The idea was to get my photos from the latest Lotus Festival up right after the three-day event ended on Sunday the 4th. I had too many other things to do, so a week went by. But at least my shots of the last two performances are up. This one is for Nikki D & Sisters of Thunder, who describe their show as “sacred steel gospel and blues.” Fun group. Singing and musicianship are first-rate. Great personalities. Very charismatic. Dancing is required.

This one is for Gadan, which does “Irish trad and bluegrass with the soul of Celtic and Appalachian roots music – all spiced with unmistakable Italian flair!” Here’s that photo album:

Another great band. Loads of fun. Great music. Can’t sit to them either.

Here’s another thing. All the photos in both albums are Creative Commons licensed CC-BY-4.0: there for anyone to use, requiring only photo credit.

I invite both bands, the Lotus Festival folks, and any member of Bloomington’s news commons to have at them as well.

Here’s more about Lotus. It’s an amazing event. If you like great music from everywhere, you’ll love the show. It’ll be back next October.

I'm in Chicago for the Marathon and our son's birthday (he's running tomorrow). Also hanging with relatives and enjoying the city, which always feels to me like a giant Boston. (Color me wrong, it's okay.)

Meaning it was fully yours

Steven Levy: I’m Still Convinced the iPod Was the Perfect Gadget—Apple’s original music player got many things right. Chief among them: It didn’t connect to the internet.

AI isn’t just a “surf’s up” moment. It’s a tsunami. You have to surf that tsunami, just to keep from drowning. 

Using your time. Your calendar is your surfboard.

What’s your best beach for riding that calendar?

Well, right now there are countless conferences with “Identity,” “AI,” or “Agentic” in their titles. Yes, they’re beaches. You can ride there.

But where will you get the most done? Where can you write the agenda, and work with other people dealing with the same problems or pursuing the same opportunities? Real people doing real work. People who can help.

Really, do you want to hear yet another CEO blather about what their VCs and marketing people want them to say? 

Or do you want to get work done?

IIW was made for getting things done. It has been a wide beach for surfing big tech waves since 2005, twice a year at the Computer History Museum in Silicon Valley. The next one is our 43rd. It’s on November 3rd to 6th, less than a month from now.

We immodestly believe that IIW is the most leveraged conference in the world. Two reasons:

1. Our focus (without limits) is on identity, with lots of real-world results. OAuth, OpenID, passkeys, self-sovereign identity (SSI), decentralized identifiers (DIDs) UMA, SSI, VRM, and Personal AI—to name a few—would not be the same without countless forward-moving conversations and work at IIWs.
2. What we don’t have. No keynotes. No panels. No agenda other than what participants choose.

And that’s you. IIW is what you make of it.

So join us. Register here.

You’ll leave wet but a lot more fit.

Closer to homes

Tornado Alley moves east. Here’s one I recorded live on my phone in February here in Bloomington, Indiana. Here is the trench of destruction dug by a later tornado that went through thick woodlands about twelve miles north of here.

Didn’t know there was one, but yeah

Chick-fil-A takes a stand against fast-food drive-thru AI trend.

Maybe

Is doomscrolling doomed?

Always a bad sign

NPR has a new privacy policy. Specifics.

Here’s a PageXray of the policy page:

That’s what it says at MoonPhase.today

Specifically, 26%.

I’ll consider them unreal if they’re not at IIW.

The UOR Foundation has plans to… Well, I can’t copy and paste the text, so here’s a screengrab:

I’ll say not. Quite.

AM I? | A Documentary About AI Consciousness.

Ever notice the groovy ditches in tidal swampland?

It’s called “grid ditching,” and is explained here:

Grid Ditching

The grid ditch system still evident on our salt marshes today, were dug by hand between 1928 and 1934. The primary purpose of this era of ditching was to put as many people to work as possible, as this was the time of the great depression. No entomological studies were conducted in conjunction with this ditching effort; mosquito control was a secondary consideration at best.

However mosquito control was achieved by default as practically every square inch of marsh was drained by the extensive project. Some engineering studies were done to determine where and at what intervals ditches were dug. Ditches were dug in straight rows by hand with sod saws and two man shovels. In 1934, at the peak of this ditching effort, over 11,000 men were employed digging ditches and when completed nearly 3,000 linear miles of salt marsh ditch were dug in Massachusetts alone.

Virtually all salt marsh in New England was ditched with the exception of one marsh in Rhode Island. Later in the late 1940s and early 1950s soldiers returned home from World War II. Housing shortages were a big problem in the more populated areas particularly in and around Boston. A generation of young families, eager to get their lives back on track migrated to the north shore of Massachusetts to start new lives.

This migration coincided with the degradation of the grid ditch system created in the 1930s. These ditches had not been maintained and now produced far more mosquitoes then they had initially eliminated. By many accounts it was so bad some considered the area to be almost uninhabitable. A few local programs were established to try to reopen the ditches but it was impossible to duplicate the labor force that had originally created the ditches.

In 1958, a grass roots effort, fueled by public demand for relief resulted in legislation establishing the Essex County Mosquito Control Project. For reasons unknown the project was not formally funded until 1965. Equipment was purchased and a major effort was launched to reclaim salt marsh ditches.

Salt Marsh Ditch Maintenance in Northeast Massachusetts

In the late 1970s, Walter Montgomery was an equipment operator for what was then, the Essex County Mosquito Control Project, ECMCP. Montgomery’s primary duty was to maintain the extensive salt marsh grid ditch system, excavated for the most part, between 1928 and 1934.

Montgomery recalls using an implement known as a scavel plow; this was a large wedge shaped device mounted under a wing plow and could be attached to the front of a tractor or sometimes towed behind. A scavel plow wedge was basically constructed to the original ditch dimension. The wedge would be dropped into the ditch and the tractor either pushed or pulled it along. As the wedge peeled spoil out of the ditch the wing plow would roll the spoil into furrows approximately six feet wide on both sides of the ditch. These furrows of spoil were then either run over to flatten them or plowed off the marsh.

On a productive day Montgomery recalls completing two or more miles of ditch maintenance but even at that rate maintenance of hundreds of linear miles of ditch was an endless endeavor. It was Montgomery’s experience that freshly maintained ditches were really only effective for about two years before requiring additional maintenance.

Typically ditches would become blocked on the high marsh and previously drained salt pannes would often reestablish. Montgomery observed that the open water areas of these pannes or ponds didn’t have mosquito larvae but the grassy sheltered areas around the edges or isolated depressions adjacent to the ponds, supported mosquito larvae.

Montgomery’s observations further supported his belief that continued maintenance of the grid ditch system was not productive and furthermore there had to be a better way to manage salt marsh mosquito populations.

That is from a .pdf titled MASSACHUSETTS MOSQUITO CONTROL OPEN MARSH WATER MANAGEMENT STANDARDS MAY 2010. It is worth continuing to read, if mosquito control is your jam.

Alas, as you may gather by now, everything is my jam.

