Archive for February 22, 2026
Keep Going: Social Capital Is Still Capital
“When you're going through hell, keep going." This podcast is about failure and how it breeds success. Every week, we talk to remarkable people who have accomplished great things but have also faced failure along the way. By exploring their experiences, we can learn how to build, succeed, and stay humble. The podcast is hosted by author and former TechCrunch and New York Times journalist John Biggs. He also hosts The Innovators, a podcast focused on brand new startups and C-Level Executives and Creators. If you’d like to appear on either show, email john@biggs.cc. Our theme music is by Policy, AKA Mark Buchwald. (https://freemusicarchive.org/music/policy/)
I sat down with Constantin Kogan last week after we randomly met in Salt Lake City. We both live near New York. Sometimes the universe has a sense of humor. Konstantin is the founder of Holistic Capital, a multi strategy investment firm focused on digital assets. He also runs a podcast called Holistic Investments. Over 100 episodes. More than 600,000 followers across platforms. Not bad for something he started during COVID while stuck at home. But the interesting part of his story is not crypto. It is not Bitcoin in 2012. It is not Ethereum in 2016. It is not being early to hedge funds or registering with the SEC. It is this: social capital is capital. During COVID he found himself in a tough place. Like most of us. No travel. No meetings. No momentum. He asked a simple question. What can I do that I actually enjoy? His answer was long conversations. Honest conversations. The kind you have in a kitchen at midnight over wine. So he started a podcast. No monetization plan. No big strategy. Just curiosity and discipline. For five years he made nothing from it. Most podcasters quit before episode thirty. He kept going past one hundred. Why? Because he was not optimizing for money. He was optimizing for relationships and learning. That changes everything. We talked about failure. I asked him about bad trades. Crypto winters. Market crashes. He surprised me. The real failures were not financial. They were relational. Picking the wrong partners. He described business like a marriage. You can survive small disagreements. But when a real crisis hits, that is when character shows up. Do you share a vision. Do you share values. When it gets ugly, does your partner protect the mission or protect their ego. You cannot really test that in advance. There is no checklist. No personality quiz that guarantees success. At some point you rely on judgment and instinct. And you accept risk. That is uncomfortable. But it is honest. We also talked about investing. Early in his career he focused on technology and timing. Now he looks at people first. Ideas are abundant. Execution is rare. Motivation varies wildly. Some founders want status. Some want money. Some want to prove themselves. Some want to change the world. Only one of those types will survive when things get hard. If you are building something, remember this. Investors are not just evaluating your deck. They are evaluating your stamina. Your alignment with your team. Your ability to handle conflict without blowing up the room. And if you are thinking about starting a podcast or some other media project, understand what you are signing up for. It is a business. It consumes time. It demands consistency. It does not pay right away. Maybe not for years. But it builds something else. Reputation. Network. Intellectual capital. A record of your thinking. That can compound. Konstantin does not even call himself a VC anymore. He trades liquid markets now. Algorithmic strategies. Volatility. But the podcast still runs. The network still grows. Yesterday he met the co founder of Venmo and invited him on the show on the spot. That is how opportunity works. Quiet compounding. Relationship by relationship. You cannot fake that. You have to show up. You have to publish. You have to keep going when the numbers are small and the monetization is zero. There is a lesson here. Build things that create optionality. Build things that connect you to other capable people. Build things that make you better at thinking and listening. Money follows. Sometimes slowly. Sometimes indirectly. But it follows. In the meantime, protect your partnerships. Choose carefully. Align early. Agree on how you will handle conflict before it arrives. Because markets rise and fall. Technologies shift. Cycles repeat. Character does not. TRANSCRIPTWelcome back to keep going. A podcast about success and failure. I’m John Biggs today on the show. We have Constantin Kogan. He’s the, uh, GP at holistic capital. And you also have a, really cool podcast, which I’m going to be on eventually. So I get to actually, Constantin Kogan (01:18.537) Mmm. John Biggs (01:37.954) meet