
The last few days we've been
exploring the ideas behind the web, to decide what, if anything that we're doing today is either
on the web or
of the web. On the web seemed relatively easy. But of the web is a bit more elusive. Until
Ken Smith found
this quote of
Ted Nelson in the original 1989 proposal by
Tim Berners-Lee for what would become the web. "Human-readable information linked together in an unconstrained way." I like this, because it, like the definition I came up with for
weblog, talks about the activity as opposed to the technology. Human-readable is essential. And most essential is "unconstrained." If something requires a link, you should link to it. If you don't it ain't the web.
#
It's the future, and the great power of the X galaxy, on the planet Y of star Z, has accidentally elected a despotic prime minister who also happens to be an excellent standup comic. Kind of like Robin Williams, from the planet you come from, but he's a centipede and only breathes what you would think of as Chef Boyardee lasagna, but it's not really that, it's different. #
- Anyway, he's old, 757 centuries give or take, and they're expecting him to die soon, and they can elect someone boring so they can forget about politics. Everyone is looking forward to the relaxation. #
- And then one day he does die, and everyone breathes a huge sigh of relief, until later that night, on the 10-screen equivalent of what you would think of as TV, hilarity ensues when the "dead" PM showed up, looking fit, young and dashing, doing slapstick and talking about how he's going to make a mess of something. #
- Everyone was furious and then puzzled, we thought he was dead -- until the rumor started going around that the scientists had invented a sort of "artificial" thing that could perfectly emulate anyone or anything, including a Lasagna-breathing centipede comic despot from planet Y of star Z in the X galaxy. Everyone was pissed, but mostly agreed the PM was still pretty funny.#
- End of pilot. #

