@kandros5591 @ValDotTown yes yes a million times yes! hit me up if you need help with anything. this is our core value prop!
Notes
- I'm about to do the funniest thing tomorrow (after all my recent MCP hate)
- @JiquanNgiam more context https://x.com/stevekrouse/status/1986922520298287496?s=20
- @RhysSullivan @hiiamArielle is my branding guru, maybe she knows someone
- @EthanWoo Excited to see a demo!
- @erikphoel https://www.theintrinsicperspective.com/p/john-von-neumann-shot-lightning-from
- holy crap @erikphoel did another Nature v Nurture banger another big L for Nature, big win for Nurture John von Neumann has been a favorite icon of the Nature crowd – turns out he's a prime example of Nurture. Suck it rubes! https://x.com/stevekrouse/status/1988690001312510274/photo/1
- MCP is mostly nonsense, but there are good effects: 1. Tricks management to green-light engineering efforts on APIs and OAuth DCR (Dynamic Client Registration) 2. Tricks LLM clients to integrate with everyone, ie an open-ecosystem, not walled gardens 3. (Just discovered this one today) The fact that MCP is a difference surface from your normal API allows you to ship MUCH faster to MCP. This has been unlocked by inference at runtime Normal APIs are promises to developers, because developer commit code that relies on those APIs, and then walk away. If you break the API, you break the promise, and you break that code. This means a developer gets woken up at 2am to fix the code But MCP servers are called my LLMs which dynamically read the spec every time, which allow us to constantly change the MCP server. It doesn't matter! We haven't made any promises. The LLM can figure it out afresh every time This is why we've shipped capabilities to our MCP server that our API doesn't yet have. We aren't worried about committing ourselves to anything. We can always change the MCP server later and the LLM will figure it out
- People often ask me how to get good at Twitter I start by pointing them back to this old essay by my friend @danshipper, "Selling Umbrellas in a Synagogue" The css on his old site seems broken, so I'll repost the relevant part of it here: The way people interact with Twitter is fundamentally different from the way people interact with Google. And so measuring things like CTR and conversion rate on Twitter is completely missing the point. Let me give you an example. If you’re ever in New York and it begins to rain, a stunning and incredible ritual occurs. As soon as the clouds begin to form, a bunch of guys suddenly materialize toting umbrellas. They walk around the whole time it’s raining selling them for 5 bucks a pop. I’ve been in at least a few rainstorms and have thought to myself “hey, what the hell?” and just bought one. After the rain goes away, the vendors just disappear into thin air. The guys selling the umbrellas are filling an expressed need. When it’s raining out and people are walking around and getting wet, they need umbrellas. The vendors conveniently swoop in because they see that need and fill it. The same thing happens on Google: people are already searching for things that they want. They’re like people getting wet in a rainstorm. They’ve expressed need, and they have the oft-quoted “purchase intent”. So putting an ad next to search results makes perfect sense. The ad is just like the guy hawking umbrellas. But Twitter is not like Google. And selling things on Twitter is not like selling things on Google. Twitter is not like a rainy Manhattan avenue. Twitter is like a synagogue. Every Saturday at a synagogue a bunch of people get together. The relationship is social, and it’s communal. They go to synagogue for the services and then the schmoozing afterward. Twitter is similar. Their tagline is, “Find out what’s happening, right now, with the people and organizations you care about.” Twitter is social. Twitter is communal. And so, selling things on Twitter is like taking our Manhattan umbrella vendor, and having him go try to sell umbrellas in synagogue. Imagine the scene. A bunch of hungry people are eating bagels and lox after services and chatting amongst themselves. Suddenly some guy comes up toting a bunch of umbrellas. “Hey I know you’re busy talking with your friends but can I interest you in an umbrella? It only costs $5. It’s a great deal!” I shiver even thinking of having to do something like that. It’s grotesque. And most importantly, it’s very unlikely to work. What’s interesting to note is that the people that the vendor is talking to are the same people that minutes earlier may have bought an umbrella from him on the street on their way to temple. But now that the context is shifted, it completely changes the way the sales pitch is perceived. In advertising, context is everything. And an umbrella vendor in a synagogue misses that entirely. As Gary Vaynerchuk might say, he’s like a teenage boy with his first girlfriend. He’s trying to close too fast! So how you sell umbrellas in a synagogue? Well, let’s say you’re Moses Goldstein of Goldstein Umbrellas. You go to services every Saturday. And then you go eat with the community. You share advice, and expertise. You trade stories with people in other industries. It may