Seems Flickr is having an outage of some kind:

 

If  you don’t, you’re a human AI

Test: See if you don’t laugh at something as you scroll down through this.

Am I alone in finding it annoying?

Does anybody want, or use, the “workspace” that shows up, whether you want it or not, every time you open a Zoom session?

Getting less faint

Wall Street Journal: The Global Bond Rout Is Getting Messy—Unwinding popular hedge fund trades helped drive U.S. Treasury yields lower, but there is also ‘a faint smell of a crisis in the making’

Overheard

“That was like hearing a mirror.”

How advertising ends and something you like less begins

Jamie Smith: Meta turning its money-printing machine (ads) into a ‘customer engagement machine’ – and it should be 100x bigger.

Theory

We can’t reconcile the Hippocratic Oath and executions.

A billion rights don’t make a wrong

Except for a few books and thousands of long-since-tossed magazines and newspapers, all my writing is on the Web.

Some of that died long ago. For example, David Bunnell (four days older than me, and for whom I was often mistaken) did nothing (to my knowledge*) to save the archives of Upside, which contained an enormous sum of early Net and Web history, and to which I contributed a single essay, not long after The Cluetrain Manifesto came out.

But lots more is still up. Alas, Google now considers them dangerous, because they are known to the world by the Web’s founding protocol—http—and not by its encrypted version: https. So Google calls all the millions (billions?) of http sites dangerous and scares visitors away. One example is the Linux Journal page linked to by the image above.

In Let me say this: Fuck Google, Dave gets this right. His explanation here is required reading for anyone who cares about history and archives. Bottom line: Google’s not secure message means this: “Google tried to take control of the open web and this site said no.”

Grayed matter

Also gone are all the digital archives of Fast Company, Industry Standard, Business 2.0, and Red Herring, which competed with Upside in the early days of the Web. Pieces written by David Weinberger and Chris Locke, two of Cluetrain‘s co-authors, are also erased from the Web’s whiteboard.

I agree

Dylan Tweeney says  AI is going to increase demand for human writers.

OMGF

This was bad.

Warning: Severe Public Service Wolf Crying

The Monroe County Alert System just ran their sirens all over town for more than a minute. They do this once a month at noon. Do they need to? Do they also need to warn that there will be a “severe thunderstorm” when what’s coming is typical summer afternoon thundershower? Or warn that “severe flooding” might be coming from the same? Yes, I appreciate warnings about approaching tornadoes. Thanks to that (and all the weather apps on my phone), I was able to shoot some tornado video back in February. (You get to hear the sirens on that one.) But I’m close to canceling the alerts, because they come too often and not for real emergencies.

_________

*As I recall, he wanted the whole thing gone when it went bankrupt. But I might have that wrong, and I welcome correction. He was a good guy, and a born journalist and publisher. I liked him, and he passed way too young.

In wasted dollars

Our species began to get civilized when it invented clothing: the original privacy tech. But that was in the natural world. In the digital one, we are still naked, and privacy is just a promise you get from “consent” (cookie notice) agreements and settings. It’s a fail. Example: the GDPR Privacy Monitor examined 97,000 websites and found that—

• 55% displayed no consent (cookie choice) banner
• 80.4% continued tracking after the user clicked reject
• 68% activate third-party tracking before the user has given consent
• 66.6% set cookies before consent

And the consent management platform (CMP) business weighs in at $4.1 billion.

We now return to hiss

WMEX/1510, which in its heyday was Boston’s main top 40 music station, has signed off for a final time. The station had a cursed transmitter history you can read about at the opening link. When I lived in Arlington, Mass from 2007 to 2013, the transmitter was nearby in Belmont, using four towers in a parking lot in an industrial part of town. It was 50,000 watts at the time. Killer signal, but a doomed site. I shot it in 2008. Here’s the photo album. In the late Teens, after a period of silence, it moved to the 1260 AM site (built for what was then WNAC) on a tidal swamp south of town. Then only 10,000 watts and just 100 watts at night, it operated as an oldies station. I shot that site too, from an airplane on approach to Logan in 2011.

What we’re watching is the slo-mo heart failure of the AM broadcast band. Knowing that, I like to document what was there before it’s gone.

In case there is a reason

This piece (first of three in a series) about Zoom’ privacy practices was written more than six years ago, and I haven’t revisited the topic since then. But I thought it might be worth bringing up.

You can deal with the identity piece at IIW

I just learned that Reverse Alignment is a thing. It addresses—

Large, coordinated investments in the human and institutional side of the AI transformation. They span identity, privacy, markets, governance, work, and knowledge. They share an architecture, and they share a method. No single sector can deliver any one of them alone.

We found a clubhouse!

Reason: Kids Are Using NPR Podcast Comments as Secret Group Chats.

AI shit gets so weird.

For example, the fake golfer Grace (aka Gracie) Brooks appeared in the midst of my Facebook doomscrolling (above) to say something to me (scrolled across her boobage) about “an older guy” watching her. Never saw her before, or cared to see her. But I am curious about “her” business model. So, after getting that screen grab, I went off to research her fake ass.

What I (and my AI employees, which can search faster and wider) have found so far:

• Multiple newly numbered Facebook accounts use the same “Grace Brooks” identity. The fuck:
  • 61590279580369 — Grace Brooks
    • Profile
    • This is one I saw. One reel says: “I have a question for you old men… If I texted you first, would you actually reply? … follow me and say your name.”
    • Example reel
  • 61590736615465 — Grace Brooks
    • Profile
    • This separate account posted a nearly identical script: “I have a question for you old men… If I texted you first…”
    • Example reel
    • Another reel asks “old men” to follow and provide their names. www.facebook.com
  • 61591441983335 — was Grace Brooks, now Emily Bennett
    • Profile (Later: now blank)
    • Earlier search indexing labeled reels from this account “Grace Brooks” and described the woman as a golf influencer addressing “old men.” It now appears in current indexing as Emily Bennett, still asking “old guys” to watch and follow her.
    • A current Emily Bennett reel. (Not much later, it’s gone.)
• Multiple accounts are on Instagram too:
  • @graciebrooks07 — the account I first found when I started digging. Has about 45,000 followers and 90 posts.
  • @graceeegf — another “Grace Brooks”: about 7,900 followers, 13 following, and 53 posts.
  • As of this evening (29 September 2026), both are still there
• The second account uses the same material and language:
  • “I have a question for old guys…” on @graceeegf.
  • “If you follow me and send me this reel I’ll send you a gift in your DMs” on @graceeegf.
  • “Will you be honest?” on @graceeegf.
  • “Answer honestly?” on @graceeegf.
• Instagram’s indexing repeatedly connects the two accounts on the same result pages. That makes @graceeegf a confirmed duplicate or companion account. I dunno, cuz I’m still new to this shit. Here are some other accounts operating in the same apparent cluster:
  • @graceeetx0 (click on her oopsiebio and you get what looks like a soft porn site)
  • @reedlenaaa (different “girl” same golf swing)
  • @avaagolfs (same, but only in a golf cart)
  • @avassecrets (bio goes here to a porny come-on)
  • @graceeetx0 (same old Gracie)
• There is no independent biography, established social presence (other than these on Facebook and Instagram), golf history, or other evidence that “Grace Brooks” exists in the natural world.

