twitter. This will help you to survive the roller coaster that might be coming for you.

• 0:50Speaker 00

  You know, yesterday Boris told you to let the model cook. I'm the guy who found out what happened when tens of thousands of people let it cook at the same time. Let's start with the question everyone asks first. How is OpenClaw only 8 months old? You know, it might be 8 months in human time, but in EGI times, it's more like 4 years. And my source of inspiration is usually being annoyed. So on a rainy day in November, I was juggling some agents, but I was also hungry.

• 1:30Speaker 00

  So I wanted to make sure that my tokens are put to good use while I raid the kitchen. And there was still no good way to just send a prompt from my phone to my computer. So some agent could check out how my agents are actually doing. Remember early 2025? And you know, guys, this is my first silent discourse. It's a very new experience, so like, give me some hands if you actually listen to me. Yes, amazing, amazing. You know, early 2025, oh my god, we're talking the old Opus 3, Gemini 2.5.

• 2:11Speaker 00

  OpenAI had O3, which was the most impressive one, but also really slow and expensive at times. And I got a dopamine hit when my agent did something right. I'm sure you remember this time. And these days, if I, if they get something wrong, I usually question myself, you know? Did I design the loop wrong? Did I not give my agent everything they need to verify their work? Do I have an error in my thinking? Am I asking for impossible things? So I came back from the kitchen, and my coding agent stopped because of something silly. And I was annoyed.

• 2:56Speaker 00

  So I spun up a new terminal session, I rambled my idea in, and I let the model cook. It built me a WhatsApp relay, and an hour later, I could send messages from my Mac to WhatsApp and back. And that in itself felt magical, but really it shouldn't have. It's like, we all did this for months already, right? We opened the terminal, and you type something in, and you get a reply. But the magic is how it felt. It wasn't a terminal, it wrote concise answers. It was proactive, like sometimes it would just like check on me during the day.

• 3:39Speaker 00

  I made it so the complexity would melt away. You don't have to think about which model, which context size, or when you start a new session. And I prompted the weights to a little bit outside the default distribution, make it feel more like a friend. And I was using it. I had so many moments where I felt like, this is the future, this is AGI. And you know what? Nobody cared. Back then, I already had a good following on Twitter. And I know it's called X now, I don't, I'll always call it Twitter. People were not getting it.

• 4:21Speaker 00

  I would keep trying to like make them understand like how magical this felt to me. But week after week, I failed. And you notice a pattern? It annoyed me. So I would create group chats with friends, and I added them, WhatsApp relay, and I would show them. I would let them talk to it. And every time, I got a strong emotional reaction. Some people were amazed, some people were scared, or freaked out even. But each time, there was a strong emotion. And the best part, there were quite a few people that really wanted it.

• 5:05Speaker 00

  And like, especially to my non-technical friends, I told them, no, this is not yet for you. And they got mad. So if that's not an indicator to have product-market fit, I don't know what is. So I spent another month tweaking the details, thinking, ah, what could I do to explain the world? You know? And then the audacity, someone sent me a pull request to my WhatsApp relay to add Discord support. You know? Like, what parts of the name are you not getting? I let the PR sit for a while, and I was thinking, and I was thinking. And then eventually, I was like, ah, what the hell?

• 5:48Speaker 00

  And out of that, I really became Claudus, because I'm good with names. And there's no more than one message channel. And so you understand how early this was. I didn't even have compaction built in yet. So like, at some point, it would just like stop. And just in time for Discord, I added a very hacky version of compaction so Mario could make a good one in Py. So it was around New Year's Eve, and as you do, I went home early to hack on it some more. And then in the first week of January, just as the geek world collectively was learning about coding agents,

• 6:32Speaker 00

  I created a Discord room, server, guild, however we call it, and I put my claw in it. And I remember the first night vividly. People would be joining Discord, and they would like watch me build it in the open. They would try to hack it, they were like talking to it, they were getting smug replies. And they see what they can do, and they finally got it, you know? Like, this was, this was the moment. I sit up all night, I let people interact with it. I had this prompt in my agents.md that would instruct it, don't do any dangerous tool calls unless the prompt comes from Peter.