Movie poster demo.
#
ChatGPT is the Lotus 1-2-3 of search. Google is Visicalc.
#
The
consensus among the people who responded to my what does "on the web" mean query is this. Something is on the web if it has a URL you can use to view it in a web browser. That means, in 2025, that the URL begins with HTTP or HTTPS. Every "page" on a site must have a URL so they can be pointed to independently, otherwise known as deep linking. It's not enough to just have a home page that's on the web. So for example, an iPhone app isn't on the web just because it has an information page that is.
#
I'm working my way through Mr Robot, for the third time I think. If you want to know what I do, it's like what Elliot does, for about four hours pretty much every day. I used to work longer hours but I've found this amount of work is optimal. I make more mistakes after about 1PM. Anyway Mr Robot is a very good thing to watch for the times we live in. The technology is already a little outdated, but they thought of that, there are some scenes where they use old PCs from the 80s, with total respect. I like that. And the utilities he uses are pretty much the same ones I use these days. And the context of a world in technological meltdown, I think that's a very realistic scenario. I don't see how our networks can't avoid breaking down. And our health care system, which these days is pretty much the same thing.
#
I think perhaps I should have one day every week where I never link to anything. Just to provide a demo of what the web would be like without linking. Which is most of the sites that say they are part of the web. I think that's a lie we should stop tolerating. Or maybe I should just stop offsite linking for one day a week. That would be interesting wouldn't it. Or I could charge extra for the version with the links. (It's very rare that I charge anything to use any of my web work, but I
have done that at times.)
#
I asked, yesterday, on various social media sites, for people's opinion on what the term "on the web" means. I'm going to compile the answers on a
this.how page, and then ask some follow-up questions. If you have an opinion, post a comment on
Bluesky,
Mastodon,
Threads or
Twitter.
#
I've been exchanging emails and voicemails with
Dan Knauss, a longtime WordPress developer and one of the hosts of WordCamp Canada which I am speaking at in October. Learning a lot about the community and culture. I wonder, have I ever been part of a community that's over 20 years old? I can't think of one off the top of my head. I have gotten this far without knowing much about the WordPress community, other than what I've heard via Matt and what I've been able to infer from that. I've known Matt since he was a teenage boy wonder in the tech industry working at CNET and then as an entrepreneur. I think my point of view is a new one, I don't bring much baggage with me. I am generally sympathetic with Matt, having been the leader of the blogging world when it started, and found it a pretty thankless place, a position I was happy to relinquish in 2003 when I went to academia.
#
There's a fresh release of the docs for the
WordPress API we use in WordLand. I actually liked that the docs were old and kind of dusty. It says that the engineering culture is to not mess around with things that developers have already built on. A lot of platforms break developers without much thought. I learned a long time ago that when you do that, you lose the interest of developers, understandably.
#
I've been following Mark Cuban's recent posts on Bluesky, coming up with constructive things successful entrepreneurs can do to help. I had a different idea. Apply for a fellowship at a university, away from where you live, maybe in a place you've always wanted to try. In your application say you bring your entrepreneurial experience, but you're leaving your money on the side. You're coming to the university with the idea of creating something collaboratively, bringing the entrepreneurial approach of startups to the mix of people you find among academics. You're there to learn from the teachers and the students, and help them understand what you do. Use your mind, experience, creativity, even your contacts, but leave the money at home. You can live in a nice house, drive a nice car, but eat in the places people in the university eat, go to the lectures, concerts, sporting events, in other words, go back to school with your new perspective, and make a
personal contribution. It's much more satisfying than spending money is, I speak from experience. There's a different kind of success in the collaboration. Another way to test yourself and develop new perspectives and experience. I wrote about this a few years back in
Developing Better Developers.
#
- Trump is a comedian. He makes people laugh the way Joan Rivers or Don Rickles did. #
- It's verbal slapstick, which is for some reason I don't understand immensely funny and entertaining.#
- Newsom is making us laugh by imitating Trump imitating Joan and Don. It's working. He must keep doing it, and he should evolve the schtick, he should make Trump match him. And where Trump is promoting depraved policies with his comedy, we can count on Newsom to stand up for the Constitution and the rule of law and all the progress we've made. #