seem like you’re just idly wasting your time. If you go and measure the ROI of what you’re doing it will stand at zero. It looks like it’s a very bad idea for you to pay your yearly dues at the synagogue. But what you’re really doing is a primitive non-scalable version of content marketing. With every person you talk to, and every story you swap you’re establishing yourself as a trustworthy, reliable and well-liked authority on umbrellas. Still, you won’t see any ROI. Then one day a member of congregation comes up to you and says, “Hey Moses, my company is looking for an umbrella vendor. Of course the first person I thought of is you!” And you suddenly have a new customer. What this says to me is that there are a lot of companies that are going to get on to Twitter’s advertising platform, throw a few thousands dollars at it, see a low conversion rate and conclude “This sucks!” These are the guys that are selling umbrellas in a synagogue. But as people understand the social web more they’ll begin to realize that on social sites the advertising context is shifted in much the same as the context is shifted between the street and the synagogue. In the street, the relationship is all about immediate need. You have a need, I’m the most convenient way to fill it. By contrast, in a synagogue, the relationship is all about connection. It’s about developing and cultivating bonds between people in a genuine fashion. And then once those bonds have been formed, they’ll be utilized when need arises i.e. when someone is looking for an umbrella vendor. The arc on the relationship is many times longer than the arc on the relationship with a street vendor. The upshot of it is that Twitter allows you to build those relationships in a scalable way. So am I going to continue using Promoted Tweets? Nah, but I do have a startup called Firefly. If you’re interested in doing better customer support I’d love to talk to you about it some time.
- @danshipper @CoraComputer Unreal!!! Congrats!
- It's been three years of Val Town. My co-founder @tmcw wrote a tell-all retrospective on the journey so far! Enjoy 🍿 https://macwright.com/2025/11/11/val-town
- @bentossell i would like to invite you to learn to write lines of code, and i would like my invitation to feel like i'm inviting you to learn how to play pickleball or padel or basketball it'll be super fun! you'll sweat! you'll see the world in new ways! you'll gain muscles! refusing to…
Text may be partial · Read original
- where do you want my eyeballs? pick ONE! https://x.com/stevekrouse/status/1988292041366032504/photo/1
- @jitl I love coq
- @bentossell do you know how to code?
- @manosaie @bentossell https://x.com/stevekrouse/status/1988253650808913937?t=AcVQiTMWVMd6PC_pg1F_FQ&s=19
- I love pipe https://x.com/stevekrouse/status/1988257237442171071/photo/1
- It's easy to conflate curiosity with the desire to be entertained Curiosity can help you learn STUFF, ie watching the history channel all day, but that's a far cry from being able to DO and CREATE The ability to do and create come from getting off the couch https://x.com/bentossell/status/1988249020645409166
- *the next installment in steve's spicy morning takes* AI is terrible for education This came as a shock to me. I've long-anticipated AI solving all problems of education in one fell swoop. We in education circles talk about Bloom's Two Sigma Problem, which says that if we can scale 1:1 human tutoring to every student, then every student gets As. Now we have ChatGPT – a personal tutor for every student! Education is solved!!! This is why the world is so sane right now, and everyone you meet is so freaking smart. Everyone has become a super-genius by talking to their personal AI tutors. I wish. Instead it seems like, if anything, we've all gotten dumber. How is this possible? How can this not make us smarter? If you look at recent history, we've gone from a society of illiteracy to full literacy to public libraries to the internet, wikipedia, youtube, google scholar, audible, khan academy... The tools to become smarter abound and yet smartness does not. What is going wrong? Why don't more educational tools help? Being excited about AI's impact on education in 2025 is much like being excited about MOOCs impact on education in 2012. Less than 1% of people will use these to actually become smarter. With MOOCs, people just ignored them, but in the case of AI it's actually worse than neutral. We all know that in order to learn a physical skill you have to get up and do that skill physically. You can't learn surfing without getting wet. You can't learn pottery without putting your hands in the clay. You learn tennis on the court. Cognitive skills are no different. You learn them through active mental exertion. You learn them by actually trying things - venturing - making mistakes, and learning from those mistakes. We call this 'fuck around find out' method "play" and it central to learning any new skill. You absolutely cannot learn any skill by ingesting material on it passively. YOU ABSOLUTELY CANNOT LEARN ANY SKILL BY INGESTING MATERIAL ON IT PASSIVELY. You can learn history that way. You can be entertained by stories that way. But you cannot