As for her unreality, here are the tells:

• Too good-looking. Call it statistical perfection: symmetrical features, flawless teeth and skin (with slight humanizing imperfections, such as Grace’s freckles and tiny lines on her face), perfect hair, improbably high boob/waist ratio, perfect makeup (or a perfect absence of it). In sum, a maximized perfection of improbabilities. (I asked ChatGPT to find similarly attractive real-life female athletes. In declining order, it gave me Alica Schmidt, Jutta Leerdam, Claire Hogle, and Romee Strijd, none familiar to me. Look ’em up. No ‘fence, but none look as perfected as “Grace.”
• Perfect lighting. As an inveterate photographer, I know how hard it is to get lighting that right.
• Inconsistent fake backgrounds. (Is that driving range the same every time?)
• Modular gestures. “She” seems to have a limited range of head tilts, direct looks, smiles, arm movements, golf swings, and flips of her skirt for a peek at her perfect butt with its pink panties.
• Identity without history. Does any athlete as perfected-looking as this one exist in the natural world? Of course not.

But why are the creeps that make her (actually, it, and them) trolling geezers on Facebook? Well, clearly this is a funnel-top operation. For what? I imagine one or more of these might be down in the vortex:

1. Paid adult content, or referral
2. Pay-to-chat
3. Romance fraud (such as the FTC cares about)
4. Fake investment (typically in cryptocurrency)
5. Phishing
6. Malware insertion
7. Affiliate traffic pumping
8. Growing an affiliate account for someone to sell off

I vote for #1, but whichever it is, “Grace” and her friends are all bait at the top of a funnel.

Real hard forks

Hmm… NiemanLab: NPR, the quintessential audio news brand, adapts to a video-first future. Specifically, “NPR … landed Machine Gods, the new video-first podcast from veteran tech journalists Casey Newton and Kevin Roose.”

I subscribed to Casey and Kevin’s old podcast, Hard Fork, and I’ll subscribe to Machine Gods too. But I doubt I’ll watch it—Just like I don’t watch the Netflix feeds of The Ringer podcasts… or much of anything but the road when I’m driving, my tools and plants when I’m gardening, the scenery when I’m walking around, and my espresso machine and its components when I’m making coffee in the morning. Those are places where I do most of my podcast listening. If I’m at my computer or watching my TV, there are many things I’d rather see than a podcast.

But,,,,, There seems to be a budget of time that people in modern civilization devote to staring at glowing rectangles: some number of hours per day. TV got us into that, starting around 1950. Some of that appetite spread over onto computer screens starting in he 1980s. Smartphones and tablets took some of that over starting in the late ’00s. Now that we have ambient connectivity and rectangles in our pockets, the division of that budget of hours is divided between—

1. What we watch for entertainment on TV (mostly on-demand streaming)
2. What we watch during work on our computing devices (including news and business-related stuff)
3. Gaming and other non-work stuff on our personal rectangles, some during work hours
4. What we listen to when we’re doing something else.

NPR has always been in #4. With Machine Gods, it wants to be in #2 as well.

Anyway, three things about this:

1. Podcasts are audio. The first time I hear “wherever you see your podcasts,” I’ll be willing to widen podcasting’s definitional scope. Before then, nah.
2. If Machine Gods is anything like Hard Fork, it won’t be a news show. It’ll be in the Technology list of Apple Podcasts and in Spotify’s version.
3. NPR sees the writing on the Internet’s wall. Over-the-air broadcasting is a dead field walking. I’ve been following that trend for years here, on my Trunkline blog, and in more than 6000 photos on my Flickr site that follows infrastructure. NPR is living off stations now (wholesaling programming that stations retail to listeners), but radio has two giant problems:

• • Over-the-air requires special devices called transmitters, antennas, and receivers. These days, only cars have those, and old-fashioned radio functions are buried deeper and less accessibly in dashboard infotainment systems.
  • Apps on phones can act as virtual radios, but how long will apps last? Look downstream at where Apple’s new App Intents will go. Try not to see apps disappearing the same way they do when you say to a phone or a smart speaker, “Play KQED.” This means that stations will become streams for live programs, and podcast sources for other stuff. How will NPR’s revenue model work with all that?

What happens to news is a big issue that it seems (to me, a geezer) only older people care about. NPR has always been a news organization. News needs currency: liveness, or close enough. With “what’s on” fading away, that’s a tough challenge.

Will U say Si to SI?

Last Tuesday, in his speech to the UN, the US president said this:

Hereinafter officially called superintelligence, changing the name, and that the use of the word artificial makes intelligence fake. It makes it sound fake. And it is not fake; it’s actually amazing, but we have to be careful. In fact, it is exactly the opposite of what it purports. From this point forward, all of United States documents, and hopefully the world’s, will be changed to use the much more accurate term Super as opposed to Artificial. So, it’s Superintelligence. In other words, welcome to the new world of Superintelligence — SI. SI; let’s see if that goes. It sounds much better; it is much better and it’s much more accurate. Let’s see if I have any power. Maybe I do, and maybe I don’t. We’re going to find out pretty soon. Superintelligence — every major new technology brings challenges, and Superintelligence is no exception.

“Artificial Intelligence”is itself an oxymoron, a contradiction in terms. There have always been better names. “Machine Intelligence,” for example. But AI is what everyone in the field, and the world, calls it. A Google keyword search for “AI” returns “About 10,140,000,000 results.” A search for “super intelligence” gets “About 2,390,000 results.” I guess that’s a start.

The Onion‘s American Voices gets these three responses to “President Trump directed U.S. agencies to rename AI to “super intelligence” on all official documents, claiming that the term “artificial” made the technology sound fake. What do you think?”:

• “Even the Constitution?”— Anton Pastranak, Systems Analyst
• “Why didn’t AI think of that?”—Will Stratton, Manifest Reader
• “There goes my one last objection to it.”—Cordelia Huestes, Retired Shipwright

My father, Allen H. Searls, was an archivist. Not a formal one, but good in the vernacular, at least when it came to one of the most consequential things he did in his life: helping build the George Washington Bridge. He did this by photographing his work and fellow workers. He shot with a Kodak camera, and then developed and printed each shot, and assembled them into an album that survives to this day. All the shots in this collection are from that album. I’ve archived them in my Flickr site focused on infrastructure. I have also Creative Commons licensed them to require only attribution. (Though I’d rather people credit Allen H. Searls than his son.)

Only two of the photos are dated. One is July 25, 1929, when workers and families celebrated the completion of the cable stringing operation. The other is July 25, 1930, presumably when the roadway was completed. I was able to piece together the significance of these dates, and guess at the date ranges of other pictures, by doing a deep dive into the New York Times archive (where I found that these guys were called “bridgemen”), and by reading my father’s copy of the Roebling Cable company’s book about how the bridge’s cables were made and put in place.

