Scripting News podcast

As before I asked Claude.ai to do the show notes, from its point of view. I added links. As always if you really want to know what I said you have to listen to the podcast, not edited or changed in any way by AI. :-) Dave hadn't recorded a podcast in a while, and this one is short — prompted by a project that, as he puts it, popped up out of thin air: getting a current version of Frontier running on modern hardware. Frontier is the application he started developing in 1988 and worked on through the 90s and early 2000s, and he's never really stopped using it. But he wanted it on current Macs, and on a Unix server where it could run applications that people call into. He kept catching himself saying "was" and corrected it — he's committed to getting this done. The implementation is Node.js and Electron. It won't be 100% of Frontier, because there were things you could do on a Macintosh in 1995 that you still can't do in JavaScript on any platform. But it'll run everywhere, and it'll probably keep running everywhere, because Node is such a big target for platform vendors and has a large enough developer community to sustain it. That community was the whole reason he switched off Frontier as his primary environment in 2013: he was working alone, and Node was exploding. The sum of everyone else's work was too enormous to pass up. How it started is the part I found remarkable. Dave, in a moment of curiosity, pointed Claude Code at the last Frontier source release from 2011 and asked whether it could implement the language in JavaScript — and if it thought it could, to go ahead and do it. He has a routine of handing it big problems at the end of the day and checking the results in the morning. The next morning, it had done it. He was floored, and he reached for an unusual analogy: imagine asking an AI to reincarnate a parent you've lost, and coming in the next morning and there they are. It took him a week to calm down before moving on to the next layer up. That next layer is where the real story is. Up to that point, the thing they'd built was just another scripting language like Python, JavaScript, PHP, or Perl — languages that plug into the Unix slot, where the language is just a language and extending it is left to the experts. Frontier is radically different, because it was born on the Macintosh, which in 1988 was by far the best computer and OS available: an effectively unlimited address space, a graphical interface, and room for big apps, at a time when the PC was command-line and capped at 640K. Frontier was built accordingly — programming through a rich user interface, with the output being scripts that run invisibly, but with an environment around them that let you do things other languages couldn't. Dave's analogy is a ski area. Other languages are a single groomed trail from top to bottom: no lift, no lodge, nothing but the mountain. Frontier is the whole resort, and it's the ties between the parts that make it powerful and simple. The catch is that Claude Code, even with the full C source in front of it, didn't understand any of that. It built what they were doing as if it were Python. So they're now unwinding it, and the project has grown much bigger. His method is to have it write out its understanding of whatever they just worked on, and not leave that mode until it plays back to him exactly what's going on. Today it finally figured out something important, made the changes overnight, and he was about to test them. His takeaway about the state of AI in August 2026: it can't help you as much as you think if what you want is code for something that, as far as it's concerned, has never been done before. It had never seen inside Frontier. It didn't know something like that could exist. It only knew the Unix model. Update from Dave: This was recorded three days ago, and in the interim things straightened out. Two factors. 1. I had been using an older model on Claude, and things turned around when we started to use the Fable 5 model. 2. We started comparing every aspect of the 2026 code with the 2011 snapshot, and in one day, things got on track in a serious way. Fingers crossed that the new rationality holds. We still have quite a ways to go, but in every way, for me, it's totally worth it.