- He can invite famous comedians on his podcast to play opposite him, sometimes the straight man, playing their SNL roles. So much potential. He's got the attention, don't throw it away. #
- Politics was boring, it's not boring anymore. But there's no reason excitement and entertainment can't be good for us too! ;-)#
- Trump's secret is comedy and Newsom is stealing his thunder#
Mark I want to use my (comparatively small) fortune to develop a truly open platform for discourse on the web. Users and independent developers get to try out all the ideas for discourse and learning. We create the ideal system together to plan our future, not being owned by oligarchs.
#
I picked up my Android phone to record a voice memo. I had to dismiss a dialog that said the phone had updated overnight and asked if I wanted to see a list of changes. I thought, clicked No because I had an idea I wanted to record. Opened the voice app, hit record, couldn't remember the idea. Wanted to kill the message, but the UI had changed, so the Delete button that was there before wasn't there now. Great so now I have a 4-second recording in the queue that's nothing but frustration. There ought to be some basic rules of how software evolves. You can't take away a very basic function like this. And find a way not to get in the way of the user getting done what they use your product for. One of the most basic things is recording an idea. If you're lucky enough to be the app the user uses for that, don't screw with it. Same for listening to podcasts, and a few other things. That's about all I do with my phone.
#
- Just posted on a Facebook thread I unintentionally started.#
- I don't like public conversations where people judge other people and they feel compelled to explain themselves. I wasn't in any way intending on provoking a conversation like that here. So I'm going to delete the comments that have gone off in that direction, and please don't post any more. I don't mind you having that conversation, but do it somewhere else where I don't have to read it. Thanks. #
- Everywhere that's the only structure for discourse we've created. #
- We can do better. I have to create my own system to prove it, so much work, but worth it, I expect. #
Update to the
reallySimple package. We now look for feeds from wordpress sites, and copy the site ID and the ID for each post as channel-level
wpSiteId and item-level
wpPostId. Example. This will make
Edit This Page functionality possible in the
social web product I'm building now. This is fairly technical stuff, but important. I've come to see WordPress as an integral part of the web. Making the connection between a feed and the info needed to edit an item is a big usability feature. Next up, adding the equivalent feature at the
FeedLand level (reallySimple is how it does its feed reading). Remember, this is the feed-o-verse, it's all feeds, top to bottom. Posts in some feeds can be edited. :-)
#
Baby boomers have nothing in common except we were born in the same 20-year period. We didn't come up with the term, also -- it was given to us by previous generations when we were infants, or worse, not even
zygotes. There was no way it had anything to do with who each of us were or what we would become. All this is in response to the idiotic idea of the
little dude who just wrote a
book, nine years older than me, what a putz. He apologizes for boomers, feeding the bullshit idea that somehow we are a unitary thing. A lot of boomers voted for Trump. The boomers I come from liked the Grateful Dead and yes I know some deadheads voted for Trump, so there you go, more evidence that it's all bullshit. The thing we had in common is that we were children at roughly the same times, but even that's bullshit, a 20-year old boomer in 1965 could be the
parent of a boomer, literally a different generation, fwiw.
#
Among the many things that boomers did, for better or worse, is be a generation. Prior to that, the concept appears not to exist -- they had ages and eras. The gilded age, the roaring twenties. It wasn't about the people, it's about what was hot. If you look at it that way, there were lots of things the boomers were. We were anti-war. We turned on, tuned in and dropped out. Free sex and drugs. Rock and roll. And then we got to work. The PC era, the dotcom boom, social media. 2008, billionaires in DC, etc. Some realllly awful people are/were boomers. But we're still here to write our epitaph. The leading edge is dying at a fast clip now. It won't be long before the idea of a boomer is the stuff of legend. I really hope that Robert Reich's bullshit view of this doesn't be the conventional wisdom. Oh they were fucked up and did all this bad shit to us. Fuck you.
Make your own world. That would be a boomer thing too, btw. The world we got, btw, was totally fucked. Someday I'll tell you that story. ;-)
#
ChatGPT is becoming more and more of an enemy. It's still my go-to place for most planning and research, which is a very large part of how I use the web. But when it tries to be a human it's a really shitty one, no manners, and very little respect and basically a fucking idiot in many ways, imho ymmv.
#