• 7:15Speaker 00

  You know, this was like 6 months ago. Where all the things we wrote in our agents.md felt more like suggestions? So I watched it very carefully. I could always pull the plug. And then at 7:00 AM, I finally was done. I said goodnight, I pressed Ctrl+C, and I went to bed. But of course, I could build the software to be resilient, so it was a launch demon. You know what happens if you like press Ctrl+C in a launch demon? Yeah, it'll just, it'll be dead for 5 seconds, and it'll start up again. So while I was walking into the bedroom, my agent happily started answering God and the world. And then I slept for like 10 hours.

• 7:57Speaker 00

  When I woke up, I woke up to around 800 messages. People tried to hack it, I pulled the plug, I freaked out, I read through everything, and nothing actually happened. But this was the moment, this was the moment where it went viral. And you all been here, you know what happened next. My inbox exploded, reporters tried to call me in the middle of the night. Did you know about this feature that Apple built when you put it on Do Not Disturb? Where people call you a few times in a row? That I think would think it's an emergency, I would still let calls through. I didn't know about it, but reporters did. My email inbox was more like a waterfall. Yeah, the Mac Mini sold out, I think they still sold out.

• 8:42Speaker 00

  I got more invites to podcasts in a month than I did in my 39 years before. And Tropic sent an email demanding the name change, and like, drop the lobster. And the project molted a few times, Claudus became Claudebot. Then there was a very short time where we don't talk about the name. And then it started on OpenClaw. Jensen called it the most successful open source project in the history of humanity. And meanwhile, my inbox was flooded with reporters, security people, and countless curious humans, and also agents. The numbers still don't feel real to me.

• 9:23Speaker 00

  In 8 months, more than 18,000 different people opened an issue or a pull request. Over 111,000 in total. I did the math, you know, who am I lying to? My agent did the math. Almost 3,000 people have commits in the repo. And some people were mad at me, because clearly they did it first, and I stole their idea, and they sent me links of something I've never seen. Some people call me AI Jesus. For some, I became the Antichrist. At some point, I started collecting the opportunities. There is a new one every few weeks. The most recent one is actually from yesterday.

• 10:14Speaker 00

  What do we learn here?

• 10:17Speaker 00

  Be careful what you wish for. I was not ready for all this attention. It almost broke me. Like, I was that close of just deleting the whole thing. I stopped answering my friends. I didn't even want to look at my phone anymore because it was just a stream. And of course, somebody leaked my phone number and also a lot of private details because I'm an enemy of humanity. And here I am just wanting to build something cool.

• 10:47Speaker 00

  And now we're getting to question two. Did you sell out? You know, this wasn't my first ride. I spent my twenties and my thirties building a B two B software company. I wrote a PDF framework.

• 11:04Speaker 00

  By hand, like an animal. I bootstrapped the company. I grew it to almost eighty people. I ignored the competition. It became the thing most enterprises would buy. And eventually I passed things on to my co-founder. I sold my shares and I very badly burned out.

• 11:21Speaker 00

  Retirement? The idea of it sounds great. And I spent almost three years wandering around aimlessly, catching up on life and parties. I did all the things that I kind of missed out on life. I had months where I didn't even open my computer, you know, just casually checking the internet with my phone.

• 11:46Speaker 00

  Like a normie.

• 11:48Speaker 00

  I always knew that if I if I give myself enough time, the urge, the urge would come back.

• 11:57Speaker 00

  I always thought the urge would be code.

• 12:03Speaker 00

  I always loved programming.

• 12:06Speaker 00

  But it took me a year to understand that that's not entirely correct. I love building. Programming was just a means to an end. And here I was,

• 12:20Speaker 00

  eight months after I found my spark again. And my inbox was full of VCs begging me to take their money.