As we know now, almost too well, we live in an Age of AI, when the entire corpus of the Internet, and God only knows what else, has been ingested into large language models that are trained and programmed to answer questions about what they “know” (even though they don’t, really). Meanwhile what do we, as human beings, actually know? Or, better yet, where can we find what we need or want to know? Libraries of the physical kind are necessary but insufficient when our instruments of inquiry are entirely electronic. The World Wide Web has turned into the World Wide Whiteboard.

We need electronic archives. Simple as that.

We all know (and, I hope, appreciate) the Internet Archive. I was going to give my father’s copy of the Roebling book to the Archive for scanning, but discovered it’s already there! That made the book easy to read (here on this flat screen), and saved my own fragile copy from further damage.

A heroic example of one person’s work to save the whole corpus of literature on broadcasting is David Gleason’s World Radio History site, without which much knowledge of broadcasting history would be lost.

On the contemporary front, Dave Askins‘ work toward online local news chronicles may prove essential if we don’t want to see current and future news disappear down the same holes into which too many past publications’ work has fallen (or remains alive but trapped behind paywalls).

For more on where this might go, see my Archives as Commons post. I’ll be talking about this, I hope, at the upcoming WoW Conference and DWeb Camp.

 

Here is me, trying to get ChatGPT (version 4o, which I pay for) to give me an illustration to use in my last post here, titled The People’s AI. But don’t go there yet (if you haven’t already). What I ended up using there is a punchline at the end of the dialog that starts here—

Me: A vast field on which the ground spells the letters A and I, with people on it, having a good time.

ChatGPT:

Here’s the illustration of a whimsical outdoor scene with a vast field shaped into the letters ‘A’ and ‘I’, where people are enjoying various activities, creating a cheerful and lively atmosphere.

Me: Make the two letters upper case A and upper case I, both with serifs.

ChatGPT: 

Here’s the updated illustration of a vast field shaped into the uppercase letters ‘A’ and ‘I’, both with serifs, where people are enjoying a sunny day outdoors. The setting is lively and festive, enhancing the creative landscape.

Me: Those are not the letters A or I, and lack serifs. Try again, with A on the left, and I on the right.

ChatGPT: 

Here’s the updated illustration showing a vast field shaped into the uppercase serif letters ‘A’ and ‘I’, with ‘A’ on the left and ‘I’ on the right. The field is vibrant and bustling with people enjoying various outdoor activities.

Me: Better, but there is no I on the right.

ChatGPT:

Here’s the updated illustration showing a vast field clearly shaped into the uppercase serif letters ‘A’ and ‘I’, with ‘A’ on the left and ‘I’ on the right. The field is lively with people engaging in various activities, set in a sunny and cheerful environment.

Me: That’s an interesting design, but I need an A and an I next to each other.

ChatGPT:

Here’s the updated illustration showing the vast field clearly shaped into the adjacent uppercase serif letters ‘A’ and ‘I’. The setting is vibrant and festive, surrounded by people enjoying various activities.

Me: That’s one big A, not an A and an I. Give me both.

ChatGPT:

Here’s the updated illustration showing a vast field clearly shaped into the uppercase serif letters ‘A’ and ‘I’, side by side. The setting is lively and festive, filled with people enjoying various activities.

Me: That has no serifs and is still just an A. I want an A and an I. Separate.

ChatGPT:

Here’s the updated illustration showing a vast field clearly shaped into the uppercase serif letters ‘A’ and ‘I’, side by side. The setting is vibrant, with people enjoying various outdoor activities.

Me: Still not separate. That’s one big A. I want an I next to it.

ChatGPT:

Here’s the updated illustration, clearly showing the vast field shaped into the separate uppercase serif letters ‘A’ on the left and ‘I’ on the right. The scene is lively with people enjoying various activities under a sunny sky.

Me: Let’s try this: An “A” and an “I” in an open field full of people.

ChatGPT: 

Here’s the illustration showing an open field shaped into the uppercase letters ‘A’ and ‘I’, with people enjoying various activities in the area. The scene is lively and sunny, capturing a cheerful outdoor gathering.

Me: Better! Now give me the same thing, with a complete “a.”

ChatGPT:  We are experiencing heavy server load. To ensure the best experience for everyone, we have rate limits in place. Please wait for 2 minutes before generating more images. Let me know if there’s anything else you’d like to discuss in the meantime!

Me (after a 3 minute pause): Thanks. Now give me the same image, but with a complete “A.”

ChatGPT: 

Here’s the updated illustration showing a vast open field creatively landscaped into two distinct uppercase ‘A’ letters, bustling with people enjoying various activities in a sunny, cheerful setting.

(Yes, it created both images.)

Me: Give me the same, but with people surrounding the “A” and the “I.” Also, please put serifs on the “I.”

ChatGPT:

Here’s the updated illustration showing a vast open field creatively landscaped into the shapes of the uppercase letters ‘A’ and ‘I’, both with serifs. The field is surrounded by people enjoying various activities in a sunny, cheerful setting.

Me: Try the same, but with “a” and “i” as separate letters.

ChatGPT: 

Here’s the updated illustration showing a vast open field creatively landscaped into the shapes of the lowercase letters ‘a’ and ‘i’. The setting is surrounded by people enjoying various activities in a sunny, cheerful atmosphere.

Me: Closer. Only now take it out of the city. I want only countryside.

ChatGPT:

Here’s the updated illustration showing a vast open field in the countryside, creatively landscaped into the shapes of the lowercase letters ‘a’ and ‘i’. The setting is serene and picturesque, surrounded by people enjoying rural activities.

Me: Please make the “a” and the “i” separate.

ChatGPT:

Here’s the updated illustration showing a vast open field in the countryside, creatively landscaped into the distinctly separated lowercase letters ‘a’ and ‘i’. The setting is serene, surrounded by people enjoying rural activities in a picturesque and peaceful outdoor gathering.

At this point I gave up and decided to give Microsoft Copilot a whack—

Me: A vast field on which the ground spells the letters A and I, with people on it, having a good time.

Microsoft Copilot:

I decided not to push my luck, and used the one on the bottom right.

It’s fun to know I am not alone at this. Here is a brilliant video of somebody far more patient than I getting ChatGPT to spell HONDA in ASCII art.

Early days, folks. Early days.

 

People need their own AIs. Personally and collectively.

We won’t get them from Anthropic, Apple, Google, OpenAI, Meta, or Microsoft. Not even from Apple.

All those companies will want to provide AIaaS: AI as a Service, rather than AI that’s yours alone. Or ours, collectively.

The People’s AI can only come from people. Since it will be made of code, it will come from open-source developers working for all of us, and not just for their employers—even if those employers are companies listed above.*

That’s how we got Linux, Apache, MySQL, Python, and countless other open-source code bases on which the digital world is now built from the ground up. Our common ground is open-source code, standards, and protocols.

