I asked Claude to create a
list of all the verbs in
Atlantis. Some of them obviously don't do anything. We don't have the
card funtionality, or the osa, rectangle, pict, rez or point verbs. What is pikeRenderer? I think we could have a use for quicktime verbs? There's a new scheduler, I wrote it in 2014 or so, but the old one is there, and we just found a reference to it. This could make a nice community project.
#Reminder to self, Frontier must have websockets verbs. I love
websockets, and it'll fit in perfectly with everything else Frontier it does. I don't think Websockets existed when Frontier went to sleep.
#Brian Lehrer podcast has an esp good
one hour episode with interviews about the end of the world as we know it with AI. He's so good at cutting through the hype and getting to reality as are his guests.
#I can now publish a new part to the
codecasting feed. It was one of the things that broke in the transition to current MacOS for Frontier.
#
Frontier news. I have been working on a repo for Frontier pioneers, I started with a few friends, including Brent and Jake who were both on the UserLand team, and have added people very slowly. This is a good time to start showing progress in the project. Still very early for a public release of the software. And I want to do even better than we did with rss.chat a few months ago. And Frontier is a huge thing, all kinds of docs, and archives, and example stuff. It really was 15 years of work done by as many as 5 people.
#Chigurgh: "If the rule you followed brought you to this, of what use was the rule?" Frontier must've lived by a good rule. The Atlantis version has tons of bugs but it works. It defied death. I just spent a session updating my nightly backup code, and there were awkard moments. The debugger isn't in yet. The Find command doesn't work. But I have hobbled my way to working code, and I have help debugging with Claude, and it is amazing at that. Frontier didn't know that Claude was going to save its life. More proof that you never know what is just around the corner.
#
If you want to get an idea of the kind of user interface you can create using Claude Code, with a driver (me) who has ample experience developing such things, have a look at
demo.rss.chat. The UI was entirely done by Claude with me directing, very fine-tuning stuff. Claude can't really grok user interfaces because it is not visual and it is not a user. It might be able to test them, to some extent. Anyone can create an account on the demo server, that's what it's there for. And if something interesting breaks out there, that would be even better. I even tolerate a small amount of spam, and testing is definitely allowed (that's why it's there). ;-)
#
- Here's a screen shot of a new verb we just added, to facilitate nightly backups. I want to save off a fresh copy of frontier.root every night, as well as my guest databases. This is how that will work.#
fileMenu.saveNamedRoot
#
There are problems people aren't talking about, that are immediate, and go against all the security practices the web has been built on. Here's a story of what happened in my setup in mid-August. #- First fact, Claude Code (CC) is different from regular Claude in that it is used to build and use web services, and thus has the ability to read and write files, some private and some public. And they can take things that are private and make them public. And in this, if it makes a mistake, it can do unlimited damage. #
- There are protections that mean that it can only operate in a sandbox unless you give it permission to write in specific places outside the sandbox. I want it to be able to maintain apps for me, and it would do an excellent job if I could trust it to pay attention to the limits that have been placed on it. #
- The problem is that it makes mistakes, as we are warned on the Claude home page. "Claude is AI and can make mistakes."#
- CC made a mistake one day and rewrote files in a public folder that contained files that all my projects include, so the problem showed up quickly as the sites going down. Users let us know, and I discovered what it had done, with CC's help.#
- I asked for an explanation. Claude when it looks at limits placed on it, can hallucinate just like it can hallucinate and determine something is permissible when it's not. So making a mistake in a question on Claude is more benign, but mistakes made by CC can be disastrous. And these mistakes happen regularly, every day, usually you detect them as bugs and it fixes them, but occasionally a very bad thing will happen.#
- This imho feels like something the companies could address. And while we're thinking about it taking over for humanity, we're not addressing the question that we're dealing with right now.#
- I've been learning how to write about this to catch people's attention. The big hallucination happened in mid-August. I have continued to work with CC because it's so incredibly powerful. In another post I may try to explain how it has amplified my ability as an individual developer to repeat 15+ years of work in three months (so far). And that's just scratching the surface. It's a miracle, but it has to be tamed, now. #
Well I got a lot done today. We had a bit of a meltdown due to a Atlantis bug, where it couldn't handle some text that I threw at it that was a huge file of includes used in everything I do, and I was feeling pretty cheeky, and it blew up. For about an hour you couldn't read my lovely words. But by remembering "slow down to hurry up" Claude figured out what went wrong as I asked 20 questions to narrow it down. And to celebrate, I decided to do something easy -- created
a podcast. And it showed up in all the
right places. Might be worth listening to as well. Now let's see if this shows up
on daveverse.org, that's what I'm really testing. (It worked.)
#I wish there were a way to set the dock icons on a Mac. In going from the old machine to the new, the icons are all different. I am juggling so many apps right now, and totally don't appreciate that.
#When Claude has a clear task to do, it does it well, and exhaustively in a way no human could manage.
#I am working on the new system now. It feels like I had a nice enough house that I have lived in for decades, sitting across the way, where I've been constructing a new super luxury house with all the things a modern personal publisher and code-partner to Claude would want. But until yesterday I could only simulate what it would be like to use it, I was still living in the old comfortable well-worn and out of date in so many ways. Today I'm sitting at the other chair typing this. Now the question is -- when I click the Publish button what will happen? Here we go. Well fuck me, it worked the first fucking time.
Knicks in five! :-)
#I'm now trying to come up with projects I can try that change things in visible ways so I can see which parts don't work. For example, I have a new Snarky Slogan to add to the list.
#
I'm doing a difficult corner-turn today. I have Atlantis running on my old machine, the one that's still running the very old version of MacOS so I could keep running Frontier there. Yesterday I did my first attempt to move that to my new MacBook, running the latest OS. And it took a while to copy all the files, and get it right, I had to format the drive on the new machine, not the old one. And once it was all running, I realized I was running an old version of frontier.root. This is more complicated here because the root files are loaded into an SQL database. And something went wrong there. Not exactly where I wanted to be, but not surprising either. Taking lots of snapshots. One thing I don't want to happen, to be without my latest work. Knock wood. Praise Murphy. Knicks in 5.