• 12:29Speaker 00

  And I didn't know I want to. So when the big labs came knocking and suddenly I was on the phone with

• 12:37Speaker 00

  Mark, Sam, Fjordas. This seemed like a much more interesting path. It also felt unreal, right? Talk about imposter syndrome. I mean, that's an important lesson for you. Everything that everything you can build can be forged or cloned. But your name cannot. So your personal brand is way more important than any single product that you ever will.

• 13:04Speaker 00

  Start working on that before you need it.

• 13:07Speaker 00

  So yeah, I know how to play the game. I also know that doing this was the equivalent of selling my soul dot M D. If you know, you know.

• 13:18Speaker 00

  The decision was not easy.

• 13:21Speaker 00

  But I, if I learned anything during my time after the burnout, it's it's this, it's trusting your gut. And my gut told me that I like OpenAI the most. Did Hermes win?

• 13:35Speaker 00

  And the short answer I can give you is

• 13:38Speaker 00

  they beat us where it hurt. We're still there.

• 13:42Speaker 00

  And both of those are my fault and my doing. In the months after the release, we got absolutely crushed by security reports.

• 13:56Speaker 00

  In some ways, we were the prototype of what many open source projects now experience.

• 14:03Speaker 00

  And even though most were super edge casey, I felt the pressure.

• 14:10Speaker 00

  And then the press, the press said twenty percent of our skills are malicious. Now, we actually were a paper bit this. We did the the numbers and the numbers are more like zero point three percent. We scanned all sixty seven thousand. We shipped the we shipped the paper. But you know,

• 14:30Speaker 00

  a correction never travels as far as a scare. I felt this responsibility. The world discovered Open Claw. And even though there was this big scary disclaimer, actually much bigger than a kid on the slides, when you install it, I knew many people wouldn't read the docs. So I really focused on that, hardening the code base, building layers and layers of security. I did sandboxing, allow lists, a web protocol with permissions built in. We were shelling out to Python for some file operations because there were some primitives that are simply lacking in TypeScript.

• 15:11Speaker 00

  To ensure your agent stays in the workspace, it doesn't follow siblings and that the configuration files are written atomically. Most of the users didn't care shit about that. Sure, they they like the abstract term of security. But in all practical terms, they updated. I broke something they depended on. I made things slower and I made things more difficult to update. And another thing I have to admit, I got sloppy. Because now I had to my time shifted between open source, the press, spending countless times on the phone with lawyers to set up a five oh one three American nonprofit. I worked on my O one.

• 15:55Speaker 00

  And you know, OpenAI is its own world that is interesting and demanding. I brought on help and we got such an amazing community of maintainers that are very much respected. And everyone added their own little feature. I felt I felt like I'm a bit in a hard place.

• 16:19Speaker 00

  After all, these people work for free, right? So who I am, who I am to to to tell them what to do?

• 16:26Speaker 00

  And also my attention was all over. So we added a lot of features. You know, features are the fun part.

• 16:36Speaker 00

  A new feature is just a prompt away. The real cost comes after. Every feature we shipped, of course, with a configuration option. Because we didn't want to break everyone's setup. At our highest, I had to count that. We ended up with around nine and a half thousand configuration options. If you count all the permutations, you can write all the tests you want. It is impossible to cover all of these and not break things from time to time. It is infinitely harder to evolve software that has users.

• 17:16Speaker 00

  Meanwhile, other companies, they were fueled by VC money. They pushed ahead. The Anime Girl company did it especially well. People started inserting themselves into pretty much any conversation on Twitter. While we were burned in security groundwork and features, they had a simpler story.

• 17:37Speaker 00

  An aggressive marketing campaign and a one liner to migrate people's claws. The main thing, though, that really hurt the project was Entropic. Not the name. The part was stressful, but I I kind of understood and they were really nice about it. It was the fact that I optimized too much on their model. I built Open Claw with Codex and G P T, but the harness for a long time really worked the best and was optimized for Opus. So when they pinged me with around twenty four hours

• 18:16Speaker 00

  notice that they're going to disable the subscription for everyone, there was not really enough time to change course. I mean, sure, we we support open weight models. We did a lot of work on them, but they really weren't that great yet. And the early OpenAI models

• 18:38Speaker 00

  simply lacked character.