learn HOW TO DO SOMETHING that way. We all know this for physical skills - imagine someone learning to dance by sitting on the couch watching people dance - but we seem to forget it for mental ones. They are no different. So why does AI make this story worse? Because it gives you the illusion of learning while at the same time isolating you from its source. Vibe coding is the prime example of this. Vibe coding is the equivalent of playing Guitar Hero, thinking that you're learning to play the guitar. In order to learn to code, you have to learn some incredibly difficult mental skills. Just imagine learning the basic skills of a sport. I'm picturing basketball. The motions are weird and counter-intuitive and you've gotta practice them a lot before they are second nature. Learning to code is just the same. Ok so now enter vibe coding. This would be the equivalent of playing a basketball video game. Sure, it looks like you're playing basketball, but you're on your couch, miles from a hoop, a controller in your hand, when you need a ball in it. Ok now to address some counter-arguments. 1. "But I use AI and it makes me smarter!" Sure whatever, you're also the sort of person who reads books and gets smarter too. You're what we like to call "resourceful", and AI is just another resource to you. I'm talking about the people who resist resources. If you wanted to learn to code, there were are a million resources to teach you before AI, but you didn't learn then. Will AI help you learn now? I don't think so. You have to do uncomfortable things with your brain to learn. AI helps you avoid those things, which means you avoid the learning. If you want to learn to code you have to get off the mental couch and get on the mental basketball court. If you're looking for the basketball court for learning to code, you can find one at the corner of val street and town way 2. "Now that AI exists I don't have to learn to code. I just have to wait for the AI to get smart enough." Yeah, that's what my brother thought about about learning to drive. Now he's 26 without a license and has to take ubers everywhere. The progress in AI intelligence is literally the hardest thing in the world to predict, and people have been getting it wrong for 100 years. You may be in for a long wait. And more importantly, why do you want to avoid mental gymnastics? You are the humans in WALL-E who don't move their bodies. But you go to the gym, right? Just the same way you push your physical body, you should push your brain! Stop working so much on your biceps and start working on your cerebral cortex. Smart is the new sexy, haven't you heard? 3. "But wait, didn't you say that Bloom's Two Sigma Problem showed that 1:1 tutoring made humans smarter? Why can't AI replicate that?" Finally, a good question! Took you long enough. Yes, this is where hope lies. The dream is no less than what @erikphoel calls 'Aristocratic Tutoring' for all. Hoel's argument is that all the geniuses of the past had incredible personal tutors. From Alexander the Great to Einstein. But we lost that when we went to mass schooling. But we can get it back with AI! But clearly that hasn't happened yet. Why not? Imagine a young Ada Lovelace, living on the estate of her dad Lord Byron, surrounded by the intellectuals of her day, tutored by Mary Somerville, the women for who the word "scientist" was coined to be a gender-neutral alternative to "man of science". Imagine young Ada being called to her daily intellectual lessons, walking through idyllic pastures, and getting to test her wits, new theories, and writings amongst her tutor and parents' friends, the intellectuals of the day Now contrast this with a modern school child surrounded by entertainments, one of which is ChatGPT, which of course they use just to write their essays for them ("vibe writing", if you will), so they can go back to watching TikTok In his new book Sal Khan talks about designing his AI to be Socratic, and like a human tutor, spend most of its time trying to uncover what the student doesn't know, so it can best address that, without simply giving away answers. It's not impossible, but that it's incredibly hard, and ChatGPT slapping a stupid system prompt on, and launching "Study Mode" is disrespectful to the scope of the problem. The job of the human tutor is the same as that of a human coach of a sport. To get the kid on the court, practicing. This is why AI is currently so bad for education. It isn't trained to get kids to practice mental skills. It's trained to display mental skills. Let's also not forget that the most important job of a human tutor/coach is the social/emotional scaffolding to actually get you to do the hard practice day in and day out. AI is woefully set up to be able to help with that. If you are reading this essay – and I'm pretty sure you are – and you're non-technical, I hope this was a wake up call for you to get off your butt and start working your brain out. Here's a secret about me: I am an absolute sucker for a good student. If you want to learn to code and you put in the work, I can not resist teaching/mentoring you. Literally nobody takes me up on this offer. Maybe you will.
- @BaronVonLeskis Cool!