The sum of business that happens atop that common ground is incalculably vast. It also owes to what we first started calling because effects twenty years ago at Bloggercon. That was when people were making a lot more money because of blogging than with blogging.

Right after that it also became clear that most of the money being made in the whole tech world was because of open-source code, standards, and protocols, rather than with them. (I wrote more about it here, here, and here.)

So, thanks to because effects, the most leveraged investments anyone can make today will be in developing open source code for The People’s AI.

That’s the AI each of us will have for our own, and that we can use both by ourselves and together as communities.

Those because investments will pay off on the with side as lavishly as investments in TCP/IP, HTTP, Linux, and countless other open-source efforts have delivered across the last three decades.

Only now they’ll pay off a lot faster. For all of us.

---

*See what I wrote for Linux Journal in 2006 about how IBM got clueful about paying kernel developers to work for the whole world and not just one company.

Newsletters are all the rage now. In recognition of that, I blogged here two years ago about the idea of writing a solo newsletter. Since then I’ve been co-producing this one with Katherine Druckman at Reality 2.o. It’s a Substack one, so I know how that game works on the production as well as the consumption ends.

Recently I also learned that WordPress makes it easy to turn blogs into newsletters, which is why you see “Get New Posts by Email” in the right column here. So, wanting an image to go with the news that this blog can now be a newsletter if you like, I said to ChatGPT, “Draw me Doc Searls blogging on the left side of the image, and producing a newsletter on the right side.” It gave me this, including the caption:

Except for the slouch, I never looked like that. But what the hell. AI is wacky shit, so there ya go.

Feel free to subscribe.

There is a war going on. Humanity and nature are on one side and Big Tech is on the other. The two sides are not opposed. They are orthogonal. The human side is horizontal and the Big Tech side is vertical.*

The human side is personal, social, self-governed, heterarchical, open, and grounded in the physical world. Its model is nature, and the cooperative contexts in which competition, creation, and destruction happen in the natural world.

The Big Tech side is corporate, industrial, hierarchical, competitive, mechanistic, extractive, and closed, even though it produces many positive-sum products and services that are good for people and good for nature. It is also, being competitive and rewarding toward winner-take-most outcomes, dominated by giants.

This war has been fought over many other things in the past, especially in tech. But AI is the big one right now—and perhaps the biggest one of all time.

Over the long run, both sides will win, because we need the best of what both bring to the world’s big round table. In the past, this has happened in countless markets, countries, polities, societies, and other contexts. In tech it happened with the conflict between PCs and mainframes, between the open and public Internet and closed private networks, and between open operating systems and closed ones. None of those conflicts have final outcomes, but they have arrived at stable and cooperative states. They arrived at those states because everyone recognized that people can do more with their own tools than those big entities can do on theirs, or by using people as extracted resources.

This conflict is perhaps best represented by the ironies that have been at work within OpenAI and Sam Altman, its prior and current CEO. We can also see it with sparkling clarity in something amazing that Sam said near the close of his keynote at the first OpenAI Developer Conference, in November of last year:

Lets unpack that.

Individual empowerment means exactly what it says. Agency is the ability to take action or to choose what action to take (Cambridge Dictionary). Scale means growth toward ubiquity.

You have individual empowerment and agency when you ride your bike, drive your car, mow your lawn, or button your shirt. You also have it when you work on your laptop, phone, and other smart rectangles. Scale means your power and agency will grow to the max while the same will happen for nearly everyone else. Scale for you alone won’t cut it. When most of us have it, that’s scale.

Technologies extend us. They enlarge our capacities in the world. Intelligence is one of those capacities. So is memory. Your rectangles help a lot with both. That’s why those have already scaled to ubiquity, or close enough.

AI will do the same, but only if it’s personal. Not if it’s  just “personalized.”

As Jamie Smith made clear here a year ago, “your personal AI isn’t really personal.”

ChatGPT4 doesn’t know that yet. I can tell because I just asked:

Me:
What is “personal AI”?

ChatGPT4:
“Personal AI” refers to artificial intelligence systems that are designed to serve individual users through personalized interactions and services. These AI systems learn from the specific preferences, behaviors, and needs of their users to offer more tailored assistance, recommendations, or information. The goal of personal AI is to enhance user experience by adapting to unique personal profiles.

There are various applications of personal AI, including:

1. Virtual Assistants: Like Siri, Google Assistant, and others, these AIs help with daily tasks such as scheduling, reminders, searching information, and controlling smart home devices, all customized to the user’s habits and preferences.
2. Recommendation Systems: Used in streaming services like Netflix or shopping platforms like Amazon, these AI systems analyze your past behavior to recommend movies, shows, or products you might like.
3. Healthcare: Personal AI can track individual health metrics and provide personalized advice, monitor conditions, or even alert medical professionals if needed.
4. Learning and Development: In education, personal AI can adapt learning materials to the pace and learning style of the student, offering a customized educational experience.
5. Gaming: AI in gaming can adapt to provide a challenge tailored to the player’s skill level or alter the game narrative based on choices made by the player.

The development of personal AI focuses on enhancing user engagement by creating more intuitive and responsive interactions that feel uniquely suited to each individual.

For a second opinion, I asked Google’s Gemini the same question.

Me:
What is “personal AI”?

Gemini:
Personal AI refers to artificial intelligence designed to assist and interact with a specific individual. It’s essentially your own AI companion that learns about you and tailors its services to your needs. Here are some key aspects of personal AI:

1. Personalization: Unlike general-purpose AI assistants, personal AI focuses on you. It learns from your interactions, preferences, and habits to become more helpful over time.
2. Focus on Memory and Knowledge: Some personal AI systems aim to become an extension of your mind. They can store your memories, knowledge, and experiences, making them readily accessible and even usable to help with tasks like writing or communication.
3. Varied Applications: Personal AI can have a wide range of applications. Imagine an AI that helps you:
4. Organize your life: Manage schedules, appointments, and reminders.
5. Boost productivity: Assist with tasks, research, and communication.
6. Enhance creativity: Help you brainstorm ideas or generate creative content.
7. Improve learning: Personalize learning experiences and provide targeted information.

Privacy Concerns: Storing personal data on an AI raises concerns about privacy and security.

Overall, personal AI holds promise for a future where technology seamlessly integrates with our lives, offering personalized assistance and support.

To both companies, personal AI is a personalized service—from them. It’s not something you own and control. It’s not about individual empowerment and agency. It doesn’t extend you. It’s hired prosthesis: an extension of them rather than of you.

Let’s name the category: AIaaS—AI as a Service.

But hats off. OpenAI and Gemini do amazing jobs. So do lots of other AI services by wannabe giants. I use AI every day to improve what I write, to generate and fix images, to answer questions that old-fashioned search engines can’t answer or suck at. I even pay extra for some of it (such as ChatGPT4 and Adobe’s Creative Suite). And it seems they all get better, all the time, at everything. Won’t personalization be good enough, eventually?