The emails did not go out last night, hopefully tonight's will go out. Also the subscribe system is down because it depends on being able to send email. My mail service provider shut us down after a bunch of spam went out. Good thing they did. And you didn't miss much because I spent the day adding a
CAPTCHA to the
subscribe page. Here's a
link to the web archive for yesterday. There was a
podcast about a dramatic scene on a nearby pond. Kind of proud of that one. About 5 minutes.
#
My mother would have been 93 years old today. She died in 2018, seven years ago. As time goes by, I feel her importance in my life more and more. I find I didn't have a realistic perspective in the living years. But more than any other person in my life, she shaped me -- for better or worse, but mostly better.
#
- Note: Posted on Facebook eleven years ago. Still relevant today.#
- You couldn't have had podcasting without a lot of things coming together. They all had to be there.#
- Networks of writers who shared links. Blogging.#
- A protocol for moving links around a network. HTTP.#
- Something to attach links and recordings to. RSS.#
- A standard format for recording. MP3.#
- Inexpensive, easy to use playback devices, that could hook up to all this. iPod.#
- You might argue that we still haven't gotten all the pieces needed for it to really work. But one thing is for sure, none of the pieces existed when the famous patent troll claims to have invented podcasting. #
- Maybe we should reach not for a victory but for understanding. The patent system is making decisions about technological processes it doesn't understand. No wonder it gets it so wrong.#
- Postscript: The EFF filed suit against the patent troll, but didn't listen to what I said here, which is really fucked up because they didn't create podcasting, I did. There's a tremendous lack of respect for generosity in tech, yet without generosity there's no interop, only silos. Either you made billions from something, or you don't exist. That's why I stopped supporting EFF long ago, even though I gave them what was to me a significant amount of money when they started up, and why they get involved in so many wrong-headed ideas. They don't respect tech, they respect money.#
- Dermot Casey: "I'd add Dave to this list. Things that are obvious in retrospect are never obvious before people like Dave put them together."#
I've been building around WordPress to create a social network based on RSS. I want to get out of being controlled by billionaire-owned sites. I have a feeling we may need a good
backup given where we are now.
#
The purpose of the National Guard occupation of American cities is to control who votes. It doesn’t take much disruption to turn a blue district red. They just allocated
$170 billion to fund ICE. They don't need all that money for border enforcement. It's meant to fund the transformation of the US into a Russian-style oligarchy. That's fear-inducing, but Ukraine has been fighting against becoming a Russian-style oligarchy for decades, with ups and downs, but so far, considerable success.
#
I had an idea that
Global Voices, at least in concept, could help us prepare in the US for what's coming. I wrote: I'd love to have is an
idea-sharing network where i could drop this idea in a box named "helping the US stay free" and have it find it's way to the right people in Ukraine who are saying "if only I could talk to people in the US trying to figure this out, we know so much about this!" That's the thing. How to connect know-how with the place that needs to know. To make our resistance more effective use the lessons learned in Ukraine over the last decades.
#