- @peytoncasper You mean calling the top? If it's the bottom, you shouldn't close your position now! 😅
- How do people learn new skills? When was the last time you learned a new skill? You might want to pause for a minute and answer that for yourself I asked this question to my fiance and she talked about tinkering around the software the last time she started a new job "How did you learn to tinker?" I asked "When I was learning to ride a bike, my dad loosened the training wheels. It gave me enough help to not hurt myself, but enough freedom to make mistakes and learn from them. It's so much better than having a parent there holding the bike for you, breathing down your neck. Trying to instruct you on every mistake." "That's so cool!" I said, "Like a makeshift balance bike! Alan Kay talks about how those are so much better than tricycles for that exact reason of letting you make mistakes safely. So cool your dad knew how to make that." Then I had a follow up question: "So how does this balance bike relate to tinkering at the software at a new job?" "Whenever I have to learn something new," she said, "I get someone to explain it, and then go away so I can tinker and figure it out myself, like on the bike. Learn from my own mistakes. Figure out my own shortcuts that make sense to me without someone breathing down my neck." I was surprised! My own story of how I learned to teach myself new skills is very similar! I'm beginning to suspect it's similar for everyone who can teach themselves stuff: 1. A sandbox/playground where you can try stuff on your own, make mistakes, and learn safely 2. An formative memory of the above so you can model future learning experiences onto it I have a suspicious feeling that everyone who teaches themselves stuff finds a way to fit the new thing they want to learn into a learning method that's worked for them before. And this sandbox/playground method is one of the best. For me, I was lucky that my playground was Logo, the children's programming language that preceded Scratch. It was created by Seymour Papert for the express purpose of being a safe and fun sandbox to mess about with mathematical ideas, and more importantly, learn the importance of a sandbox when learning. (He expresses both goals explicitly in Mindstorms, which everyone who cares about education should read. Go read it!) So from then on, whenever I needed to learn a new skill, I knew that job #1 was getting myself into a sandbox as fast as possible. Humans learn through trial and error, a process which in children we call "play" Here you can see the roots of Val Town and why browser-based programming is so important to me: get the programmer into the sandbox as fast as possible. (There's also a fun irony that the word sandbox here has a double meaning: a children's safe play area and a secure isolated compute environment) I'd invite you dear reader to think back to the sandboxes of your past. Do you try to recreate them whenever you learn a new skill? Tell us in the replies!
- @simonw @ollieglass @AnandChowdhary Oh! I forgot that was part of it!
- @simonw @ollieglass @AnandChowdhary I had it create a rubric for itself (based on your start of a rubric) and then draw an image, and it's pretty solid! https://x.com/stevekrouse/status/1987693554605432999/photo/1
- @Paul_Kinlan ha nice!!! i just bought http://repro.fyi and (for now) did the same redirect i want to make something better than http://sscce.org though when i have time
- @joelcompiles Try remixing my val and playing with it! I agree, it's hard to bootstrap up a simple example like this. I think some new abstraction is on the cusp of being invented
- @JacobColling Noooooooo 😝
- Is there a good infosite about how to make a good repro? This seems decent, but I'm never going to remember http://sscce.org. Needs a better domain https://x.com/stevekrouse/status/1987545316762005902/photo/1
- https://www.val.town/x/stevekrouse/capn-web-demo
- When Kenton Varda personally tells you to read his blog post, it's time to read it (again) I finally get RPC!! It's so cool! Getting the code running in a live demo really helped Hopefully this video demystifies it for others https://x.com/KentonVarda/status/1987208923003170840 https://x.com/stevekrouse/status/1987519775363285252/video/1
- @KentonVarda Going to read this blog post for the third time. Hopefully this time I grok it 🤞
- You guys have to stop calling my content bangers. I'm becoming insufferable to my fiance https://x.com/stevekrouse/status/1987485670525280351/photo/1
- Joint-stock companies were a mistake. We should really go back to one company one owner. Good luck making a billion dollars that way Jeff
- @kssreeram If there's no reason for human's to express their taste, then yes you're correct
- @gonzalo__nunez 🥹 thank you!