• 18:42Speaker 00

  So maybe write this one down.

• 18:45Speaker 00

  Your dependencies business model is your business model. You know, that's how fixed now. Sounds pretty awesome. Open weight models are actually good.

• 18:58Speaker 00

  I learned a lot about harness engineering. But in many ways, people moved on. You can see that in our download charts. We bottomed out at around eight hundred

• 19:13Speaker 00

  thirty five thousand weekly downloads in May. And then after being declared death in in June, we peaked at four point seven million, the highest ever. Both of those are true at the same time. A hype is like the weather. You might see it coming, but you can't control it. In my case, it was a storm. Question four. Is it still fun? You know, somewhere around February,

• 19:40Speaker 00

  it stopped being fun. I started to feel like it started to feel like a responsibility. I woke up and the man who didn't want to build another company found himself in a situation where he had two jobs. Or should I say a job and a calling? I was struggling and worst of all, I stopped using my own product. Somewhere in that time, I stopped making a product I love and I worked on making something for everyone. It became less of a thing that I use every day and more a thing that I saw and felt was work. And I wanted to picture who everyone really is. One of them had a grocery agent.

• 20:22Speaker 00

  Another one tried to social engineer my bot. Between everyone adding features and all the organization work, I became the person that fixed the bugs, fixed the security issues, and provided support and built a foundation. And because all these people were like giving the rumor mill, "Oh, OpenClaw is owned by OpenAI", I didn't want to take too much help from OpenAI. I mean, yeah, they gave me token and I, boy, did I use that.

• 20:54Speaker 00

  But I was also pulled into other projects. And there was a whole flood of people that I couldn't this easily block who wanted to talk to me. In hindsight, I could have many done differently. Like, I could have asked for more help. I could have moved responsibility off my plate. But I was so deep in everything that I didn't take time to think through strategically. Luckily, I met a bunch of amazing people and little by little, things aligned. I figured out my visa, eventually formed a nonprofit. We got amazing companies as donors and I found some really good people that believe in open source

• 21:38Speaker 00

  and started working with me. I also need to give Nvidia a special shout out because they were very early and they simply asked me what I need. And then they sent people to take over much of the security work. And I think it was somewhere in May, around my birthday, where I had this feeling that things are starting to feel good again, where the joy of building for me was coming back. And yeah, somewhere in the press, the press decoined an OpenClaw killer every other week. At some point, I think I counted twenty of them. There's even a literally a project called OpenClaw Killer.

• 22:21Speaker 00

  It's an uninstaller, which is totally unnecessary because we have an uninstaller, but you know.

• 22:27Speaker 00

  But none of the killer stories ever picked up what this is actually about.

• 22:33Speaker 00

  Open source. My source of inspiration is being annoyed. These days, I get annoyed when I have to use software where I can't just send a prompt to my agent to change it. That's the fun part that's coming back. It's hard to compete with someone who's just there having fun. Fun is velocity.

• 22:58Speaker 00

  The weeks I enjoyed building, the product got visibly better. The weeks I didn't, we shipped config options, question five. What's next?

• 23:12Speaker 00

  Yeah, some people in the audience might be like, "Is this finally the part where he talks about graphs?" First of all, I'm super happy with where we are with the foundation. Our mission is to bring people closer to AI. And things are changing so fast. For many people, it feels scary. I'm proud of one thing that OpenClaw achieved.

• 23:37Speaker 00

  And that for many people, it moved the eye from this thing that's like nebulous and scary into something that is fun and weird, you know, lobsters and all of that. And we'll keep pushing there.

• 23:52Speaker 00

  Keep building a great ecosystem of open source software

• 23:57Speaker 00

  with events that bring people together and with education. We have ten people now on payroll. We're hiring a few more roles, including a CEO. Second of all, I can't admit claw a noun.