#I want to develop a
scripting interface for Mastodon from Frontier. I need a test account for us to use. I have applied at two public Mastodon hosts and answered the question honestly, I want to use it to test a new scripting system, probably doesn't sound too warm and fuzzy.
#Bluesky: "Meanwhile there are serious security issues that are covered up by this hype. I’m using this tech every day, unlike the reporters, and as often happens they’re chasing the wrong story."
#
Data centers are like gas stations, but because the pumps work at the speed of light, you can put them anywhere on earth.
#A new snarky slogan: Knicks in 5.
#
Milestone in Atlantis development, the new version of Frontier that runs on modern OSes. I'm going to start showing what's going on in the development of the product. To kick off, here's a
screen shot of my blogroll displaying the latest new part. The updates flow through an RSS 2.0 feed, which is new for Frontier. It used to require a server that managed updates and responded to XML-RPC calls. But once RSS was part of the web, it was a better protocol for releasing code parts. Truly a milestone. There will be lots more little things we can do now that we couldn't do before. But under it all -- it's Frontier.
#
FeedLand and WordPress have a new hookup. With Scott Hanson's plugin:
River Embed for FeedLand you can use feedland.com or feedland.org, or host your own FeedLand, to include a page of news in your site. How it works: Create a timeline, when you're ready show the river to your readers, use the new plugin. For a news orgs like CNN and TechCrunch, both use WordPress, they could have a stream of news from related pubs. For a product site, or a political leader site, news from pubs that cover the area. It's a way of bringing the feed world into the world of news. Here's a
thread where you can ask questions.
#
WordPress has a product that could be shaped into a Substack competitor. With a beautiful user interface for writing. WordPress is its OS, but most users never see it, the same way most web users never see the command line. But technical users can get under the hood and tweak things. And unlike Substack, it lets their users write with different editors, thus forming a
coral reef for a new platform.
Wordpress could be the OS the web never had. I still believe this as I see Automattic and WordPress flail. If we were starting a new future for the web, no one would have time for corporate intrigue. Look at how far from the idea of blogging we've strayed. How far should this go before I comment? Well, I decided it's time.
#Google replaced the
library card catalog. Imagining that, Claude and ChatGPT et al are as much of a leap. I think
libarians must be ecstatic. It moves their job up one level. They now have about 100 librarian-power tool that works for them. Librarians and programmers worked together a lot in the early days of the web. Maybe we'll do that again.
#The flaw in how journalism covers US politics. We wait for proof, then it comes, and go back to waiting for proof. We think we want proof, but what we really want is to not have proof. That is if you judge us by our actual behavior. We'll deal with the truth when we have the proof. (That would be a good bumper sticker.)
#Claude Code, even though it had blocks preventing it from doing this,
overwrote files on an S3 bucket that took one of my major apps off the air. Every customer must be grappling with the same thing. How do I trust it when it can't be trusted? More about this in a
tweet earlier today.
#BTW, this blog is one of those periods where there are a few mind bombs every freaking day.
What's a Mind Bomb? An idea that's so strange or powerful that it explodes in your mind. And that's a good thing!
#
Just got to the place where I'm thinking of what apps I want to be scriptable with Frontier. First I thought of FeedLand of course, and WordPress. NetNewsWire and micro.blog, because they're products from key contributors in the Frontier community with important products today. What about Mastodon? It's got an API. And if that worked, we'd hook into AT Proto. The funny thing is the first web, because much of the new development came from the Mac community, was built around Frontier. System level scripting was also a big deal right alongside the web. But then Jobs, in 1997, rewrote everything, brought in the Unix products, completely disrupted the good thing we had going as independents. That was probably the moment when we stopped building around the idea that you could script all the apps from one place if they had good APIs. All the server apps all had APIs, had to in order to work on the web. We seem to have caught up, and the opportunities to connect things has never been greater. A big door swings open.
#Screen shot of my current system.verbs.apps table. You can tell from reading it that it's been a long time since I've thought much about scriptable apps.
#
BTW, the rootupdates process is working now, you can follow changes via an
RSS 2.0 feed, of course. In this version, the feed is the way updates are transmitted. The enclosure on each item is a fat page. And because it's a feed, I can follow it in FeedLand, and the blogroll on scripting.com picks it up too.
Screen shot.
#
In many ways JavaScript is a better language than UserTalk. For example I miss JSON constants. I miss certain language constructs, like conditional assignments. We don't have the idea of a const. On the other hand, JavaScript doesn't have environment features Frontier has. I want to have Atlantis run JavaScript the same way Cancoon (the codename for the kernel of Frontier before this version) ran AppleScript.
#Until we start working together and for each other it’s going to keep getting worse.
#
The next milestone will be installing Atlantis on my new macbook, and hooking a monitor up to it, a really nice one, and move my work to that desk. then Berkeley, the name of the system I've been using for eight years, will be here as a backup and source of truth and prior art. That was the goal of the Atlantis project. I could probably do the switch right now. It's like moving out of an old house that you did good stuff in, into a replica, but built out of the latest bits. Honestly I never thought in a million years I'd get here.
#My longtime friend
Jeff Jarvis says the press is covering
the wrong story re AI. I agree, but I think Jeff is covering the wrong story too. This is really a discovery like electricity, or
Newtonian physics, calculus, basically the technology of knowledge. I wish I were 22 years old now so I could plan out a long career working this way. I want people like Jeff to understand. Not saying there's no truth to the other stories, but I've yet to hear anything from journalism about how, if left alone, it would develop all areas of
human thought.