- Holy crap Kenton Varda replied to my rant with a tweet thread. Best day ever https://x.com/KentonVarda/status/1987208904724652273
- @KentonVarda Holy crap, I'm starstruck Thank you so much for replying so thoughtfully! Especially given my snark
- @kssreeram I anticipated this question almost word for word and addressed it! https://x.com/stevekrouse/status/1987236866265907247/photo/1
- AI coding today is bottlenecked by LLM speed, intelligence, and cost – all seeing regular 10x improvements Which begs the question: Where is this all going? What is a positive vision for the future of coding with AI? In a positive AI coding experience: 1. I understand more about the problem space & my code – not less 2. I am able to express my taste more & make more choices in implementation – not less 3. I am in a flow state, immersed in the creation – not waiting or constantly switching contexts On the AI improvement side, let's make a couple 1000x assumptions that seem a decade or two out: a. throughput = 1m tokens / sec b. intelligence = smartest human level c. cost = 1 cent / 1b tokens A corollary of this is that as the cost drops, we'll use more and more inference in parallel. So for the sake of imagination, picture: i. 100 of the smartest people you know ii. reading and typing 1000x faster than you iii. hooked up to vm sandboxes (so they can run experimental code safely) It's immediately obvious that the bottleneck is getting information to and from the human to this army of AIs. It's an I/O problem! Point (1) above is about me wanting to get data from the AIs and point (2) is about me wanting to get data into AIs. Which begs the next question: is the I/O input-bound or output-bound? Are we trying to get more data from the AIs or into the AIs? I believe output is the bottleneck: How fast we can get data from the AIs into the human brain. The bottleneck is how fast a human can understand and learn. This is very profound and counter-intuitive, so let me say it again HUMAN LEARNING IS THE BOTTLENECK Why? Because we want to maximize the expression of human taste, but human taste is limited by what the human knows. It must be the job of the AIs to inform the human such that he can make good choices. (This rhymes with HARC's vision of ensuring "human wisdom exceeds human power") Let me evoke this with an approximate conversation I had with a non-technical person: Friend: "I want to build a social network" Me: "Ok... why?" Friend: "Because when I started college it was really hard to meet people, find clubs, find a good roommate." Me: "Are you telling me you want to start a social network for college kids?" Friend: "Yeah, why?" Me: "No reason. Ok so what about facebook didn't work for you?" Friend: *lists random problems with facebook* Me: "Ok sure. What are your plans for adoption? How will you get folks onto your network?" Friend: "Campus ambassadors, marketing stunts, a better product." Me: "Hmmm, sounds really hard. Have you read The Lean Startup, any Paul Graham, or any Nikita Bier on how to start and grow a social app?" Friend: "Nope" Me: "Ok, I'd start there" Friend: "Nope, I just want you to find me a code monkey to build it" Me: "Nobody will build this for you. You should learn to code so you can build this yourself." Friend: "No, I'm the ideas guy. I'm a coder" *friend drops out of college, raise a couple million, gives it to code monkeys to the expected result* I think you get the point. The bottleneck here is not helping this person make a social network for college students. The bottleneck is them learning more about startups, technology, etc, being education enough even to have good goals. Let me give a thought experiment. What if I told you that everybody that worked at Google was actually an AI? The only human in the whole company is Sundar. Now Sundar is going to retire and he is tapping you to be the new CEO and only human at Google. Congrats on your new job! Now as the new CEO, are you going to be like my over-confident friend and start telling your AI army to start making random apps that you think are good ideas? No! You're smarter than that. You know that your ability to be a good CEO of Google is bounded by your ability to UNDERSTAND as much as possible about how Google works. Then and only then, when you have a clear-eyed view of things, can you even begin to have a hope of expressing your human taste in a way that will have a positive impact The problem of AI coding reduces to the problem of teaching humans as fast as possible This insight is completely against the grain of vibe coding. Most of the fervor around AI coding seems centered around non-technical people celebrating that they never have to learn anything new in order to do technical things. It's all about skimming on the surface with the least understanding possible to get the most done. But why, you might ask, do humans need to understand stuff if the AI is super smart? For the same reason that we want the CEO google to be as smart as possible! The details matter. If a human can't express their judgement in an informed way, then they're better off not expressing their judgement at all. Let me give you concrete examples that I've seen over and over again with non-technical vibe coders I've encountered: They do not understand the basics of HTTP, and client, server, database architecture They do not understand the basics of debugging and the importance of a reproducible example People who don't understand these things (yet), shouldn't be making decisions about apps. They should be learning those things, so that