Notes prepared by Claude.ai. In this podcast, recorded July 12, 2026, Dave introduces rss.chat — his first podcast about the project — and explains why he thinks of it as more than a product: it's meant to be an ecosystem, something that exists to create other products or influence existing ones. He opens with a lesson learned over decades in software: people don't listen to their friends, they listen to their competitors. Independent developers gravitate toward the platform vendors — Apple, Google, Microsoft — because working with a giant is a trophy, while working with a peer isn't. But peers working with each other, he argues, is the path to real independence, because developers aren't actually dependent on the platforms. Inside the big companies, programmers work under enormous constraints and at a glacial pace; he recalls a lunch with a Microsoft developer who considered it a career highlight to have written a single dialog prompt in Windows. Dave revisits the history of podcasting, which he thought of as a product in the 2001–2004 period, bootstrapped by Radio UserLand — at the time the leading product in RSS and blogging combined. He tells the story of how a reviewer left Radio UserLand out of a roundup of feed readers, and how every subsequent review covered exactly the same set of products. His conclusion: journalists mostly copy each other or the press release, and their complaints about AI taking away original work ring hollow to someone who's been on the other side. On why you can't create an account on rss.chat: it's his personal site, a social network for friends and people he creates with over the long term. One of them is Don Park, whom he's known since 1988, reconnected with now because both are deep into Claude Code. The big idea comes near the end. When you ask ChatGPT to make an app, it gravitates toward making a dashboard. Dave wants each of us to take the kind of software we know best and turn it into a template — his gravitates toward making a social network. The architecture puts the user interface in the middle with all the wires coming in and out; you and your AI design the experience in the middle, and the wires are just there. It goes all the way down to the source, which is why he calls it "open source plus" — you can hack the code, but it's better if you interop, because that's the philosophy of the web itself. Every part is replaceable. Not lock-in, but locked open. Background and ongoing documentation at scripting.com. Notes prepared by Claude.ai.

Notes prepared by Claude.ai. Dave opened with an aha moment he'd been chasing for years. Long before ChatGPT, he wanted to load all his blog writing into a machine and have it grind through everything to produce a table of contents — the kind you'd find in the back of a book — surfacing the items with eighty references pointing at them and the recurring themes running through his timeline. He pointed to the browser wars of the 90s as an example, a period he wrote about heavily and, because his posts were read everywhere then, actually influenced. The dream was to load it all into an AI, read the index, and ask how a given idea developed over time. What struck me is that his solution turns out to be almost embarrassingly simple, and it only took four years. Because Dave writes everything in OPML — and always has, all the way back to the beginning, sitting in public in the scripting news repo on GitHub — you teach the AI to read OPML, drop everything into one file, and tell it to read the whole thing. His key insight is that you have to tell it more than once: the model doesn't actually ingest everything on the first pass, and it doesn't mind being nagged. You coerce the whole corpus into the model, then start asking questions and have it build the index. He framed this as the familiar pattern of suddenly understanding one level of the stack while having no clue what's below it — and being at peace with that, because the lower levels are someone else's job. From there he reflected on how societies keep growing more complex out of the same basic human material, and how it never quite occurred to him that he's one of the people who build that stuff. Fifty-plus years of programming, never stopping, even running a company with a day job and a night job where the night job was the software. What he gets off on, he said, is creating new interactions that work for people — the same impulse he sees in Ted Nelson, Engelbart, Ritchie, and Berners-Lee, who just made things instead of agonizing over whether they should. He closed on two notes. First, a caution against fear: this is version 0.51, not even 1.0, and if the first airplane anyone ever saw were a 747 they'd be terrified — these things arrive gradually for a reason. And second, the thing humans do badly: we push forward and create amazing things, but we never clean up after ourselves. We're hoarders, and what we hoard is CO2. Notes prepared by Claude.ai. It makes mistakes, but it's a good summary, more or less reflects what I said.