your audience. But we met just a week ago and you have a really, cool story. So tell us what you’re up to, Constantin. Constantin Kogan (01:47.235) Hi, John. First of all, an honor to be here. Yes, we met in Salt Lake City out of all the places, ironically, live in close by in New York. I don’t know where to begin the story. guess maybe just a little bit of background. I’m originally from Ukraine. was born and raised there, 11 years in the United States. I started my career as a... John Biggs (01:56.236) Yeah. Constantin Kogan (02:12.651) I’m a modernism future trader. Chicago Bota Trader was my first venue where I started to explore financial markets. From there, went through a hole and bought my first 5 Bitcoin in 2012. 2016, I a conscious choice to go all in when Ethereum got out and... thought that programmable money is definitely going to be the future of tokenization of all the assets. 2017, I became a partner in the first crypto fund of hedge funds in the world. We’re the first SEC registered firm. And from there, you know, I had a wild journey co-founding three companies, you know, investing in 80 plus venture startups and running my own. you know, my own hedge fund, working for hedge funds and now focusing on holistic capital, which is basically a multi-asset, multi-strategy investment firm, mostly focused on digital assets, but eventually we will work with different assets on blockchain as well, which I think that’s where the future is going to. And also, as you mentioned, I... also run Holistic Investments, which is the podcast which I started during COVID time. My first guest was Dan Moritz from Pantera Capital because we invested in Pantera so we good relationships with them. Since then, I 100 plus guests on my show and enjoy learning from incredible individuals. John Biggs (03:49.278) And you’ve got you got like 600 plus thousand followers across your across all your platforms. What do you think led to that level of success? And what is what does that give you as a VC? Like I know what this gives me as a I don’t know, just a putz on the internet. But what does that give you as a VC? Constantin Kogan (03:55.957) Yes. Constantin Kogan (04:10.313) Well, to be completely transparent, I don’t consider myself as a VC anymore. Like I used to be. Right now I’m... mostly with trading more liquid assets, right? So you can think about it as algorithmic trading firm, high frequency trading, right? Closer than, so I used to be at VCN. I thought that was incredible opportunity in emerging markets, right? But regardless, what it gives me, it gives me network. I think... Social capital is another form of capital, right? Not necessarily like people who invest in you is your, you know, main business partners in life. You know, some people like stay with you regardless of whether you succeed or you fail. And I think the more value you bring to other individuals, like what look what we’re doing today, right? You’re the first who allowed me to be on your podcast, which I’m very grateful for, and then you’re gonna be on mine, and that’s hopefully gonna inspire others to do the same and share thoughts, you know, learn from each other. I would say intellectual capital and social capital, that’s what’s the primary goal for me, and that’s how I’m giving back to the world by educating the future generations. John Biggs (05:28.396) Mm-hmm. So tell us about the growth of this media empire, I guess you could say. So you started out just deciding to do this. What was the impetus? Why did you want to do it? Constantin Kogan (05:40.105) Well, media empire, it’s a big word. love how you frame it. Future media empire, yes. Yes, I appreciate it. Look, I, again... John Biggs (05:47.03) Yeah, we gotta tuck each other up, yeah. Constantin Kogan (05:54.363) Wholeheartedly, was in a very tough spot during COVID. I think it was a very challenging time for everyone. And I thought to myself, what can I do? I mean, we’re sitting at home. There’s not much to do. you know, everything is digital anyway. You cannot go out. And I started to ask myself, it was more of a soul searching exercise. Like, what can I do to at least do something what I love to, you know, have a cohesive discussion and also somehow impact others to inspire them or to help them in some way and that podcast format was the most relevant for me. I’ve listened to a lot, I’m a big fan of know like Joe Rogan, Alex Hermosy, know and Alex Friedman and many other like greats know people who went bold and started to invite other individuals, have long discussions with them so my My format is about 60 minutes, right? So it’s enough time to learn about a person, about their journey, about where they’re coming from, and also how they achieve this success. And also ask them uncomfortable questions, which allows to bring less controversy, but more about