they are the kinds of people who can make apps. I'm not trying to be elitist. I'm saying there are levels to things. I have no business flying a plane or building a plane or anywhere near the hood of a car. Yes, I can spend money and get someone (pretend they're an AI if it helps) to do those things for me (call that "vibe flying" or "vibe fixing a car") but I am not doing those things. If you don't understand what you're doing, you're not doing it. You're commissioning it. Vibe coders are commissioners, like my non-technical friend, who wasted millions on getting code monkeys to build his dumb social network. The limiting factor is not what they can get built, but their ability to know what to build. This is why the world is filled with garbage AI apps with zero users, not lots of new vibe coded app businesses. If I haven't convinced you, you may as well stop reading. If I have convinced you, great. Let's talk about: How does one get data into the human brain as fast as possible? Obviously, we could talk about brain-machine-interfaces, neuralink, yada yada, but for the purposes of this rant, let's stick to the five senses we know and love. What can I say? I'm just old-school that way. So what's the most educational 5 minutes or one hour you could imagine? Think back to a time you learned something very quickly. What were you doing? I learn a ton by reading. The Lean Startup, PG essays, etc, taught me a ton about how how to know what to build. The sad truth (for an educator) is that the pathways to greater understanding have been open to all ever since public libraries. Google, Wikipedia, and now AI, only make this story better. Yet people resist learning. I think only 10% of the people I recommend the Lean Startup or The Mom Test to read them. This is going to be one of the key problems to solve if we truly want to empower people with AI: somehow convince them to learn. Somehow make learning fun. Most of what I know about actually building comes from getting my hands dirty in the details and actually building. Ironically, current AI coding tools isolates its users from this process, which is entirely counter-productive given the goal is deeper understanding Let's examine one example topic in particular. I've spent a lot of time teaching people about client, server architecture, APIs, and servers. You can't just read about these concepts, you have to play with them. You can't learn surfing without getting in the water. You have to make some API calls. You have to write some server responses. You have to do some debugging. It takes hours and hours for these concepts to sink it. And there's no way to skip this part. The human ability to learn surfing has been entirely unaffected by the rise in AI, and the same is true for learning how to about client/server architecture. Not to pitch my company, but this is the problem Val Town is trying to solve: we get folks into a running programming environment so they can immediately start playing with running code. Come on in, the water's fine: http://val.town How can AI help? Maybe it can find a way to make learning more fun or engaging? Maybe it can paper over the unnecessary annoying parts? Maybe it can help design amazing curriculum? Maybe it can be the world's best Socratic teacher? I don't know the answers, but I think those are the right questions.
- *gets up on soap box* With the announcement of this new "code mode" from Anthropic and Cloudflare, I've gotta rant about LLMs, MCP, and tool-calling for a second Let's all remember where this started LLMs were bad at writing JSON So OpenAI asked us to write good JSON schemas & OpenAPI specs But LLMs sucked at tool calling, so it didn't matter. OpenAPI specs were too long, so everyone wrote custom subsets Then LLMs got good at tool calling (yay!) but everyone had to integrate differently with every LLM Then MCP comes along and promises a write-once-integrate everywhere story. It's OpenAPI all over again. MCP is just a OpenAPI with slightly different formatting, and no real justification for doing the same work we did to make OpenAPI specs and but different MCP itself goes through a lot of iteration. Every company ships MCP servers. Hype is through the roof. Yet use of MCP use is super niche But now we hear MCP has problems. It uses way too many tokens. It's not composable. So now Cloudflare and Anthropic tell us it's better to use "code mode", where we have the model write code directly Now this next part sounds like a joke, but it's not. They generate a TypeScript SDK based on the MCP server, and then ask the LLM to write code using that SDK Are you kidding me? After all this, we want the LLM to use the SAME EXACT INTERFACE that human programmers use? I already had a good SDK at the beginning of all this, automatically generated from my OpenAPI spec (shout-out @StainlessAPI) Why did we do all this tool calling nonsense? Can LLMs effectively write JSON and use SDKs now? The central thesis of my rant is that OpenAI and Anthropic are platforms and they run "app stores" but they don't take this responsibility and opportunity seriously. And it's been this way for years. The quality bar is so much lower than the rest of the stuff they ship. They need to invest like Apple does in Swift and XCode. They think they're an API company like Stripe, but their a platform company like an OS. I, as a developer, don't want to build a custom chatgpt clone for my domain. I want to ship chatgpt and claude apps so folks can access my service from the AI they already use Thanks for coming to my TED talk