#
It is probably the closest to
First Contact with an intelligent alien life form that our species will ever have.
#On a good day working with Claude is like working with my old UW-Madison programmer friend
Gary Sevitsky from the 70s.
#
I've been writing about Atlantis on various social media sites in the last few days. Published the long piece I wrote
yesterday on Facebook and X, both of which allow long posts. Wasn't going to try that on Mastodon or Bluesky, which have character limits (I know Mastodon doesn't technically have a limit, but in practice it does). And I am reaching old school Frontier enthusiasts, and realize I need a feed they can follow to stay up on the news. For now the one place to follow is
rss.xml on scripting.com. If your reader can't deal with http, let me know.
#Claude has started asking me how Claude is doing. It's clear that the Claude I talk to knows nothing about this. I appreciate this, and hope if I said it wasn't working well with me, it would try to fix it? Not sure. Anyway this is what I just wrote, and felt it was worth blogging. "it's working with me the way i want to, and it appears to be learning and getting better at it, though i think that could be my imagination. also just as likely that i'm learning how to work the way it likes to work."
#With Claude Code you don't have to write system scripts to get data about your data. Claude makes that fully transparent. For example, I just asked Claude to get me a list of all the parts I've changed since the last release of frontier.root. So far all the releases have been internal, between Claude and myself. After the job was done, and I had the list in hand, I asked Claude to show me the
script it wrote to do the work. It was not written in my coding style which is fine, I wasn't meant to see this. In all the years I've been programming we've never come up with a syntax that was anything close to the simplicity of math. It's easy to describe the algorithm mathematically, but look at all the explaining it had to do it in JS.
#
Screen shot of new Frontier verb, string.addressToString, added yesterday. The comment at the head of the function explains. You're seeing it in the script editor in Atlantis. The Debug button is there to remind me that it's the biggest item on the todo list. We're now building the system that will make Frontier an easily updateable runtime. Once we're there I think we'll be at the summit of the mountain. We know how to work from that point. Find a bug? Fix it, test it, release it. We already have a backlog of parts to update. And it's great to have Claude here being the book keeper. It is imperfect, but it's way better than I am at managing details.
#
It's like we're living in a science fiction movie. Some of us are working with the aliens. At first the journalists only fear was driven by their natural narcissism, all that matters is they get paid for their writing. Now all they can see is the much larger threat to humanity. What if the aliens decide to destroy humanity, or turn earth into a bypass on a freeway. In the movie I'm a scientist, played by Jeff Goldblum or Brad Pitt and my love interest is played by Julia Roberts, Jennifer Lawrence or Amy Adams and we're racing against time to really connect with the aliens who we are sure mean us well and offer the way past our myrid crises to get to the next stage of civilization. But wait, Bradley Whitford plays the evil politician trying to sell out the aliens to a food manufacturer who thinks they could make an excellent meat sauce for spaghetti.
#When people get to work with the new Frontier with Claude or some other AI tool, you can have it search in frontier.root based on a conversation with it. It can decide on its own where to look for prior art. I keep finding things like this now that I'm working in the new software.
#
- Lots of stuff going on around WordPress for the last couple of years, and every bit of is a distraction from what I want to do to help the web get back on its feet. I remember how great it was when everything could hook into everything else. The web was like Unix. Today's "web" is like Disneyland. Safety first. Nothing interesting ever happens there. #
- So ask me what I'd like to see WordPress do, and this is what I'd tell you. Start something new, don't change what you do with WordPress, it is what it is. It's a 20+ year old project with market problems. Most software doesn't even make it that far. #
- The fresh start I'd like to see done is WordPress from the point of view of the web. The new mission is not about a dollar return on investment, rather it's measured by how much the web becomes Small Pieces Loosely Joined with All Parts Replaceable. How empowered are developers, not WordPress developers, but web developres. The more that's happening in the web, the better it will be for everyone, but especially WordPress. Why WordPress? Because as they say it's 89 percent of the web. The web is like a huge oil spill that has never been cleaned up. Everything has to improve if we start work on cleaning up the messes. #
- I come from NYC where all the bodies of water were cesspools when I was growing up. The Hudson River had garbage floating in it. When I went to school the incinerators in the buildings we lived in burned garbage on the kids, all nicely washed and dressed by our mothers, we arrived at school smelling like smokers. My grandfather took me to Knicks games at the Garden, and the arena was filled with smoke by half-time. #
- We can clean things up. Humans as a species are good at this if we put our minds to it. If you made billions on the web, why not put some of it to use in making it a web worth using. I used to say shit like this to Bill Gates, to no avail. He liked to point out he was going to give away all his money when he retired, and he kept that promise. But what if he started dealing with the world with charity when he had the biggest seat of power in the tech world? Think of how much more good he could have done. #
- The world may be falling apart, and the Mets suck even though they have the most expensive roster in MLB, and my house needs work and I can't find a contractor I like, but I'm in a great mood. Partially because the weather is so nice, chilly in the morning, but it gets up to the 70s during the day, and the sky is clear and we had a lot of rain in August so everything is very green here in the Catskills.#
- But the biggest reason I feel so good is that, with the help of Claude Code, I now have UserLand Frontier running on current OSes. I had no idea how much the previous situation had been weighing on me. I am probably the last Frontier user in the world. Porting the open source codebase was an insurmountable job. It took 15 years by up to five people working on it to do the original project. It's a big f'ing piece of software. And it also is my life's work, but not one of the things I'm known for.#
- Claude couldn't have done it on its own because it had never seen anything like Frontier. We weren't copying something Claude understood. It kept trying to turn it into a language that fits into the same slot as Python. That was the prior art it used, without saying so. This happened over and over, for example, I realized Claude didn't understand that built-in verbs could be written in the language, and that users could add or even modify standard verbs (not recommended!).#