• 24:12Speaker 00

  You know, Kparty dropped the open Satya says enterprise-grade claws in Microsoft's keynote. There are thirty-three thousand claw-named repositories. If we are in a simulation, we are certainly in one of the weirder ones that won't get shut down. I dig this part of the future. Third, we still don't have an agent that's always on, always syncing. There's still so much to do. The landscape and the tech in AI are evolving faster than the software that we build around. And that's an opportunity for all of you.

• 24:54Speaker 00

  Our workflows are also evolving. Like the vision I had early on, where we shouldn't think about session or compaction. The world is finally, the models, the tech is finally getting to a stage where this is becoming a reality.

• 25:12Speaker 00

  We're entering a world where we finally move on from the text, text-only interfaces, to voice and multimodality. Just yesterday, we got a hack working that your claw can now FaceTime you. And this is kind of what matters why OpenClaw exists at all. Every lab will sell you an agent. OpenClaw is the alternative. Open source runs everywhere, works with any model. And if you run local models, your data never has to leave your device.

• 25:48Speaker 00

  Your agent, your machine, your life. That's not even my thesis, that's Gary's, you know?

• 25:57Speaker 00

  We just shipped it first. So we also finally are building OpenClaw with OpenClaw again. But this time with a twist, where everyone sees each other's session on a Teams server. And there's a claw that knows what everyone else is working on and can also take over orchestration of the work. And we are finally leaving this slowly, this weird blip in the future, where people work in terminals and run around with their laptops open because the agent needs to keep working. If you only remember three things. Number one, don't stop having fun. Fun is the ultimate driver so you can get the best ideas. Number two, listen to your gut.

• 26:41Speaker 00

  And also, fix the things that annoy you. It might just become the next big thing. And number three, stay focused.

• 26:52Speaker 00

  You know? Another podcast is not what will make you win. Live in the future, build what's missing.

• 27:02Speaker 00

  And when they write your arbitrary, keep shipping, it confuses them. Now, these were five questions. I'm sure you have many more. And I think we have plenty of time for QA. So first it was agents, then loops, then graphs. How are you building these days? I mean, it was always sessions, right? But in the beginning, you had to like actually care that like you would clean and like you would make sure that your instructions are coherent. And these days, it's more like my sessions are topics. Clearing a session, sometimes even a disadvantage because there's so much information in there that helps the agent.

• 27:47Speaker 00

  But the big thing, the big thing that shifted is I tried to make the agent a more proactive work for me. So when I shift my attention to something, I don't want to read issues. I want to see fully reviewed and tested PRs. Maybe I like the feature, maybe I don't, but like I don't want to like split my attention. At the same time, it works. If you come to me and you tell me this feature idea, I'm gonna get mad at you. Like, it's so easy that you just discuss the feature idea with an agent. You build it, you make screenshots, you let me play with it. That way, if it's good, we can like immediately enter in it.

• 28:29Speaker 00

  But most of the time, people will figure out why it's not good and don't even come to me. What comes after graphs? And what's next for OpenClaw?

• 28:40Speaker 00

  I know, like sometimes I like to shitpost on a Sunday and then like my Twitter explodes. But also, it's not a shitpost, right? So anytime you, you know what we as engineers did for the longest time? We built automations to make our life easier. That's like, that's been going on since our profession exists. So if you design, call it loop, call it graph, call it workflow, it's kind of all the same. If you design something that gets a trigger, gets an input and does something for you.

• 29:18Speaker 00

  And maybe there's a decision in the way, boom, there's your graph. It's not, it's not magical, even though like, you know, I favorited some of those graph engineering posts because I'm kind of curious what their opinion is that it would be. In my world, it's just like, it's just a better way of our automation story that we did for so long already. In a world of build fast, ship fast, how to make sure that what you build is still reliable and scalable?

• 29:51Speaker 00

  Yeah, that's the part I messed up for a while.

• 29:55Speaker 00

  Because I was not, I was not focused. And the models were not really good at testing.

• 30:04Speaker 00

  I think that the models are really good now. We have, we not just have sessions that remember. We have orchestration trained into models so they really understand and know to use subagents. We have computer use, we have browser use. Like, all of that together is like your perfect Q and A environment. Like, I did that yesterday where I spin up Codex, used twelve subagents, understand my project, break it down into features. And then each, each subagent would like stress test the feature or code review feature and then inform the other session where to focus testing on.