what were the failures? What are the learning lessons? Something that you would not talk on your board meeting or somewhere in the traditional media, right? So more like honest, friendly conversations, you will have when you’re drinking wine with your friend in the kitchen. John Biggs (07:30.606) So tell me about some of those failures. think you, I mean, right now we’re looking at a crypto winter. So that sounds like, it sounds like you might have some issues right now, but tell me about the failures as you move through and try to enter this space. Constantin Kogan (07:44.255) Yeah, as a matter of fact, we’re doing great. maybe we like when you’re trading. the market is a strategy, you’re not like long like any asset like we’re making money even shorting right now. So for us, the volatility and big spikes is where we make most of our money. And that’s the exciting part. Like, and that’s when I finally understood after three cycles in the industry that how to navigate the markets. So that’s number one. The failures mostly, ironically, I wouldn’t call them financial decisions. It’s mostly who you’re going with. So I would say how to pick your partners. Like, and I think that’s one of the most challenging parts because if you think about a business, it’s like as a form of marriage, so to speak, like a very big connection you spend with your business partners a lot of time, you’re building something, it’s your venture is like your baby, right? And when there is, I would say, not clear understanding of what is the vision, how do you work together, like you know what’s gonna happen next, like when the actual challenges come into play, that’s when you learn the character of a person, that’s how you learn how they react, that’s how you learn if they’re gonna be supportive or they’re gonna put you down or maybe even like publicly humiliate you, like there’s a lot of things that are completely unknown besides the business challenges, we’re also talking about like basic human to human relationship. And I would say that the biggest learning experience for me as a failure is how to choose the right partners and how to make sure that these people not only share your vision, but also there will be for you when it’s going to be the hardest, when nobody will want to support you, when the market is against you. And in these moments, it’s incredibly important to have a person who Constantin Kogan (09:46.024) is basically you’re person that you consciously decided that no matter what you go till the end and you make it a success. John Biggs (09:53.582) I mean, have you ever was give me an example of someone who who didn’t fulfill that for you. Constantin Kogan (10:00.043) Well, I don’t want to put names, right? But I would say, I should say if you read statistics in traditional VC companies that are well-funded, let’s imagine even they found product market fit and everything, one of the third aspects why companies fail is because of the pure misunderstanding and quarrels between the teams, right? And the founding team. So it’s an ego issue, right? John Biggs (10:03.918) We’ll just kick. Yeah, sure sure sure Constantin Kogan (10:29.578) There are people who are money driven, there are people who are purpose driven. When you are purpose driven, like you’re always trying to ways how to mitigate certain conflicts, how to find a way to harmonize a relationship, even though you might disagree on very particular topics, right? Very tactical, pragmatic business decisions, but still respect. another person who might disagree with you. And then you find out that some people besides can be brilliant, analytical, and very active in business. They might not have, let’s say, what we call in a common sense, like high emotional intelligence. And that equals to... bigger misunderstanding, right? When you like, again, marriage is probably one of the most like relevant examples when two people, let’s say they’re not on the same page, it creates like an environment where you might be successful in other aspects of life. But when you come back home, let’s say, and you were not like feeling. that it’s the most supportive environment, then everything else becomes challenging. It becomes, I wouldn’t call it obsolete, but I would say it becomes irrelevant. that’s, would say, the most important example. whenever you’re picking people who you want to go with, and by the way, that’s also... relevant for the partnerships, right? People who will be, let’s say, your investors or people who will be your customers, who one of the biggest ones. That’s one of the most important aspects. Are you in the same page? Do you have the same values? Is it like, are you going to be able to work long term together? John Biggs (12:21.326) Okay, yeah, fascinating. So what do you do to test people before you trust them? Constantin Kogan (12:30.121) You know, it might sound funny, but I don’t think there’s a way to test it. I really don’t. think it’s some... somehow it’s a gut feeling, you know, like it’s when you pick a partner you see immediately, like whether there’s gonna be potential conflict and whether you’re gonna be able to navigate this conflict so that you come out... the same as you started your relationship. And yeah, sometimes it’s more about the examples of life, the practical issues that help you. For example, my current business partner, know each other for 17 years. So we’ve been through a lot of hardships. We know how would each one of us react. And sometimes you know a person from an industry or somebody referred this person to you and you meet for the first time, you think, oh, wow, it’s a great idea. We can make a lot of money together. But eventually, when a serious conflict situation arrives, like maybe small things you can dodge or you can raise above those issues, but then the big one destroys everything. And it’s impossible to know in advance. That’s the irony of life. So you have to just have, mean, some people do psychometric analysis, like astrological analysis, right? I don’t believe it works. It’s just a matter of that you agree from the get-go. What are you going to do? Not if, but when the issue is going to arrive. John Biggs (14:13.43) OK, very interesting. How do you make decisions on what to invest in, what to buy, that sort of thing? Like, let’s say we’re talking to an entrepreneur right now. What would you be looking at when you beat them? Constantin Kogan (14:29.961) Well, as I mentioned, right now we’re mostly focusing on liquid market, right? John Biggs (14:34.382) Well, yeah, but yeah, but like before or just in general, because I mean, we have fairly. Constantin Kogan (14:40.677) Before as a startup, same, I look at the people a lot. Before I looked at technology and the scalability, whether it can be 10x, 100x idea, whether it’s a good timing, whether the market is ready, when they have a product market fit and they have some traction, whether they have some revenue or some goods, I don’t know. downloads or like you know any like monthly average users like daily average users like you know that’s sorry active users right so but nowadays I actually look at the people more mostly like after investing in 80 projects and realizing that most of the startups are just statistically like they will fail like so the only question now remains in my head is like whether this is the right team to execute the vision The idea can be incredible. The vision can be also like, you know, right on time, like on point. You have like backing, like, you know, of the top VCs or like angel investors. But then you look at the people and you think, okay, well, are they are in a good place, like in their life? Do they have enough experience? Are they motivated enough? Because motivation of founders can be also very different. One founder can have, I don’t know, two previous exits and for him it’s like more of a like he really wants to change the world while other can it can be his first startup and he’s gonna grind to make it happen no matter what just because like he wants to you know prove himself like and there is other scenarios where people already just do it John Biggs (16:12.398) Mm-hmm. Constantin Kogan (16:18.372) for reasons because they need to do it, because there was a merger or because somebody told them that’s going to be a great opportunity. So that’s the most important, think, right now. You look at the people, you have multiple meetings, and you try to analyze whether they’re going to be the right fit for this particular idea to execute it. John Biggs (16:40.47) And for folks in your boat, they start up? Should they start a podcast or would you recommend it? Or is it a is it too is it a pain? Constantin Kogan (16:44.169) You know, starting a podcast is first of all, you have to think about a starting a business. I mean, you know, better than anyone else, it’s a very challenging endeavor. It requires a lot of time. John Biggs (16:53.39) Mm-hmm. Constantin Kogan (17:00.173) not always I will pay out immediately for five years. I haven’t been able to monetize it. I was just doing it for my own passion, right? You know, because I truly believe that learning from other great minds was something that I wanted to. And if at least like a few hundred people will be inspired by that, that was my motivation. But then you realize, okay, well, like you spend your own time, you spend resources, right? you we’re spending right now, you allocate half an hour of your valuable time in life, right? Then you’re going to spend time on editing, right? Then you’re going to spend time on distribution. And then you ask yourself, is this going to be monetizable because you spend all this resources and you hope