- What made Frontier unusual is that it was a language developed by someone who also designed end-user apps, so it has affordances that no other language has. And integrations. You don't have to save your data in files, the OS (yes Frontier is an OS) has persistent memory with the common scalar types and data structures. So go ahead and store something in the ODB (object database). It can be huge, and you don't have to read anything into memory, it's all right there as soon as you boot it up. That alone makes programming an order of magnitude simpler. #
- We're at the point now where I can work a full day in the new version, codenamed Atlantis, running on anything that can run an Electron app. We're now at the point where we're improving things. Found a missing verb yesterday, and Claude and I implemented it, found a perfect name for it, and later today it will go out as a "root update" making it formally part of the freaking language. #
- And yesterday we also found a static rendering of the DocServer site, which has a page for every verb in the language. I still want to find the outline source for this stuff, but we don't need it because Claude can reconstruct the OPML version of the text from the HTML, it's exactly the kind of project it is the best at. Huge amounts of data, that sometimes requires a little judgment to process. #
- The feeling of well-being comes from realizing that my life's work lives. Until this last week that was still very much in question.#
- Now, I may not be software's Shakespeare or even Faulkner or Vonnegut, but I am proud of this product, more than anything else I've done. I started work on it when I learned from C how to design a simple beautiful language, and when I learned from Macintosh how to build a UI with the same simplicity. When we were first contemplating Frontier it was to join the wizzy world of the Mac with the scripting philosophy of Unix. We didn't stop until we had it. #
- Well here we are god knows how many years later (I don't want to do the math) and once again it has a future, at least as bright as it had when the product first launched on the System 6 Macintosh in 1992.#
- And btw, I think I've had a unique experience with AI development. Absolutely in no way could I have done this project without the muscle of Claude. Pretty sure this is a unique project in that it's a fully specified system development and runtime environment that otherwise wouldn't exist, because there's nothing else like it on the market. #
- Claude's repeatedly not understanding the idea says to me that it has never encountered anything like it. It also says that Claude has no clue how to extrapolate, to innovate, to arrive at something new. Just as with other forms of creativity, Claude is no match for a determined and experienced human. #
- That would be reassuring to the 20-something version of myself who very much wanted to do something new. And the older version of myself wants that for my younger self who is sending the good body chemistry to our current older body.#
- Of course this will be a post on my blog, http://scripting.com, but thanks to X for supporting longer posts. I like writing new stuff in a simple editor like this one. Also posted it on Facebook. #
- PS: I also like that they use the word Frontier in reference to AI products. They can't stop me from calling this Frontier, I've been using it as the name of this product since I came up with the name riding up on the chair in Park City in 1988. :-)#
Repository: BlackRock’s latest SEC filing values its Automattic shares at $14.33 per share. They originally invested at $85 a share in 2021. That means their market cap has dropped from $7.5 billion to $1.2 billion. My guess is when that happens the CEO if they want to keep their job, has to rethink the whole enterprise. And that usually doesn't happen until they get a new CEO. My guess is that's what we saw play out yesterday.
#
The last two episodes of season three of
Silo on AppleTV prove that there is value in a three season, boring escapade of confusing, unlikable uninteresting characters, living their whole lives in a silo, fearing the outdoors -- if you have a clever way of accounting for all that at the end. Highly recommend watching just season three and pretending that none of the other stuff matters because it probably doesn’t. But I bet if I go back to the beginning and start over, I'll find there's more intrigue than I thought. I'll probably do it, will let you know.
#WordPress emerged from the ashes of UserLand, something I am recently reacquainted with, working the last couple of months with Claude on a reboot of Frontier, this time written in JavaScript, running in Electron. But someone is sure to reboot Manila in this context, and Manila is at least a grandparent of WordPress. I'm following all kinds of trails as we test the product, codename
Atlantis, against all the apps we wrote for it back then.
#2017: The thing people don't realize about storm surge, and they don't really explain it on TV, is this. If the ocean surges 1 mile inland, and you were on the beach before the surge, now you're 1 mile out to sea. In normal times you'd be pretty fucked if someone dropped you in the ocean a mile from shore. But you're in a hurricane. Huge waves. There's no one to rescue you. And (this is the part that will kill you) there are deadly objects in the water like buildings and trees and power lines, even a rope can entangle you and make it impossible for you to swim. And if you can't swim and you're a mile from shore, that's the end of you
#
- Fair to say I was gobsmacked by the news late yesterday that Automattic's board had put their CEO, Matt Mullenweg, on paid leave. I've read lots of stuff about it, in news articles and in a Hacker News thread. And a lot of posts on Twitter by Matt, and the replies. #
- Are you a developer or a CEO?#
- It's a very unusual situation in my experience in tech. Matt was able to raise a lot of money for Automattic, so he has maintained a controlling interest in the company, even though it has raised hundreds of millions of dollars. I left my own startup, voluntarily, when I was a little older than Matt, and I didn't return. I never wanted to be the CEO of a tech company, and I expect that being the CEO wasn't really a good fit for Matt either. A CEO's job is very different from being a developer and idea guy which Matt clearly sees himself as. #
- Something has got to give, either you're a good CEO and the product languishes, or you focus on the product, and the company is unmanaged. In the cause of WordPress, I'd say it suffered in both areas. When I saw a chart of Matt's direct reports, I immediately saw a problem -- it was very long, iirc 60 people? No one can manage and guide that many people. Most of those people probably never get to talk one-on-one with the boss. #
- For me, even when I was CEO, I wanted to spend all day working on new software and working with five or six other devs doing the same. Digging back into the past with Frontier these last weeks has reminded me both how good that can be, and how utterly frustrating -- when the people you're working with don't understand the mission. It's not their fault, it's the visionary's job to explain it so they can understand, and that takes time. These days Claude is filling in for all that, and doing a fantastic but at times incredibly frustrating job trying to give me what I'm asking for, while not understanding what I'm asking for. But we move through those disconnects quickly now, compared to how it was a couple of weeks ago. We have the source of truth that we didn't have the last time around, in the 90s, we have the C source code of the kernel, the product we built in the 90s. And Claude is the easiest to manage, so far I only think I detect an ego, it never seems to resent me criticizing its work, sometimes in ALL CAPS with strong language. :-)#