No. Because they aren’t you. They also aren’t yours, so they can’t extend you. They can seem to. But they don’t. They also don’t have access to most of your private life. Nor should they.

But your private life could use some AI help. For example—

• Schedules, including on your calendars, past and future
• Health data, including all your medical reports, prescriptions, appointments, insurance information, past and present providers, plus what your watch, phone, and other devices record about you
• Financial records, including bills, receipts, taxes, and anything called an account that involves money
• Travel, including all the movements your phone (and phone company), watch, and car record about where you go and where you’ve been
• Work—past and present, including whatever HR systems know or knew about you
• Contacts—all the people, businesses, and other entities you know
• Business relationships, with brokers, retailers, service providers, whatever
• Subscriptions, including all those “just $1 for the first four weeks” offers you’ve accepted, plus other forms of screwage that are stock-in-trade for companies selling subscription systems to businesses.
• Property, including all the stuff on your shelves, floors, closets, garages, and storage spaces—plus your stocks and real estate.

It’s not easy to visualize what a personal AI might do for those, but let’s try. Here’s how Microsoft’s Copilot (or whatever it’s called this week) did it for me before I got rid of all its misspellings and added my own hunks of text:

All that stuff is data. But most of it is scattered between apps and clouds belonging to Apple, Google, Microsoft, Amazon, Meta, phone companies, cable companies, car makers, health care systems, insurance companies, banks, credit card companies, retailers, and other systems that are not yours. And most of them also think that data is theirs and not yours.

To collect and manage all that stuff, you need tools that don’t yet exist: tools that are yours and not theirs. We could hardly begin to imagine those tools before AI came along. Now we can.

For example, you should be able to take a picture of the books on your shelves and have a complete record of what those books are and where you got them. You’ll know where you got them because you have a complete history of what you bought, where and from whom. You should be able to point your camera in your closets, at the rugs on your floors, at your furniture, at the VIN number of your car that’s visible under your windshield, at your appliances and plumbing fixtures, and have your AI tell you what those are, or at least make far more educated guesses than you can make on your own.

Yes, your AI should be able to tap into external databases and AI systems for help, but without divulging identity information or other private data. Those services should be dependent variables, not independent ones. For full individual empowerment and agency, you need to be independent. So does everyone else with personal AI.

Now imagine having a scanner that you can feed every bill, every receipt, every subscription renewal notice, and have AI software that tells you what’s what with each of them, and sorts records into the places they belong.

Ever notice that the Amazon line items on your credit card bill not only aren’t itemized, but don’t match Amazon’s online record of what you ordered? Your personal AI can sort that out. It can help say which are business and personal expenses, which are suspicious in some way, what doesn’t add up, and much more.

Your personal AI should be able to answer questions like, How many times have I had lunch at this place? Who was I with? When was it we drove to see so-and-so in Wisconsin? What route did we take? What was that one car we rented that we actually liked?

Way back in 1995, when our family first got on the Internet over dial-up, using the first graphical browsers on our PC, and e-commerce began to take off with Amazon, eBay, and other online retailers, my wife asked an essential question: Why can’t I have my own shopping cart that I take from site to site?

Twenty-nine years later, we still don’t have the answer, because every retailer wants you to use its own. And we’re stuck in that system. It’s the same system that has us separately consenting to what sites ironically call “your privacy choices.” And aren’t.

There are countless nice things we can’t have in the digital world today because we aren’t people there. We are accounts. And we are reduced to accounts by every entity that requires a login and password.

This system is a legacy of client-server, a euphemism for slave-master. We might also call it calf-cow, because that’s how we relate to businesses with which we have accounts. And that model is leveraged on the Web like this:

We go to sites for the milk of content and free cookies, whether we want them or not. We are also just “users.”

In the client-server world, servers get scale. Clients have no more scale than what each account—each cow—separately allows. Sure, users get lots of benefits, but scale across many cows is not one of them. And no, “login with Google” and “login with Facebook” are just passes that let calves of ruling cows wander into vassal pastures.

For individual empowerment and scale to happen, we need to be self-sovereign and independent. Personal AI can give that to us. It can do that by solving problems such as the ones listed above, and by working as agents that represent us as human beings—rather than mere users—when we engage with Big Tech’s cows.

This will be a fight at first, because the cows think they run all of nature and not just their own farms. And $trillions are being invested in the same old cattle industry, with AI painted all over the new barns. Comparatively speaking, close to nothing is going toward giving independent and self-sovereign individuals the kind of power and scale Sam Altman says he wants to give us but can’t because he’s on the big cow side of this thing.

So where do we start?

First, with open source code and open standards. We have some already. Llama 3, from Meta AI, is “your own intelligent assistant,” and positions Meta as a more open and user-friendly cow than OpenAI. Meta is still on the top-down Big Tech side of the war we’re in. But hell, we can use what they’ve got. So let’s play with it.

Here on the ground there are all these (with quotage lifted from their sites or reviews such as this one)—

• MindsDB: “an open-source AutoML framework”
• Alt.ai: “It’s an A.I. which aims to digitize users’ intentions and place it on the cloud to let our clones deal with all digital operations.”
• Keras: “a multi-backend deep learning framework, with support for JAX, TensorFlow, and PyTorch”
• PyTorch: “Python package that provides two high-level features: Tensor computation (like NumPy) with strong GPU acceleration, and Deep neural networks built on a tape-based autograd system
• Tensor Flow: “open-source framework for machine learning”
• CoreNet: a deep neural network toolkit for small and large-scale models, from Apple
• Haystack: an “open source Python framework by deepset for building custom apps with large language models (LLMs).”
• Image Super-Resolution (ISR): “(an) open source tool employs a machine learning model that you can train to guess at the details in a low-resolution image:
• Blender: “A rich interface and numerous plugins make it possible to create complex motion graphics or cinematic vistas”
• DeepFaceLab: “open source deepfake technology that runs on Python”
• tflearn: “an advanced deep learning library”
• PYTensor: “a Python library that allows you to define, optimize/rewrite, and evaluate mathematical expressions involving multi-dimensional arrays efficiently.” (Was Theano)
• LM Studio: “Discover, download, and run local LLMs”
• HuggingFace Transformers: “a popular open-source library for Natural Language Processing (NLP) tasks”
• Fast.ai: “a library for working with deep learning tasks”
• OpenCV: “a popular Computer Vision and Image Processing library developed by Intel”
• Detectron2: “a next-generation library that provides advanced detection and segmentation algorithm” and “a PyTorch-based modular object detection library”
• Ivy.ai: “an open-source deep learning library in Python focusing on research and development”
• OpenAssistant: “a project aimed at giving everyone access to a great chat-based large language model”
• PaddleNLP: “a popular open source NLP library that you can use to glean search sentiment and flag important entities”
• Delphi.AI: “Clone yourself. Build the digital version of you to scale your expertise and availability, infinitely.”
• Fauxpilot: “This is an attempt to build a locally hosted alternative to GitHub Copilot. It uses the SalesForce CodeGen models inside NVIDIA’s Triton Inference Server with the FasterTransformer backend.”
• Ray: “An open source framework to build and scale your ML and Python applications easily”
• Solid: “Solid is a specification that lets individuals and groups store their data securely in decentralized data stores called Pods. Pods are like secure web servers for data. When data is stored in a Pod, its owners control which people and applications can access it.”
• Sagen.ai: “Your very own AI Personal Assistant to manage your digital life.”
• YOLOv7: “is one of the fastest and most accurate open source object detection tools. Just provide the tool with a collection of images full of objects and see what happens next.”