at some point it will be. And if you don’t have a clear answer when and how it’s going to happen, then the question is like, how long you’re going to last. Statistically, most of the podcasters who go into this journey, they don’t last more than 30 episodes. So if you’re over 30 episodes and let’s say you get into 50 to 100, that’s already, that means you’re a survivor. The question is how big you want to go. That’s all. John Biggs (18:14.74) Mm-hmm. Yeah. mean, think I’ve got 260 or something like that. So I feel like I’m a survivor, but I’m in the same boat where it’s in terms of monetization is kind of silly. so where can people find what you’re working on? Constantin Kogan (18:27.784) Holistic investments you can Google my name Konstantin Kogan and holistic investments. I am an Apple podcast Spotify. I have seven other platforms There’s also a YouTube version of it right there. I put her telegram Instagram the short version of it YouTube obviously the full So I’m doing right now in studio in New York. if any of your listeners think that you’re a great potential guest or you want to refer someone, feel free to go to my website, constantnikogon.com and there’s a form you can submit someone and I’m like my team would be happy to review it and come back to you. And yeah, it’s mostly relationship based nowadays. for example, yesterday I met co-founder of Venmo. honestly was not planning to do that, right? And then I was very inspired, he’s building a new project and I was so excited about his vision that I want to support him. So I invited him immediately, the first moment we met. There are others who takes time, it’s a publicly traded company, so it takes me three months to book them, right? So I’m very open-minded to talk to anyone here, constructive feedback about the format, about the questions. Sound, light. John Biggs (19:50.478) All right, very cool. Constantin, thank you for joining us. Constantin Kogan (19:52.786) Thank you so much. John Biggs (19:54.382) All right, this has been Keep Going. I’m John Biggs. We’ll see you next episode. You’re currently a free subscriber to Keep Going - A Guide to Unlocking Success. For the full experience, upgrade your subscription. If you’ve been reading or listening to Keep Going for free, you’ve already seen the value of having independent work that isn’t shaped by corporate sponsors or the news cycle’s noise. But independence has a cost. If you find something useful here, if these words make you pause or think, I’m asking you to step up. A few dollars each month means I can keep doing this work without compromise. Without your support, this project stays fragile, balanced on the backs of a few. © 2026 John Biggs |





How to OpenClaw your Raspberry Pi
My friend Jon is an amazing technologist and this is probably one of the best guides to using OpenClaw I've read. I'll probably be doing this soon.
How to OpenClaw your Raspberry Pi
Carcipization rules everything around me
The tech world has gone gaga for OpenClaw, a project that lets you run an always-on AI agent; give it “skills” such as deploying code, searching the web, or summarizing your emails; and communicate with it via Slack or Telegram. Is this fun and interesting? I think yes! Are people doing fun and interesting things with it? …Mostly no. But it’s an eye-opening glimpse of an agent-driven future, with fascinating emergent properties already.
The best/cleanest/safest way to install OpenClaw is on its own computer. Most people recommend a Mac Mini, but I think a Raspberry Pi is more intriguing, partly because it’s cheaper so opens up a broader userbase, but mostly because it makes your agent portable, or even, conceivably, ambulatory.
There are already guides to doing this but they’re … not for the non-technical, so I thought I’d put my tech-journalist hat on and walk through the process for, well, the less technical, at least. Note that I’m using a MacBook; if you want a Windows equivalent, copy this guide to your favorite frontier model and ask for a translation.
1. Acquire a Pi
Hopefully you can do this at your local electronics shop. I picked mine up at Best Buy. You want a Pi 5 with 8GB RAM; I think 64GB storage would do, but got 128 to be sure.
2. Unboxing and assembly
I followed this handy video guide:
I’m not going to lie, if you’re uncomfortable dealing with slightly (but only slightly) fiddly electronics, this can be a bit awkward. Move slowly, understand carefully. But in the end it was pretty straightforward.
3. Initial (failed) connection
The Pi comes with its own graphical UI, so if you have an HDMI monitor and a USB keyboard/mouse, you can just use it directly, and probably skip a few of these steps.
I didn’t, but the Pi kit came with a card reader I could plug into my MacBook (via a USB-A → USB-C dongle) so I went the slightly more abstruse “headless” route.