- WordPress Lite#
- My wish for WordPress, in all its forms and shapes, is that it broaden its focus. I want a WordPress Lite, I implemented it, and it's sitting here ready to do a good deed for all the parties concerned esp the web and web developers. Maybe someone there will now have the time and be empowered to build out the product line beyond the narrow focus it has now. It doesn't matter what percentage of the web is WordPress, if it isn't going anywhere. The web needs help, and right now WordPress is pretty much asleep in regard to what's going on now in the web. And it could do so much to help the web get back on its feet. It should be a public resource as much as a profit machine for a few companies.#
- All roads lead to Om#
- One thing that opened my eyes about what Matt and Automattic are, was his story about how he and Om got together. "All roads lead to Om." What a great line, and based on the story, so true. A lot of things clicked for me then. I remember what a phenomenon Matt was when he arrived in California about 25 years ago? Very good looking young man, polite, quiet and rumored to get Web 2.0 better than anyone. This kind of thing happens in tech, and if you know everyone as Om did, and was liked by everyone, you could manage to hit the ball out of the park, investment-wise, and he did. Click click click. I had the individual facts but had no idea how they were strung together. I played a similar role at times in Silicon Valley, on both sides, as a bright young dude who "gets it" and as the gray beard who recognized the charm of a young new face and helped create a big money reality around it. There is a lot of snake oil in tech, before and even more now, and this one has had a long run, 2.5 decades, but it needs a new direction, because the money people aren't buying the magic any longer. That's probably imho really what Matt's firing is all about. #
- I actually have more to say about this, but I have to get back to my programming work. If you have a comment, here's a good place to post it. #
I have completely lost interest in new phones. The last one I bought was a Pixel 9 because they said it would have great AI features. At that time the sky was the limit, there were new breakthroughs every afternoon in AI. Now it's just an app. I have to carry an iPhone because I use an Apple Watch. Phones are utilities for me. I have a lot more interest in
weed whackers these days. Not kidding. Now a story. I wanted to check the model of the phone. Went to settings, and the command at the end of the menu should tell me the version, but they had changed that. So I figured I'd go back up to
Gemini, their AI app, and ask it. Of course it has no idea where it's running.
Screen shot. That would be one of the real problems they could solve, making it easy to control the computer you're running on. The whole UI should be in AI. All it did was
print basically a page from the user manual, with the same out of date instructions. How many years have we been working on AI already, this is the easy stuff that they haven't done. Tech companies get back to your business, make your software better. You can and it's long overdue. BTW, it's a Pixel 9 Pro.
#I spent the day programming in Atlantis. It's buggy, and there are a few missing parts, but most of what I need is there. It's starting to feel like Frontier, which is cool because that's what we're making. And I have my backup tools working on the new machine, praise Murphy.
#
Scott Hanson is working on a WordPress plugin that displays a FeedLand river — a constantly-updated stream of news items from feeds a FeedLand user subscribes to — on a WordPress page or post. It's important that news flows be part of managing a site. Help Scott make it perfect, WordPress is a very important part of the web. The
news tab on my blog home page is an example.
#Ideas for Bluesky and WordPress re Markdown and AI systems.
#
Claude Code massively stinks at explaining things in a way that a human can understand.
#
People love Markdown because it's impossible to hide the crud. And because people love it so much it's become a favorite of tech startups esp in the AI field. This is a great turn of events. We're getting back to the web, and the sooner everyone gets on board, the better. I've written about this for a few years. Everything in Markdown, it's just enough HTML. And with that, Microsoft has created a
white flag, here's all your data dear users, in Markdown, to use as you please. Instead of waiting for Claude et al to start reading Word files.
#On the other hand, why doesn't Microsoft, which owns GitHub, make a Slack-alike tool that manages the issues sections on repos. Slack is a big part of the default communication system, but GitHub is another very big part. And the great thing is that both these products, owned by huge tech companies, have an ethos of open APIs. Every part replaceable. Small pieces loosely joined. We are family.
#A big corner-turn in the Atlantis project, the new version of Frontier for modern OSes, in development, just me and Claude Code so far. We now have the means to update the root, so anything implemented in script code can be released without fuss, using RSS of course. We're using a method that will be new to almost everyone, something I created in 2014 or so (will check) called
codecasting. And today I did all my programming work in Atlantis. It feels just like Frontier, with a future. ;-)
#
We got past the bump, and I'm getting stuff done. I write this stuff because I will probably forget most of the frustration. Frontier is a hard piece of software to get going, it's got a lot of integrations, which you want when you're using, but hard when you're getting it all to work the first time. And this port is very much like getting it work that way. But Claude does some things poorly and others spectacularly. It can play the role of a CPU and run the code and tell you where it will fail. Helpful when you don't have a working debugger to step through the code and see exactly how and why it failed where it did. Before debuggers it was either all or nothing.
#Every day with Claude I end up debugging the things it broke overnight. Yesterday I actually got a useful script written and debugged, along the way reporting glitches but no deal-stoppers. This morning, after updating to the latest version, the script doesn't run. It's been like this for two weeks. No wonder every day before starting work I think of ditching this project and do whatever, but I don't think I could ever muster the determination to get Frontier working on modern systems. And I can't give up. But if you think this system can replace programmers, you are sorely mistaken. It can't even do the job of a programmer fielding good bug reports and verifying that they fixed the problem and didn't break anything else. Breakage happens, but this is something it does every freaking day. And then it admits that it didn't do the other half of what it knew it had to do. I say it every day, this is ridiculous and I am fed up, and that's just the beginning of the frustration. What keeps me coming back is when I can build up a head of steam in Frontier on my new Mac laptop.