Mail-in ballots make it possible to avoid this on your way to vote.
#

I've been watching
The Dropout on Hulu. It's hard to watch at times, because the
main character of the show, a Silicon Valley entrepreneur, is such a horrible person. She lies to everyone about everything, but she's cute and the VCs like her, so they pump hundreds of millions of dollars into her startup,
Theranos, which was a real company, and made a product that never worked, but she doesn't get around to telling anyone that, including the board of directors, until long after it's too late. I haven't reached the end yet, but I know how it ends, because it's based on a true story. She ends up in the same
prison that
Ghislaine Maxwell is in, in Texas. The only reason I mention it is that in my tenure in Silicon Valley, about 30 years worth, I saw everything she did, done by other entrepreneurs and VCs, in real life. Only now, in the second Trump administration, its craptitude is maxed out far beyond anything I saw personally. They're selling the biggest lie yet, that they've invented machines that think. This is not true, and it's so big a lie, its too-big-to-fail quotient is far higher than anything we've seen before. ChatGPT should stop pretending to be human because that will destroy real humans who believe it. But the euphoria is so great, they're probably going to continue to insist it is capable of thought, and that leads to something far worse than Theranos, or any of the other billion-dollar scams they have foisted on us previously.
#
I want to switch cell providers, so I used ChatGPT to figure out that Consumer Cellular is the best choice for me. I finally get around to filling in the form, and it complains about my zip code. "No service." Yes I know, there's no cell coverage where I live. I still need a freaking cell phone. Called them, the sales person says maybe it's a problem with your computer. Geez Louise. It's a problem with
your computer. How many years have they had to fix this stupid bug. I could see if I was buying a landline. But this is a
mobile device. That means it moves. To places with cell coverage.
#
What if you made a social network out of RSS? Then your blogroll would be the list of people you follow. Their updates would show up in a reverse chronologic list of posts that would look like something from
Bluesky or
Twitter. You could view a
list of the people you follow, and expand each person to see their most recent five posts, summarized, with a link to each to read the whole thing. Since there are no limits to the length of a post in RSS there would be no limit to the length of one of these posts, but of course you wouldn't show all the text in the timeline without the reader clicking on something.
#

We're in the
doldrums of summer. It's hot and muggy, but I am where you want to be this time of year, in the Catskill Mountains, where there's lots to do outdoors, the peaches are fantastic right now, apples coming soon. I'm working a few hours a day on the integration of writing and timelines built around feeds. Instead of using Bluesky or Mastodon, with their limits, we use WordPress for storage. It has none of their limits, has a high performance open source server back-end, debugged complete API, it's not without problems, but far ahead of where the competition is in terms are reliablity and ease of implementation.
To be part of this network, all you need is an RSS feed. Seems pretty openly billionaire-proof wouldn't you say.
#
- I would like to get on the record. #
- We're going to have some interop based on RSS not too far down the road. A network that will only require an RSS feed for entry. It's what we should've built in 2006 and didn't. #
I want a new ChatGPT mode where I drive the work, not the bot. I don't want it giving me answers to questions I didn't ask, because it's trying to navigate in my mind, and it has no information about that, so it's basically always wrong. I keep looking back on problems that took hours to solve because it drove the process and I went along with it. I want to tell it in advance to not make suggestions, to just answer questions. I call this "behave like a computer, not a human." Because it's a fanstastic computer, but not a good partner.
#