—and lots of others that readers can tell me about. Do that and I will add links later. This is a work in progress.

Below all of those we still need something Linux-like that will become the open base on which lots of other stuff runs. The closest I’ve seen so far is pAI-OS, by Kwaai.ai, a nonprofit I now serve as Chief Intention Officer. I got recruited by Reza Rassool, Kwaai’s founder and chair, because he believes personal AI is required to make The Intention Economy finally happen. So that was a hard offer to refuse. Kwaai also has a large, growing, and active community, which I believe is necessary, cool, and very encouraging.

As with most (maybe all) of the projects listed above, Kwaai is a grass-roots effort by human beings on the natural, human, and horizontal side of a battle with giants who would rather give us personalized AI than have us meet them in a middle to which we will bring personal AI powers of our own. In the long run, we will meet in that middle, because personal AI will be better for everyone than personalized AI alone.

Watch us prove it. Better yet, join the effort.

---

*I am indebted to Lavonne Reimer for introducing and co-thinking the horizontal vs. vertical frame, and look forward eagerly to her own writings and lecturings on the topic.

Among all artists, writers alone suffer the illusion that the world needs to hear what they have to say.

I thought that line, or something like it, came from Rollo May, probably in The Courage to Create. But a search within that book says no. ChatGPT and Gemini both tell me May didn’t say it anywhere.

Still, I think it’s true that writers write because they have to. They can’t not write. It’s what they do, how they live. And I’m one of them.

The need to write is for me a vivid fact this morning, a few days past a catheter ablation on my heart. There is so much I need to say, because I suffer the illusion that the world needs to hear it. Does it?

I am sure C.S. Lewis and J.R.R. Tolkein had the same affliction. I am also sure that the world is better for having read both of them, even if the world could have lived without their writing.

As for time, I have had twelve more years to write than Lewis got, so far, and five less than Tolkein.

Time to say what?

I want to say that personal AI will do far more for all of us than what we will ever get from AI as a corporate service. And to say it better than I just did.

I want to say that we will do better with rulers who care about people than with rulers who merely rule. And to say that better than I just did.

I want to complete the work of John McPhee by reporting as best I can what has happened to the great characters that anchored every one of his essays and books. But that project is not on the back burner. It’s in the fridge, where I’ve kept it for decades (while continuing to read the entire McPhee oeuvre, much of it repeatedly).

Speaking of burning, I am impelled by Dylan Thomas, who wrote “Do not go gentle into That Good Night,” before dying at just thirty-nine. The poem was for his father:

Old age should burn and rave at close of day,
Rage, rage against the dying of the light.

And so I do.

Before there were search engines, there were directories. The biggest and best-known was Yahoo. On the first graphical browser (Mosaic), it looked like this:

The directory idea made sense, because the Web is laid out like the directory in your computer. There is a “domain” with a “location” or a “site,” containing something after the last / in a path of /something/something/something. Geeks call these directories too, and the string of somethings a path. Directories in computing also follow an outline format: heads, subheads, and subheads of subheads.

While this design is boundlessly flexible, it also suggests durability, if not permanence, because it’s good to find stuff where it rightly goes and to find it in the same place over and over again.

That was what Yahoo assumed in the early days of the Web—as did everyone who bought a domain name. I’ve had searls.com since 1995. Dave Winer (father of outlining and progenitor of much else) has had Scripting.com for even longer (and has a lot more in that domain).

But we don’t own domain names. We rent them. And the World Wide Web isn’t a library. It’s a whiteboard with stuff written on it. Some of that stuff is located on directory paths. A lot more is coughed up by database systems on an as-needed basis.

The Yahoo directory failed. In its place search engines appeared. Search engines don’t catalog the Web like a library might. They index it. That means they send crawlers down the Web’s directory paths, recording everything they see into a searchable index. I explain here how that works and where this went:

The Web is a haystack.

This isn’t what Tim Berners-Lee had in mind when he invented the Web. Nor is it what Jerry Yang and David Filo had in mind when they invented Jerry and David’s Guide to the World Wide Web, which later became Yahoo. Jerry and David’s model for the Web was a library, and Yahoo was to be the first catalog for it. This made sense, given the prevailing conceptual frames for the Web at the time: real estate and publishing.

Both of those are still with us today. We frame the Web as real estate when we speak of “sites” with “locations” in “domains” with “addresses” you can “visit” and “browse”—then shift to publishing when we speak of “files” and “pages,” that we “author,” “edit,” “post,” “publish,” “syndicate” and store in “folders” within a “directory.” Both frames suggest durability if not permanence. Again, kind of like a library.

But once we added personal movement (“surf,” “browse”) and a vehicle for it (the browser), the Web became a World Wide Free-for-all. Literally. Anyone could publish, change and remove whatever they pleased, whenever they pleased. The same went for organizations of every kind, all over the world. And everyone with a browser could find their way to and through all of those spaces and places, and enjoy whatever “content” publishers chose to put there. Thus the Web grew into billions of sites, pages, images, databases, videos, and other stuff, with most of it changing constantly.

The result was a heaving heap of fuck-all.*

Back in 2005, I wrote in Linux Journal about a split between the “static” Web that was like a library (with its “locations,” “sites,” and “domains” you could “visit” and “browse”), and the “live” Web of blogs and posts. Then social media came along, and the live branch of the Web outgrew the static Web’s trunk.

Last week came news that a leak revealed lots of interesting poop about how Google actually ranks search results. Here are two things I don’t need those leaked documents to tell me:

1. Google favors the present over the past, the current over the archival.
2. Google no longer indexes, or ranks very old Web pages.

I speak from experience here, because I have some old pages that are on the Web but don’t seem to be indexed, meaning searches don’t find them. I also have Easter eggs on a couple of those pages: words that exist in no language but made those pages easy to find when I did keyword searches for them. Now I get “No results found for _____.” (I won’t reveal the word because I want to keep testing Google.)

Countless publications have also come and gone on the Web without leaving a trace. Upside was a gigantic publication from the Nineties through the dotcom boom. Not a trace of it remains. Far as I know, nothing remains of Fast Company‘s early issues.

But hey, God bless the Internet Archive. Here’s a piece I wrote for PC Magazine in December 1982 about a PC application that taught card counting in blackjack:

As the evanescence of “content” increases, so does the importance of archives.