• 30:46Speaker 00

  So we're not yet at the point where you can automate everything. You'll still, you still need to do some manual click-throughs so that you know how it feels. But like for a lot of the typical bugs that users will encounter, you can actually now, you can prompt your way and you get very far.

• 31:07Speaker 00

  Okay. AI tools. Ah, what's your decision you made purely for speed early? That you still live with today? I think that was really early in in deciding that.

• 31:23Speaker 00

  I don't read all the code. I see code review more as a. As risk management. You know, sometimes you touch a system that is. Scary. Kind of wanna like read a little bit closer and other times. You build UI. Do I really care how your eyes build if it looks correct? No. So you kinda. You glance over or you simply. You simply accept that.

• 31:53Speaker 00

  It looks right. Part of it is just like.

• 31:57Speaker 00

  You develop a little bit of a feeling how long something should take. So if I do a small tweak that should like change how dragging works. And it takes three hours, I know something's wrong, I'll look closely. But otherwise. Part of code review is simply like observing. Looking how big a change is and trusting your gut. Okay. AI tools make it easy to build a product in a weekend now. But building isn't the hard part. Getting people to use this. How would you go from a working prototype? To your first ten real users today? Well. I think that was part of what I addressed in my talk. User number one. Should be you. And. My users two to twenty were friends. So.

• 32:44Speaker 00

  I'm sure you have some people. That would actually test your stuff. But you need to be the first user if you don't. If you don't get excited about your building. It'll probably not make sense.

• 32:57Speaker 00

  Like. In this day and age. Eyeballs are kind of the the most expensive currency because. Building something so fast now. How do you balance solving issues that annoy you and make features you think? People. You want. That's a hard one because oftentimes it it kinda goes together. I get annoyed if something's not there as I wanted. I haven't I haven't, to be honest, I haven't fully figured that part out yet. I feel. I could just work for months on issues because there's always gonna be weird edge cases in software. Uh, especially if you add more and more features. But then again, if I only do that, I'll lose interest in working. So it needs to be like. It needs to be a healthy mix.

• 33:41Speaker 00

  If you could back and change the thing. One thing about open claw. What would you change? I would be less stressed out. About. Security researchers.

• 33:55Speaker 00

  They are really good at making you feel really bad. They would send a report. They would email me, they would call me. They would through everything they can possibly get to get my attention. But not actually to help the product. In most of the case, it's really just. For them to get clout. For them to get a point, oh, we found something. And most of them really. Send reports that their agent produced without actually even testing it. I would, I would take a stronger sense of explaining. What are the parts that we guarantee? And what are the parts that? Will not be fixed because that that's not our security boundary. But I honestly, I had no. This was my first time I was.

• 34:40Speaker 00

  Exposed to this world, so I I just didn't know.

• 34:45Speaker 00

  How to handle that. And I I lost a few months and got a few gray hairs. To learn. What's the single biggest bottleneck in today's agentic infrastructure? Reliability. Tooling. Memory. Evos. Managing compute, if that makes sense.

• 35:08Speaker 00

  Like.

• 35:10Speaker 00

  If I run one test locally in my machine. TSG will spin up sixteen threads and will bottleneck my machine. If ten sessions do that.

• 35:21Speaker 00

  Two of them will probably timeout and will have to do it again. And there's no really good system of like managing all of that. Now, if I do web stuff, it's easy to create a cloud session. If I do like something that requires Mac OS. That's already where like ninety nine percent of the tools fail me. If it's something that needs other stuff that's on my computer, same. And we haven't really built something yet where. Things could easily move from here to here without issues, at least. I didn't see good stuff working yet.

• 35:53Speaker 00

  Or where I could.

• 35:57Speaker 00

  Drive a fleet in a reliable way. Like right now.