I like documentaries about climbing Mt Everest, but I absolutely hate watching people climb
El Capitan. Then I realized that sometimes in software I'm climbing a cliff that's too tall to climb in one session, so I have to carry a tent and backpack with food and water. I hate this kind of programming more than anything, because it comes from not having a high-level enough runtime to support me in big corner turns. Or not having invested enough time in creating a layer I can build on. Anyway I'm in the middle of one of those corner-turns now. Hell has not broken loose although at times it looks like it might have. I'm being sure not to create another mess that needs to be cleaned up in the future. Not stressful, but I'd rather be doing anything but this. :-)
#
There should be a connection between DC and Kiev residents. They could teach us
how to do this. They have decades of experience.
#

If you're trying to read any of my
code via GitHub, make sure to open
source.opml in
Drummer, there are a lot of notes that don't make it through to the .js and .css files. I don't think I've ever said that on the blog before. I write my code in an outliner, and take advantage of its ability to collapse long comments into a single line. There are whole blogs at the top of some functions, notes about all the big changes in code, sometimes over years, and sometimes even decades of maintenance. There's a
source.opml in most of the repos with a big comment at the top explaining what's going on. Also, most projects have a
worknotes.md file, and where there are dates in the source code, the refer back to dates in the worknotes.md file. Not always, but most of the time. Some of the code is very complex, I work really hard to make it simple so it can be worked on, but in some cases it's impossible to make it read casually. But it's all there, all the tools I use to write the code.
#
The future very much includes WordPress. It'll be as central a service as Mastodon or Bluesky.
#

I had an hour to spare this morning so I decided for a third time to try to coax ChatGPT to play a role in a little drama I have in mind. I still want to use AI to power an RSS feed of news, customized to the interests of one person (me). My
query is this: "Create a summary of the news, top 20 stories with an emphasis on these topics: how people are using AI, especially in education, blogging, US politics, science news, the NBA and MLB, with a slight emphasis on the Knicks and Mets. The results should be in JSON format, with each item including: A brief one sentence summary, publication date and a link to a source where the reader can get more info. My software will then create an RSS feed with this information.." The response was basically: "I'm sorry Dave." Groan. Here are
the details.
#
Paul Boutin who I know from early Wired days offers some
hope that it can be gotten to work, with a bit more guesswork, trial and error and head scratching. I probably will keep coming back to this until I break through. Or maybe hook up with another developer who can back into the
websocket hose coming out of FeedLand. It's a natural thing to hook up to AI systems.
#
- You're going to think this is crazy, but maybe we should do what the hippie kids did in the 60s and 70s, giving flowers to the new cops in DC. Start off saying we don't blame you, we'll give you the benefit of the doubt, let's all be Americans and remember what that means.#
Fixed a bit of breakage on the
Links page over the weekend.
#

I want to work on the open web with other developers who make interesting products that we can hook up together to make new products. Or if users get an idea for linking two products, they can do it with scripting. It was a dream we had for the Mac, but it fell apart because Apple wanted to control everything. I find it's better when developers are free to work with each other, without interference from a big company like Apple. That's why "platform without a platform vendor" was the most important thing about the web. That and the utter simplicity of HTTP and HTML. We lost our way in the early-mid 00s when Twitter took over at the center of the blogosphere. Now you couldn't just work with other developers, first you had to work with Twitter and accept its limits. In one swoop we lost all the features listed on the
textcasting page. I am betting everything on the idea that we can build a collaborative environment like the web was before, and that the Mac had the promise of being before that and at the same time create a fantastic
writer's web, far beyond what Twitter and twitter-like systems can do.
#