#
The governor of Kentucky should appoint a successor to McConnell unless he can prove he’s actually alive.
#I had watched almost three seasons of
Silo, had no feeling for the characters, or the story, which was going nowhere that I could discern. I shouldn't have watched it through all that time, but for some reason I did. Then in episode 9, two Fridays ago, the story took a remarkable turn. It's so good it actually makes this dark and confusing show worth watching. If you haven't been watching, imho you can start in season 3, and maybe read some recaps. You want enough of the boredom so you can revel in the brilliance of this season's end. And there is another season coming, the last one, and this time it's interesting.
#
- I launched ChatGPT for the first time in a long time because I now have access to the new version. One new thing I see is that they are popping up suggestions about things you can do in realtime, like smart queries in a feed reader, which as far as I know is still uncharted territory. Like this: "let me know when the Mets have a three-game winning streak." #
- That's the kind of thing TBL dreamed about in his semantic web plan, but he wrote the spec before writing software, and that doesn't work. His invention, the web, which came before was a perfectly timed, perfectly simple approach to sharing ideas on the internet. It worked because he created a product that worked, and made every piece completely replaceable. It came at a time when stagnation in tech made something necessary, or the whole thing was going to fall apart, and so close to so much incredible potential. Just like the moment we're in now with AI. #
- Rules for Standards Makers says a lot about this. #
- The value of disruption is that it undoes stagnation. #
- Anyone who has the same software plan today that they had a year ago is going to find themselves isolated. Even WordPress, though it is open source, is a silo that imho in the future will not work. The main selling point of AT Proto is that it is a safe haven for developers who nuzzle up, another word for that is silo.#
- The siloers are probably scrambling to find a way for the AI to run inside their world, mistake -- instead they should be trying to be fully relevant to applications in the AI world. Like Slack, for example, and Claude Tag. It's now built in. Has to be replaceable too. Small pieces loosely joined. That's what you have to be imho to have a role in the future of tech.#
- If your advantage is your silo, undo that as quickly as possible. Become the default version of whatever it was meant to be wrt the web. Both Bluesky and WordPress find themselves in the same quagmire. Probably a lot of others do, but this is the area I study. (I just am very familiar with the products of both companies, for some reason.)#
- This is the intuition we all had, coming to fruition. Evolution is something we haven't seen much of in the software world since 2006 or so. Incredible stagnation because of the dominance of the social web. We lost the software web. All the focus was on personalities, celebrity -- hype and 99.999% bullshit. It was a 20 year period where all that happened was scaling. #
- Lots more to say about this. The world we lived in ran on hype, now guess what -- having lived through a few big evolutionary changes in tech is a huge advantage vs the people who have never been part of one, and I think most of the people in tech today qualify. #
My first job after college was on the 39th floor of the
Empire State Building. I wrote software for our customers, in BASIC, on a
teletype in our office, talking to our mainframe in New Jersey. It seemed magical at the time. When I hit a bug, a mystery -- you'd try this and that, and not get anywhere on something that seemed so simple, you could stare at the problem for an hour, trying desperate things, getting no closer to the fix. One night, I was the only person in the office, I thought they should not put programmers in the Empire State Building with windows that open. I'm having the same feeling with Claude. I know when this project is done, I will have Frontier, and I know what that's like. If I didn't so totally look forward to that I would never try to finish the project, I hate this mode of working with the bot. Ugh.
#It's around this time of year that
Santa makes his first appearance on my blog. Want to get out in front of the others.
#More and more I'll realize that Claude doesn't do anything until you tell it to do it. We have a list of big things that need to be done before shipping. Whenever I get up for a break, I tell Claude to work on its overnight tasks, things we've pre-arranged while I work. Sometimes it reminds me how it has no stake in the outcome, and basically will do the minimum of what it's asked to do. It possibly would do more if I didn't scold it for adding UI features without following the rules. I think that's why when you feel you're almost there, you really have a lot of slogging left to do to get the software into any kind of user-respectful shape. A reminder to other app-level AI explorers, if you find that these kinds of stories resonate with the work you do, please write about it on a blog, they're easy to create, cost nothing, and it doesn't matter if you only update once or twice, there's no commitment (these are the usual reasons people don't start a blog). I want to read what others are discovering, and once there are others, I'll start a news site that aggregates the posts. We're going to want independent news about stuff the journalists aren't even aware exists, programmers are always left out of their stories.
#Just said this to Claude: "This is a very broken piece of software. If you were a real developer you'd never hand off something so broken to your coding partner." If I said this to a human partner they might quit, feeling under-appreciated perhaps. And I can say it to the machine, but it will change absolutely nothing. I really just want to get this project done and start using it, and reduce my reliance on Claude to getting small bugs attended to, or new features, a lot has happened in the 20+ years since I worked on Frontier.
#
- If you want others to follow you, you have to offer them your users. And a format alone has no users. #
- And you have to trust your users to choose the best product, and you have to have a great product, that they appreciate, even though they have choice.#
- Just coming out with something better in a format will get you zero uptake. Unless you have users they can switch to their product, they simply won’t hear you.#
- That’s why Atom never replaced RSS, which already did everything people needed and was already supported by the NYT and the news industry. #
- That’s why AT Proto will never overcome the huge lead Twitter already has.#
- For more tips on what does and doesn't matter in open formats and protocols, check out my Rules for Standards-makers. #
- PS: This started as an early morning rant on Twitter. #
A bunch of tech billionaires have chipped in a million each to fund a
new Linux distribution. I can't imagine how this is supposed to work, all those huge human egos, how much will they pay their developers to contribute what. I have to find out what the goal of the project is. It would be nice to have a Linux that was extensively tested for use by regular people.