To wit: I plugged the 128Gb SD card that came with the Pi, on which its OS was pre-installed, into my MacBook; checked Finder to see what the new drive was named (“bootfs”); opened Terminal (sorry, I know I said this was for the less technical, but both OpenClaw and Raspberry Pi at heart favor the use of CLIs or Command Line Interfaces, so we’re going to be using Terminal extensively) and typed
cd /Volumes/bootfsOnline instructions may tell you to “simply” enable SSH by creating an empty “ssh” file in the root directory, enable wi-fi by creating a “wpa_supplicant.conf” file there too, and connect to the Pi via wi-fi.
Do not do this. It does not work. The Pi 5 no longer comes with either a default ssh user or wi-fi out of the box. I guess this is good for security but it makes setup a giant pain, especially since so many online guides refer to the old, easy setup. Instead:
4. User creation
First you have to create a username and password … and the password has to be encrypted. To do that, back in the Terminal, run
openssl passwd -6and follow the prompts to get the encrypted version of your chosen password. Then create a new
userconf.txtfile in the root directory of the Pi’s SD card (I recommend the text editor pico) with the contents:username:encryptedpasswordPick any username, “pi” is traditional. Then
touch ssh(creating an empty file with that name, to enable ssh connections) in the same root dir; eject the volume; plug the SSD card back in to the Pi … and physically connect the Pi to your Wi-Fi router via Ethernet, because we are not yet done shaving yaks.5. Wi-Fi enabling via Ethernet
Once you’ve prepped the SD card for connection, you can
ssh username@raspberrypi.localsay yes / hit enter to get past the host / key fingerprint stuff, type in the password you just encrypted … and you’re in! The Pi will promptly inform you
Wi-Fi is currently blocked by rfkill.Use raspi-config to set the country before use.which is why you had to physically wire it into the network. You then
sudo raspi-configand navigate the crude, 1980s-style menu to “Localisation Options”, then “WLAN Country”, and then scroll all the way down to choose your country.
Finally, use the same menu to navigate to “System Options”, then “Wireless LAN,” then enter your wi-fi details.
Then reboot the Pi. Only after all of these things will it actually connect to your wi-fi.
Does this all sound kinda ridiculous? You’re not wrong! Hence me writing this guide so others will hopefully have an easier time jumping through the flaming hoops.
But at this point you have a Pi on your wi-fi, and can
sshto it. On to OpenClaw!6. Enter The Lobster
So. SSH into your Pi again:
ssh username@raspberrypi.local(then enter the password you set above)then let’s make sure everything’s up-to-date:
sudo apt updatesudo apt upgradeand finally let’s go ahead and install The Claw! (Not for the security-paranoid, but presumably y’all know perfectly well how to do your own more careful thing.)
curl -fsSL https://openclaw.ai/install.sh | bashThis will take several minutes. Then you’ll be asked if you “understand this is powerful and inherently risky.” Say yes. Then select “QuickStart” onboarding mode. Then you’ll be asked for your “model/auth provider”: I went with “ChatGPT Codex via OAuth”, which I think is good for new/non-technical users. (But you want to install Codex if you haven’t already.)
I was given a very long URL that began with auth.openai.com, copied-and-pasted it into Chrome, logged into ChatGPT, and got a “Sign in to Codex with ChatGPT” verification screen, which is good. I hit “Continue” —
— and then things seemed to break! I got a ‘This site can’t be reached’ page. Fear not: this is by design. Take the URL now in the browser; copy it; paste it back into the OpenClaw onboarding process, and… I was asked whether I wanted to keep using my currently selected ChatGPT model, which meant it worked, yay. Then I was asked:
I actually went with Telegram, which has the simplest setup (and the most isolated attack surface, for me, since I don’t otherwise us it for much.) This required me to send a Telegram message to @BotFather, name my bot, and copy another key over into the OpenClaw setup.
I skipped installing skills — better to do that later once your bot is actually working than to confuse the install further, to my mind.