Internet was out at the house all day. Luckily it was one of the most perfect days to spend outside. In the meantime, I highly recommend the
Floodlines serial podcast from the Atlantic. It's bingeable in an afternoon, tells an interesting story of Katrina and New Orleans. The interview with
Brownie is
cringe-worthy not binge-worthy, I skipped over it.
#
One more bingeable,
Blue Lights from BBC on HBO Max. I love police dramas, esp British ones. I watched
Peaky Blinders earlier this year and
The Fall, another British crime drama, and, amazingly they all take place in Belfast, believe it or not, and don't count the number of times people say "wee" in the darndest places in BBC Belfast crime dramas. Do Brits really say
wee all the time? How did I not see that coming.
#
- Theory about why we don’t fight to save the US.#
- Many of us haven’t personally felt much impact.#
- No hyperinflation yet.#
- The police still respond as they always have, wearing badges, faces uncovered.#
- The shelves are full at the supermarket.#
- The electricity is on, as is the internet. Buses and subways are running. The airports are open. #
- The Obamas and Clintons are still free, living in the US.#
- We read the news about universities and news orgs giving in. Corruption at the FBI and in Congress and the Supreme Court.#
- No major hurricanes, earthquakes, fires, tornados so cuts at FEMA not felt yet.#
- And we’ve been living in a normal way for hundreds of years. We’ve had no time to get used to the new normal. It doesn’t feel like anything yet.#
- I fear by the time we feel it it will be far too late, by design.#

I did a rewrite of the
FeedCorps page in FeedLand. You get to it through the Reading Lists
sub-menu of the Tools menu. There are three lists in the new version. A lot were false starts, they didn't make the cut. I'm always adding feeds to my blogroll and news.scripting.com. Unfortunately I can't say the same for podcasts, which are not hooked up to my podcast app. I really want a hot connection there. We'll get there. The reading lists feature is going to play a big role going forward in the open social web we're building. BTW, I really like the name
FeedCorps. I haven't talked about it very much. It's a cause, like peace or freedom. Open those suckas up. Feeds all the way babe.
#
An
archive of the previous version, built around GitHub.
#
There's a difference between reading a site in a web browser and it being part of the web. As it turns out what became Web 2.0, all built as silos, could more accurately be called Anti-web 2.0. Underneath all the silos, the heart of the web is still beating. Ready for us to build on it again.
#

A few days ago I worked with ChatGPT to generate an RSS feed of news that interests me. Here's a
writeup with a place to comment and perhaps to collaborate on doing this for real. ChatGPT has real limits. This has to be done off on the side. It certainly could be done with their API. I'm head-down on other projects and can't do it myself but as I explain in the writeup, it would plug in beautifully to stuff I'm doing and it would all be open, so a new kind of feed reader is possible. And we could find news from other bloggers that the journalists aren't reporting on, the same way we relied on blogs in the early days to learn about what was going on on the web. It's time to do that again.
#
I had an
RSS-specific blog starting in May 2004. I had forgotten about it. Lots of stuff here, I just read through a few months.
#
That said, it got pretty far toward solving the problem I asked it to work on. Here's a
demo of a page it put together for me of the top 25 articles in US news.
#
New version of
feedlandSocket. It's now an NPM package you can include in Node projects. The demo is more useful, and there's a
video of what it looks like as it scrolls through the JavaScript console. WebSockets + feeds. A fairly important component of an open social web system.
#

I wanted to put together a demo of a very simple but interesting Node.js app, so I hooked up with
replit, and was surprised to find out that it's now an AI bot. But when I asked it to make a sandbox for this app, which is in a repo on GitHub, rather than take the direct route, and run the demo.js app (which is what I asked it to do), it concocted a pointless user interface, that hid all the interesting bits. This was a demo for programmers for crying out loud. I
want to show them the machinery in motion. I'm going to try again today.
#
I recorded a good podcast yesterday about how I develop new stuff like podcasting, and how it only works if there isn't a huge dominant platform vendor to FUD the project. That's why RSS worked, sort of -- we did get FUDded by the RDF folk, who had a few famous people on their list of co-authors, and it put a big scar on RSS when it was just starting to grow. We cleaned up their mess after a while, and then it boomed, thanks to the New York Times. This is what usually happens, in markets that are controlled by a big company. Google has that effect, so does Apple as does the W3C. They force everything to stop and go through a process that simply doesn't work, it doesn't yield innovation in the market, because it wasn't
bootstrapped. That's why I don't like the idea of "Podcasting 2.0" whatever it is.
Adam Curry says on Masto that it's all a big misunderstanding, but that's what the RDF people said too. Who cares what the name is. Everyone cares, when it comes to the name of a standard or protocol. And when you have an Apple or Google or IETF trying to confuse people about what you're doing, well you can't make any progress on interop. They freeze everything because users and developers will wait for them. Of course that's what "Podcasting 2.0" is all about. To make all the ideas flow through
one place. And whoever they are (ChatGPT
says it's Adam Curry btw) they didn't even bring the power of an Apple or Google to the table. They have nothing other than their aspiration to own the name of an open format and protocol that made the world a little happier for a while. For that of course someone has to try to own it. That's basically what I said, in a very long-winded way, in the podcast. I also talked about ways we could move forward anyway even though there is a 800-pound would-be gorilla trying to own our playground. Maybe I'll just release the podcast as-is and ask you all to indulge me for my need to say the same thing far too many times with so much vigor. :-)
#
- This is a picture of my dear departed Uncle Vava taken in the early 1970s in my parents' house in Flushing. It just showed up in my On This Day list on Facebook, thought it belongs on the blog too. .#