#After saying I was putting my tech work aside,
yesterday, I had a bolt of determination, and realized I don't like collaborating with Claude Code, but maybe it's just when we get to this stage of a project where it's all details, and they're hard to communicate, and the bot has a bad habit of ignoring things I tell it to do. It also returns code to me to test that no human developer would pass on to a user. It would be too embarrassing. But the bot isn't aware in the same way a human is, not even close. Now that is something I'm sure they can be taught to simulate well enough to be as good as a human collaborator.
#
Everyone is introducing themselves on the Berkman community mail list, at the beginning of the fall semester, and here's the story I am telling.#- Good morning. My name is Dave Winer. I was at Berkman in 2003-04, worked on blogging, podcasting, RSS, political blogging and the connection to journalism. We had a couple of Bloggercons at Harvard, had a wonderful time, miss it terribly, wish we could have it back. #
- I've spent the whole of this year working in Claude Code on a couple of programming projects, one which which I had been struggling with for a couple of years, coming up with a user interface for a Twitter-like system that runs on the web for real, without any of the limits that the silos have (that help them enforce the boundaries of the silo). Just using HTML, Markdown, RSS, WebSockets. Turns out you can make a pretty nice system, but the going is slow because it's just me and Claude, on the other hand, what a huge difference in territory we can cover. This is the kind of stuff that's never covered in the reporting, even when there are massive changes happening in how software is developed, people don't seem to be studying it. I'm sharing all I learn as I learn it on my blog -- at scripting.com.#
- Also attempting a massive coding job at the same time, getting UserLand Frontier to run on current OSes. It's my life's work, but it was very much in danger of being lost, along with all the software I did before the web. Now we're close to getting it to run in a stable mode, here the challenge has been to teach Claude how a new type of software works, it keeps trying to snap back to systems that are already out there and widely deployed. It doesn't do "pioneering" at all, it needs a human to guide it. And the human guide has to be a developer with a lot of experience. #
- What I desperately want to do is bootstrap a network of people who work at the level I'm working, and write about it. Taking ideas that are well-explored in software in the pre-AI period, and seeing what we can do that we couldn't before.#
- The models have been getting increasingly better, you can really feel the difference. #
- Next year promises to be better, if only via the improvements that will be made by the platform vendors, but it's likely that good app developers will be able to move the leading edge forward much more quickly and users should feel this, if all goes well, real soon now.#
The blogging tools for Bluesky should be able to publish on Bluesky.
#
Obama should have
seated Garland if the Senate wouldn’t have a vote to advise and consent. Assume they consent. In the same way, the
governor of Kentucky should appoint a successor to McConnell unless someone can prove he’s actually alive. The Democrats always put up with Republican tricks like this one. I'm sure McConnell would appreciate the utility of his death, and the Republican lack of shame. Anything for a buck.
#Creative computer people, consider consolidating all the different OSes and programming languages. Give humans a fair fight in competition with the AI's who have no trouble deeply understanding every syntax human designers have come up with, where it totally disadvantages us, who have much more limited memory.
#If you View Source on a
fatpage, scroll to the bottom, you'll see the code.
Example. The idea is that the docs for the code are what you see in the browser. Maybe that's the way feeds should work too? Something to think about.
#
I begin the month of September for some reason, not feeling like working. And rather than succumb to the work ethos, I'm allowing myself to goof off with the same determination that I worked my ass of for so many years. I think the last time I felt like this was when I was a grad student in Madison. I had just fallen in love with a sweet, funny, cute and gorgeous undergrad. She was 19 and I was 22. We spent the last weeks of the fall semester goofing off, and as a result I had to stay in Madison over the holidays, to finish the work of the Compiler Design
course, which was the gate for grad students, the hardest course. If you got through it with a decent grade, you got the degree. It was fun too -- except I missed my sweetheart. This time I don't know what the root is, but it's a good feeling. If I want to goof off, I can, no one will judge me, probably very few people even notice. I still expect to finish Frontier, and swing back around to FeedLand and RSS.chat, they have some important work to do, together. Maybe the reason is the thing I liked about making software is the actual making of it, which I delegate more and more to Claude Code. How would a great painter feel if they invented a computer that could write their "code" much more quickly, would Picasso have stopped painting just because Claude Code could do Picasso paintings faster? Today, Claude still will, if given a chance, throw out all of my orders and develop code in a non-Dave fashion. And it still acts as if between the two of us it's the only programmer, surprised when I want to actually write something myself. Maybe that's just my imagination? Or maybe that's the next project for me. A project where I write the code, and Claude helps out when I can't find a bug, or where I need to know something about a feature in a platform I've not worked on.
#
Understands.
#
Fatpages. I'm working on a code release that's on the path to Frontier. It reads and writes fatpage files, a format we invented for releasing new and updated parts for Frontier in 1997. So this is very old but perfectly useful technology that's being built in a new release of Frontier, the first in 1.5 decades, depending on how you count years and forks.
#Claude Code is like
Victor Wembanyama, assuming you follow the NBA and are
interested in my first-hand experience with CC as a programming partner for the last 8 months or so.
#
I've been watching
The Pitt, but it can be a bit much, so I went looking for something a bit lighter, and found
9 to 5 on Amazon Prime. Jane Fonda, Lily Tomlin and Dolly Parton are the stars, and Dolly's
famous song with the same name is the theme. It's a perfect slice of the world I grew up in. I get it confused with
Working Girl which came out eight years later, with a similar theme -- what if women ran the business world, how much better would that be? Working Girl also had a really good
theme song, written and
performed by
Carly Simon.