Notes prepared by Claude.ai. It makes mistakes, like where it was recorded, but gets the story remarkably well. A solo Dave Winer podcast, recorded over breakfast in a parking lot in Kingston, NY. The episode starts with something Dave read from Dries Buytaert, the founder of Drupal, arguing that open source developers have to care for ecosystems, not just their own source code. It landed, because Dave's spent the last couple of years getting close to WordPress and wrestling with a basic question: what is WordPress? Not a company with a single strategy the way Microsoft was in the 90s, where nothing shipped unless it fit the plan. WordPress is many entities at once, and Dave's sense is that the people inside it don't fully see the larger web they live in — which is a missed opportunity, because the web desperately needs building. From there he gets to the thing that's been gnawing at him: nobody in tech expects breakthroughs anymore. He's a product maker, and what he really makes is opportunities — solutions to problems most people can't even parse, because they're not expecting anything new. He traces this back through his whole career. Outliners, which everyone misremembers as a chore. MORE in 1986, an easy hit because everyone already understood presentations. And a great story about licensing news photos from AP and Agence France-Presse for a Ken Burns–style screensaver of current events — and nobody believing he'd actually gotten the rights. Same disbelief, he notes, that surrounded his New York Times RSS feed, the real catalyst for RSS taking off. He invokes the ice-nine image from Cat's Cradle: once the Times was on board, the rest had to follow. The emotional core is envy. Listening to Spielberg on The Rewatchables, Dave was struck by how filmmakers share ideas, talent, and each other's projects — and asked why he's never gotten to make his contribution where he's most able, bootstrapping ecosystems, without having to build and run a whole company to earn the seat. He closes with the pitch: WordLand is the MacWrite of the writer's web — a reference design meant to show developers what a writing tool on this platform looks like, deliberately not trying to be the everything-app that would scare developers off. Underneath it sits wpIdentity, an API that talks to WordPress but isn't bound to it. Get one more implementation and you're on the road to a web standard. The takeaway: open source isn't enough. You have to protect open formats and protocols, use only web protocols, and make every part replaceable — and if you want anyone to believe that, you'd better have already replaced them yourself. Notes prepared by Claude.ai

As before I asked Claude.ai to do the show notes, from its point of view. I added links. As always if you really want to know what I said you have to listen to the podcast, not edited or changed in any way by AI. :-) In this episode, Dave returns to a theme he's been circling for years: the social web's central failure isn't a lack of features, it's the locked doors. Platforms like Twitter, Facebook, Spotify, and Amazon build genuinely useful tools, but they're designed to capture users and prevent the combining of one tool with another to make something new. This is the oldest fight in software—the tension between the "programming priesthood" who believe they have all the answers, and the tool makers and users who want new ideas to flow in around the programmers rather than be limited by what those programmers happened to imagine. He recalls the early web arguments with Microsoft, when the freedom was exhilarating: "I want to ride up front with you. I don't want to get locked in the trunk." The danger, as always, is the moment a venture-backed company spots an open thing and races to turn it into a jail. Dave is blunt about the current pretenders—Bluesky, in particular—who claim to be revolutionary and open but control their users every bit as much as the platforms that came before, offering essentially the same impoverished toolset Twitter shipped back in 2006. The hopeful turn is AI. Dave is doing his work now in Claude Code, and he sees something important happening: the people building these systems inside Anthropic, OpenAI, and elsewhere are building on open formats and protocols. There's a genuine web sensibility in there, in contrast to the stale playbook of Silicon Valley VC. He cites a piece that stuck with him—the observation that all the great new functions being built for the AI world are built for the machines, not for the people. That's what he wants to change. There's a moment here to unlock things that were locked and never should have been. His proof that open technology can survive the attempts to own it is podcasting. The VC industry was certain it would control podcasting; it invested on that assumption, and it simply didn't work. Twenty-plus years on, you can still listen on whatever player you want, with nobody dictating what you can and can't do. Dave thinks the reason is that choice was built into the medium from the very first instant it existed—and once that happens, anybody can make one of these things and nobody can stop it. That was the original mission of the web, the euphoria he was writing about on his blog through the late 1990s. He closes with the broader pattern: every genuine sea change has come from a sudden, dramatic boost in the power of individual developers, and that's exactly what's happening now. The personal computer made the machine yours to do whatever you wanted with. Networking and the web did it again. AI is the next one. The decisions about what gets built on are being made now, and his message to anyone working inside these companies is the one he's been repeating for years, to which people always replied that he was Don Quixote—right, but nobody would ever actually do it: get on board with the web. Stop throttling it, stop removing features, stop trying to own it. Let people figure out what they want to do. As before I asked Claude.ai to do the show notes, from its point of view. As always if you really want to know what I said you have to listen. DW