• 36:03Speaker 00

  I use too many systems, I screen share into some computers to like distribute the load. I shouldn't be doing that. How do you keep an open source project opinionated? And pointed in one direction? Whether they're just merging the N plus one PR that adds a random feature? And how do you communicate that direction to the community? Have you ever said no to popular PR because it pulled the project? Off course? Yeah, yeah. I would say I.

• 36:34Speaker 00

  I didn't say no enough.

• 36:39Speaker 00

  These days I.

• 36:42Speaker 00

  When I do new open source, I write a vision dot M D file. Where I can explain. What it is now. Where I see this to be. But of course, it's it's incorrect, it's not perfect science. And it's something I I need to adhere to better because it is. It is always tempting to add this one feature that looks really cool. But. What you rarely think about is. When you merge this feature, it really means. Here's this pile of code that I don't need, that. The person probably doesn't really understand, that I don't fully understand, that I also got responsibility. When do you expect to have claws that are perpetually running? That are proactive in their work? I mean, honestly.

• 37:28Speaker 00

  That's not so much a tech problem, it's more a token problem. Where. We could do that today.

• 37:39Speaker 00

  But you wouldn't get very far with your subscription. And not everyone.

• 37:46Speaker 00

  Is willing to spend so many tokens. It's also.

• 37:52Speaker 00

  But the part is not easy is designing a system that.

• 37:57Speaker 00

  Doesn't just burn empty tokens. Even the my early system of like. Heartbeats. Was too static and not.

• 38:08Speaker 00

  Not proactive enough. And then especially bad if you have a large session. And then one hour later, you call like a heartbeat check up on everything. And that means you send six hundred thousand tokens back to the server after the K V cache cleared. And you pay.

• 38:27Speaker 00

  A stupidly amount of of of money for. A lot of. Not useful work. So there's a lot of things that can be done to optimize that. It's also really, really hard. Can you tell us more about your own personal setup? What do you host your claws on? What model are you running? What harness do you use? Do you still read?

• 38:54Speaker 00

  Can we scroll? Do you still read your code? I use my. My MacBook. But I usually. Use. Jump desktop to screen share into my studio. And then just use the computer there because that one's always running. That one, I can run whatever I want, fast. And I'll not drain my battery. And I can close my laptop. And things keep working. Um, and I have a few other. Remote machines where sometimes we can see. The the part that's really nice about it is because I do a lot of Mac software. Agents love to take over my screen and click around. And if you put that in their own, if you give them their own machine, it will not bother you.

• 39:39Speaker 00

  Otherwise, you you'll fight with the agent for the mouse cursor. Do you still read your code? I think I answered that a little bit with. The term risk management and also. If I do open source by myself. Is a difference, it is a different. Risk management than if I do software at OpenAI, where we do still read all of the code. Peter, how would you approach? Your next startup idea?

• 40:09Speaker 00

  I don't know, should I tell this to everyone? Like, I feel like it gets a lot of copies. I mean, the most important thing is you need to build something that you wanna use. Otherwise, it'll just not gonna be good.

• 40:20Speaker 00

  Second of all is.

• 40:23Speaker 00

  I hope you worked on your personal brand and on visibility. Because in this day and age, there's so much noise out there. That your hardest problem is not the tech, it's not the software. Not even the people, the hardest problem now is like getting eyeballs. Maybe I would pick something again that's. That's in the category. Hard. And boring.

• 40:47Speaker 00

  Because that's usually a category that.

• 40:51Speaker 00

  Is a little bit easier to actually find people that will appreciate when you solve something. If you pick something that is fun, even if it's hard. You can have a very tough time, especially in a time where. People can just prompt things into existence. All right. Last one for today. What's a product you want someone to build? You know, I feel it's very easy to have. To get a.

• 41:19Speaker 00

  A test box for Linux. It is unreasonably hard. To get one for Mac that works really well. And all the stuff that I I I got for Windows. Is also quite annoying. Um. I haven't found a really good provider yet that.

• 41:38Speaker 00

  Does all of that fast and cheap. Um, I'm not sure if this is the business you wanna be in because dev tools are inherently. Hard. But that's something I would love to have. Thanks, everyone.