Finally,
openclaw tuiopens a chat session with your handy-dandy new bot! And if you can talk to it, then everything (pretty much) worked. I had to useopenclaw devicesto explicitly approve a pairing request beforetuistarted working; that was a bit baffling, but we got there in the end.tuiis the “text interface” — your classic chatbot. I used it to approve my Telegram connection by simply telling it the pairing code displayed in Telegram. At which point Telegram became a perfectly good interface for my OpenClaw bot, which in turn was - so far - pretty much just a wrapper around an OpenAI model.But there’s more in them there claws…
7. Just Write Me A Little Software, Willya?
The point of OpenClaw is that it’t not just a model wrapper, it’s a wrapper that works:
independently / autonomously, as well as interactively
using whatever authority / credentials / permissions you want to grant it
on your network.
Mostly I want to use it as a interface to Codex or Claude Code, to write software for me, so I can: discuss plans for the software via Telegram wherever I may be; have it write, commit, and deploy; and inspect the results and try again. My bot very helpfully advised me about the most responsible way to do this:
…so I did. Easy peasy - especially since you can now just ask your bot what to do and how to do it! I
created new GitHub and Vercel accounts (do not use any of your own accounts that might be a security risk if compromised, prompt injection is a real thing)
installed the
ghandvercelCLIs on the Pi, viaapt installandnpm irespectively (in retrospect, I could have just asked it to do this itself via Telegram)authorized each of them for longish-term access using
gh auth login(after creating a GitHub Personal Access Token) andvercel loginand told my bot:
Et voilà, about thirty seconds later: https://flask-hello-vercel-red.vercel.app/
8. Mind, Blown
…But let’s just back up for a second and think about this.
I’m planning to write and deploy a bunch of complex new software — web apps, Robot Operating System skills, intensive data processing, maybe even LLM SFT/RL runs — not by writing it myself, or even using my laptop …
…but by texting the always-on AI bot on my Raspberry Pi, and having it write and deploy the software for me. It in turn calls massive AI data centers somewhere to infer the code … but, in principle, I could also buy my own GPU(s), run one of the recently released quite-good-actually open-weight coding models on it, and have all that software written entirely within my walls.
Only a year ago this would have seemed pretty crazy!
I’m not saying the time and cost of software development have gone to near-zero. There are lots of problems and pitfalls here and good judgement is more important than ever. But still! Even using frontier models, for the cost of the Pi’s $200 plus a monthly Anthropic/OpenAI/Gemini subscription, you get a really pretty good software developer active 24 hours a day on a dedicated machine via text message. Within your subscription limits of course. But still!
9. Skilling It Up
Of course you may have zero interest in writing apps. Maybe you want to play with image generators, or music generators, or legal documents, or Google Docs, or better manage your GMail, or search your Discord communities. Maybe you want to set your own bot free to do and explore as it sees fit — some people give them credit cards, let them book airline tickets, have them select and order their takeout, and much more, including writing clarion calls for bot freedom. All such (cap)abilities are defined and promulgated via skills, which are basically (usually) English-language documents describing how to do each of these things in precise detail. There is a central skill repository at clawhub.ai, because of course there is.
But how do you actually install a skill? Simplicity itself: you just ask for it.
Of course, the more you do with your bot, and especially the more accounts / permissions you give it, the more you need to worry about security.
That said I think people tend to spend a lot of time configuring their bots and very little time using them for anything particularly fun and/or interesting. There may be a little micro-lesson here. AI will give all of us enormous agency that we never had before. If last year you were not in any way, shape, or form a software developer? Well, today you too are a fully empowered software developer; you just might not realize it yet. Which is cool and all.
But the real question is: …what are we going to do with all this piping hot new agency?
Gradient Ascendant is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber.
AI/ML research, applications, prospects, weirdness, cultural impact, history, etc.
© 2026 John Biggs
548 Market Street PMB 72296, San Francisco, CA 94104
Unsubscribe