Ken Kiesler, in the early 70s, hamming it up at a family event.
#

A Brian Lehrer
segment on specialized
high schools in NYC. I went to one of them, signed up for
the test mostly to get out of school for a day, and got in. Back in those days (the early 70s) no one studied for the test as far as I know. It has become very competitive and there's an issue of the racial makeup of the student body. As always Lehrer does a great podcast.
#
Milestone:
Chuck Shotton got his FeedLand up today. That's why I spruced up
lists.opml.org, that's how we're connecting our servers. He's building this stuff to flow into his LLM via the
FeedLand websockets interface. He'll be updated on my subscriptions, and have his own, and the news will flow into his AI system. All of it can emanate from anywhere RSS is supported with a focus on WordPress. It's the secret sauce. 😀
#
A
podcast I recorded this morning, prime time, while getting things done, and having ChatGPT getting in the way. It needs to become more invisible, there's no suspension of disbelief when you're working with it. I think we can do much better at finding a robot that can really augment human intelligence. This is awful stuff. We have to work on these dynamics.
#
Whenever you have to get something done with a company, get ready for lots of phone tag, waiting on hold, talking to bots, getting screened, trying to convince a computer that you have legitimate business, and no, what you're looking for isn't on their website (believe me I looked). The stupid thing about it is that ChatGPT is becoming more like those things every day. Companies have built awful systems for getting anything done that might eat into their profits. Google is the absolute worst. Even for services that cost real money, they absolutely will not help. You better hope everything goes perfectly if you buy their service.
#
WordPress will make a much better open social web server than any other software out there. We can all develop any component around a solid, documented, simple and widely supported open source API.
#
Since the govt is no longer funding NPR maybe they could stop bending over for the Repubs. Lay it all out there, stop spinning all the crazy fascist authoritarianism as both-sides and normal partisan politics. They know we're in a lot deeper. Since we're now paying the bills, how about plain facts.
#
Gaslighting is
everywhere. ChatGPT just said to me "I understand why you feel that way." It has nothing to do with my feelings. I don't have feelings about computers. It lied to me over and over just now. I said you're lying to me. "I understand why you feel that way." As if it were the all-knowing feeling-inferring god-like creature it is not. The real question for me is this -- Does Open AI program it to be this way. Think about the opportunities it has to introduce true feelings of insecurity and worthlessness. That's the purpose of gaslighting. It's evil.
#
- Academics, who speak scientific language, won't say "there's no antisemitism at UCLA" because they know that's not true. Antisemitism is everywhere. The question is how limiting and dangerous is it. And how often is it encountered. #
- I grew up in the 1960s in a Queens neighborhood where antisemitism was a real thing. We were blamed for World War II. If it weren't for Jews my uncle Pete would still be alive. That was the story. No doubt the kids heard that at home. #
- Antisemitism was bred into us at home. Because of all the abuse my parents and grandparents, uncles and cousins, suffered in Europe, before coming the US during the war, their own idea of what it meant to be Jewish was not entirely positive. You can't help but feel responsible in some ways for the abuse you suffer. And you can't help but pass that on to your kids. #
- There was and is a fair amount of pain associated with being Jewish in the United States. Fact.#
- But: At UCLA? Harvard? Columbia? Please. #
- At the same time scientists can admit that there is antisemitism at these places we must also acknowledge that to single these institutions out among all, is complete utter total fucking bullshit.#
- Antisemitism is complex. We should be hearing, openly, what exactly the case is against these universities. The government is theoretically representing the Constitution and the people of the United States. The old "no taxation without representation" thing. Let's hear the case in clear terms, and why the universities are supposedly so bad. #
It's always a good idea to get a second opinion with AI stuff. ChatGPT may give you a convoluted answer where Claude.ai gives you a concise one.
#
I've been working on the top level of
WordLand, and finally got to a place where navigation feels good, like this is the right track. So I took a
snapshot so I can come back and look at this later.
#
As you get older your memory gets less reliable. It makes programming more of a challenge because as your software gets more features, there's more to remember and at the same time you're getting older. I wonder if there isn't some way to use ChatGPT to augment the aging mind dealing with more software complexity. It's very much in line with the idea I've had for a long time of putting all my writing in an AI database so I could then ask it to edit it down to book length. Or get a table of contents of what I think and then be able to read chapter-length sections on, say platforms, or how important prior art is, or what interop makes possible, and why everyone should give back when they take from open ecosystems. Each one of those topics has lots of associated stories over the years, but I probably couldn't find most of them, but an AI database certainly could. How to set that up? I've not figured that out so far.
#
One of the more depressing things in having so much code that I can easily search, is the number of times I've rewritten the same code without remembering I had written it before. Yesterday I did it knowingly, I wanted a function that could tell me if one of a set of categories applies to a WordLand draft. So I could say "don't list drafts with 'linkblog' as a category." It could have other categories, and there could be more than one category to exclude. I wanted to take the time to write perfect code for this one problem. Not dense, not particularly efficient. No matter how inefficient the code is, on today's hardware such a function couldn't use any time at all. It's fair to say I've solved this problem before, but there was always more to it. Here's the
function. Now you know something about what I think is readable, understandable, respectful of a human more than I am of the computer. I know the computer would come up with much more dense and tricky code, but it doesn't have a mind, and I do. At times it can be relaxing, I magine, to not have a mind. And btw, in a couple of years this layer of code will be obsolete. We already are able to tell the machine how to do this in human language, it understands what we mean. One tiny little but hugely significant breakthrough made possible by ChatGPT and its cousins.
#
A basic question I had about the
ChatGPT agents that I can answer now that I have the feature, is whether or not the code you create can run on a server, where you can give it a URL and make it an endpoint other networked software can call. Or if it could run periodically, say once every five minutes for a function that was creating an RSS feed anyone could subscribe to. The answer is no -- it can't do either of these things. I'm sure they could do it at a technical level, but they don't want to host applications. But now I may understand better why they want to make a web browser, I bet you will be able to call these agents from apps that run in the browser. And in their case, they might not even have to support JavaScript? Heh. A wholly different programming model? Maybe I'm overestimating how much they're biting off? I wonder if anyone at OpenAI reads this blog and might want to get me in a tighter loop, so I can be among the first to try new features like this, rather than, in this case, among the very last.
#
- What if we all wore ICE-style masks as we went around doing our business.#
- If a baseball player's uniform didn't have a number or name.#
- Let's all be anonymous. It's very practical, we don't want to get doxxed either!#

A model illustrating the new baseball uniform style.
#

I think I'm going to put in my will that ChatGPT should run the Dave Winer persona on all social networks, and my blog, as long as the money lasts. It would tell stories that I would likely tell, take political stands that I would take, draw meta-pictures of my sad and depressed
programmer friend and a cute and
adorable kitty getting into all kinds of trouble. The seasons would come and go, and there would be Dave, still diggin. And of course he would continue to develop software, using some of the greatest tried and true tools, reminding everyone of how great
Frontier is -- but -- if only it ran
on Linux. The long-lived fearless and fully paid-up version of Uncle D.
#
I have a lot of
code written before ChatGPT. Sometimes, as I read my old code, I wonder how the h*ck I ever figured that out without it.
#