So maybe stop reading here and start reading here. We have a lot of work to do.

The Santa Barbara News-Press was born in 1868 and died in 2023 at age 155. Its glory years ran from 1932 until 2000, when the New York Times sold it to Wendy McCaw, who rode it to hell.

That ride began with the Santa Barbara News Press Controversy in 2006 and ended when Ampersand, the company McCaw created to hold the paper’s bag of assets (which did not include its landmark building downtown, which McCaw kept), filed for Chapter 7 bankruptcy in late July of last year. Here are stories about the death of the paper in three local news journals that have done a great job of taking up the slack left when the News-Press began to collapse, plus one in the LA Times:

• ‘Santa Barbara News-Press’ Files for Bankruptcy: Publisher Ampersand Claims Few Assets and Many Creditors, by Jean Yamamura in the Santa Barbara Independent (July 23, 2023)
• Santa Barbara News-Press Declares Bankruptcy, Staff Told All Jobs ‘Eliminated’, by Joshua Molina, in Noozhawk (July 23, 2023)
• Santa Barbara News-Press Files for Bankruptcy, Staff Fired, by Edhat Staff (July 24, 2023)
• Santa Barbara News-Press bankruptcy brings uneasy end to an owner’s bitter tenure, by James Rainey, in the Los Angeles Times. (July 29, 2023)

I followed those with this in We Need Deep News:

From what I’ve read so far (and I’d love to be wrong) none of those news reports touch on the subject of the News-Press‘ archives, which conceivably reach back across the century and a half it was published. There can’t be a better first draft of history for Santa Barbara than that one. If it’s gone, the loss is incalculable. (August 18 2023)

Last month brought bad news about that:

• ‘Santa Barbara News-Press’ Online Assets to Be Sold: Bankruptcy Sale for $250,000 Subject to Bids in April, by Jean Yamamura in the Santa Barbara Independent March 8, 2024
• A local paper went bankrupt. Now a faraway buyer wants its assets: The Santa Barbara News-Press’s digital assets are up for sale. Locals worry they could become a farm for AI-generated SEO bait. By Ernie Smith in Fast Company. (March 5, 2024)
• Santa Barbara’s Collective Memory, Sold for Kindling: Will ‘NewsPress.Com’ Become a Zombie Website? by William Belfiore in the Independent. (March 29, 2024)

But then, thanks to William Belfiore’s appeal in that last piece, we learned this:

• ‘Santa Barbara News-Press’ Website Goes to ‘Local Kids’ Group Fronted by Ben Romo Makes Winning Auction Bid of $285,000, by Jean Yamamura in the Independent (Apr 09, 2024)

The only mention of archives was in the closing sentences of that piece:

The purchase of the website included the Santa Barbara News-Press trademark, which would be important to the groups looking at the physical archive of back issues, photographs, and clippings by topic. Romo, who was once a paper boy for the daily, acknowledged that his group was supportive of the archive remaining local, too.

I don’t know what that means, and I haven’t checked. But I am sure that the archives ought to be managed by the community as a common pool resource.

As it happens, my wife and I are visiting scholars at the Ostrom Workshop at Indiana University, which is concerned with this kind of thing, because its namesake, Elinor Ostrom, won a Nobel Prize in Economics for her work on how commons are self-governed. In her landmark book, Governing the Commons: The Evolution of Institutions for Collective Action, she lists eight principles for managing a commons, which are summarized here:

1. Define clear group boundaries.
2. Match rules governing use of common goods to local needs and conditions.
3. Ensure that those affected by the rules can participate in modifying the rules.
4. Make sure the rule-making rights of community members are respected by outside authorities.
5. Develop a system, carried out by community members, for monitoring members’ behavior.
6. Use graduated sanctions for rule violators.
7. Provide accessible, low-cost means for dispute resolution.
8. Build responsibility for governing the common resource in nested tiers from the lowest level up to the entire interconnected system.

Journalists, especially those who report news, are not herding animals. They tend to be competitive and territorial by both nature and purpose. So the collection of news entities I wrote about in We Need Wide News and We Need Whole News will almost certainly not cohere into a commons such as Lin (her nickname) Ostrom addresses in that list.

But they should cohere around archives—not only because that’s the right thing to do, but because they need those archives. We all do.

So I hope Santa Barbara’s many journals, journalists, friends, supporters, and interested local institutions get together around this challenge. Build a commons around those archives, whatever and wherever they happen to be.

Meanwhile here in Bloomington, my other hometown, we are pushing forward with The Online Local Chronicle that Dave Askins wrote about in the previous installment in this series. We might call that a commons interest here.

 

 

We who care about journalism are asked to join the Save Journalism Project, and its fight against Big Tech. Their pitch begins,

and adds,

On the first point, we should note that journalists have been working for magazines, broadcasters, newsletters and themselves for many dozens of years. So journalism isn’t just about newspapers. Also, because so many journalists have long made livings in those other media, the loss of work is far greater than the 2,400 gone from newspapers. It’s truly massive. I don’t know any field where the loss of paying jobs is larger on a percentage basis. Not taxi driving, not hospitality, not retail, not manufacturing… not anything I can think of. (Well, maybe nuns. I don’t see many of those these days.)

We should also respect the simple fact that now there is more journalism than ever: in blogs, social media, podcasting, and other places. Most of those kinds of journalism don’t pay, but that doesn’t disqualify the work from the label. Hell, I’m committing journalism here and this doesn’t pay.

“The story of big tech’s threat to journalism” (what the Project wants us all to tell) is also something of a red herring because it distracts our attention from causes much bigger than Big Tech.

Every new technology “works us over completely,” Marshall McLuhan says (in The Medium is the Massage). And no new medium, no new technologies, have ever worked us more than the digital kind. The change began with digital tech and integrated circuits and then went absolute with the Internet. Together, digital technologies and the Internet have radiacally changed our species, our civilization, and our planet.

Not long ago, in a conversation about this with Joi Ito, I asked him how big he thought the digital transformation was. Bigger than broadcast? Print? Writing? Speech? Stone tools?

“No,” he replied. “It’s the biggest thing since oxygenation.” In case you don’t remember, that happened between about two and a half billion years ago. (Joi also writes about it here.)

So, while journalism matters enormously, it’s just one casualty of digitalization. And, let’s face it, a beneficiary as well. Either way, we need to understand the whole picture, which is about a lot more than what journalism sees happening in the mirror.

Here’s one outfit working on that bigger picture. I‘m involved with it.

I also don’t expect most journalists to take much interest in the subject, because it’s too big, and it doesn’t make full sense as a story, which is journalism’s stock in trade. (I explain a bit about journalism’s “story problem” in this TEDx talk.)

Still, some journalists are on the case, including me. Love to have others join in. But please don’t bother if you think Big Tech is alone to blame. Because the story is bigger than that, and far more than a story.

---

I just copied and pasted this post from here in Medium, where I posted it in July 2019. It expands on a post now archived here. It’s kinda sad that not much has changed over all that time.