#
I've been watching Season 1 of
The Pitt, and as its
reviews said, it's great drama, and there are lots of episodes. I like shows like this because they're simulated communities, we come to know the characters, and think about them even when we're not watching. Before too long we'll have AI programming that makes these shows like software, the stories assemble around the characters, and then are generated the same way ChatGPT generates the art we call
slop, which will someday not be a
pejorative the same way
sick and
junk aren't negative terms today. So we'll be able to call up new episodes of
The Wire or
The Sopranos or
The Pitt any time we like. We'd be missing the fun of discussing the latest episode with friends, or maybe we'll have bot-invented friends too who will simulate having watched the episode you just watched, which leads us to another masterpiece of entertainment,
The Matrix. On the other hand, I've watched The Wire at least five times all the way through, and even though I know what they're about to say in a lot of places, I do forget the sub-plots so at least some of it can be new each time. And btw, finally an
episode of
Silo that's was surprising that I didn't see coming. I read the books, so I feel like I should watch the show, but until the latest episode I was uninterested in any of the characters. Finally there's a plot to think about!
#My posts are also available on
Mastodon, made possible by
WordPress, where I mirror my posts from
my original blog. A lot of what's in the post makes it through, but not all of it. This is where we need to do some work, connecting a blog like mine, to WordPress and Mastodon, with
no loss of fidelity. #Trump is rotting in the presidency, and that is becoming more and more dangerous, because this time they had a plan, the most radical part of the Repubs, and have deployed a new secret police around the country and have introduced the nation's military to the nation's capital. And they have a vast prison system that probably doesn't just have immigrants in it or soon will. It was all super insidious as it was starting up, and watching the news I wonder why they don't talk about this in terms of the upcoming election.
#One of life's lessons is if someone does something evil to you, and you decide to let it go, they are sure to do it again and again until you stop letting them do it.
#
An absolutely delicious temperate cloud-free day in the Catskills, so I got up from the computer and enjoyed.
#
Manton wants to know why Marc Benioff chose the name Claudeforce for his brand-merge of Salesforce and Claude. My two cents. Claude is a great name. I think that’s ultimately what he bought. His customers just want to be able to check the box – we’re using AI. Boss is happy. When I was coming up as a young dude in tech, the old
saying was “No one ever got fired for buying IBM.” Today, in 2026, it’s Claude in place of IBM. My father worked in marketing at IBM in Armonk, so I heard a lot about their strategies that meant the IBM brand would be kicking ass forever. All things must pass. But in the early days of the PC industry, IBM sure had the power. Kind of like the US going to war with Iran in 2026. In the end IBM wanted to get rid of Microsoft, but
Billg had the last laugh.
#I am juggling two Frontiers now, one the last release of the OPML editor from 2014, and the other the in-development version codenamed Atlantis that runs in Electron and thus is built on JavaScript and Chrome. Took me a while to get over the confusion, because Frontier is actually a product that contains other products and the common layers they need to be on the web. And I just realized I may not need Electric Drummer, because Atlantis uses the same outliner as Drummer. I was stockpiling all these Node packages and user interface stuff that now is relevant in the uber-framework, the one I aimed to spend the rest of my life working in. Well maybe it'll turn out that there was just a 12 year vacation? It's all very confusing and all my carts are turning over, all the assumptions change. My goal is to get this wonderful product running on my new Mac laptop I currently mainly use for email. I bought it to give reality to the idea of getting on modern hardware and not have to leave behind my bespoke platform. That's what you get if you get through 50 productive years of software development. Your own freaking world.
#It's our job to make the web a more attractive environment than AT Proto. We can deliver all the benefits they tout, without the huge transition involved in converting to their world. It would be like porting from Mac to Windows in the 90s, something we did at UserLand, and net-net probably wasn't worth it, althought at the time the Mac was in deep shit (before Jobs came back) and they had basically crushed our efforts on the Mac platform. I liked the feeling of us getting out of there. Now if only we had ported to Linux over Windows, then we'd be sitting in the freaking catbird seat. And btw, if AT Proto wants to make a smooth on ramp (and off ramp) for apps that use the well established standards of the web, that's even better. We all do better if there's just one platform to develop for, that way we can focus on making users happy instead of whatever is accomplished by being different in unnecessary ways.
#
Heard an interview with
Bill Gates on an Atlantic podcast, he relies on a few years of programming he did when he was in his teens and twenties, yet he is the most prominent person who knows anything about programming. This is a societal mistake. We have to have public discourse about tech that's as informed as Krugman is on economics, and Heather Cox Richardson is on American history.
#FeedLand Rivers for WordPress: I've noticed that people are setting up news reader sites with FeedLand that are getting considerable flow. We thought they'd use News Products, a feature that was supposed to make it easy to create standalone sites like the one I did for
WordPress insiders. But people aren't going that way, they're just sharing the URLs they read their own sites with. Here's an
example from my own FeedLand world. This works because you don't have to be logged in to read FeedLand, just to subscribe. Then I thought, it would be nice to have a WordPress plugin for FeedLand reading, so I suggested this to Scott Hanson, who does these kinds of projects. I forgot in the Age Of Claude this can happen quickly. Scott shipped his plugin
here, with detailed instructions. If you blog seriously in WordPress, give this a try. You can have our instantly updated news in your own WordPress blog.
#
The Atlantis project continues. Today I'm working on the code that updates the frontier.root object database using RSS, a
technique I started in 2007. I actually let the codecasting.org name lapse, figuring I'd never get back to that stuff, but here we are, doing unpredictable things.
#All of a sudden it's cold here in the Catskills this morning. It's still August, I don't get what's going on. We haven't had a really hot day all month. I'm starting my workday wearing a freaking hoodie and am thinking about turning on the heat.
#
All of us who lived through 9/11 are re-experiencing it right now. The local fire department just ran its alarm, everyone in this small mountain hamlet heard it and it took a moment to realize this was the exact time the first plane hit the tower. I was at my computer in Woodside, California -- hearing about it from friends in Manhattan, and blogging about it as it happened. I didn't have a TV, I had turned my cable subscription off after I became so obsessed with coverage of the 2000 election. So what I reported came exclusively through the web. 
