I left dinner at the Uptown to stand at the corner of Kirkwood and College in downtown Bloomington, Indiana, to shoot the tornado my phone just told me had formed eight miles west of there. That's where I was facing when I shot this video, from which I pulled a bunch of screen grabs in Photos' edit view. This covered about four minutes starting at 7:03 PM.

Earlier, when we got the first tornado warning, I went out and shot this video, from which I have a similar series of screen grabs:

That was about five minutes, starting at 6:42 PM.

Both these videos and all these screen-grabs are free to use, and Creative Commons licensed to only require photo credit. And I'm also not prickly about that. It's just fun to see where they prove useful. Have at 'em.

And if you're interested in news, and how we can start remaking it, starting here in Bloomington and towns like it, see what I've been writing about that, with a big hat tip to Dave Askins of Bloomington's B Square Bulletin.

Be there

Surveillance-based pricing (just for you!) will be the subject of this talk at 4pm Eastern today. Register and attend at that link.

One of many

This is one reason why I'm still staying away from OpenClaw.

Never too late for the late

Today is Ron Phillips' birthday. He died five years ago, but his absence remains constant and heart-wrenching. I'm also sad to note that I haven't written a proper remembrance for him here. So that's now on my list.

Extra points if you can say where this is.

What you're reading is written and posted on the Web. While the Web isn't a place, we know it as one. The language we use to describe it is concrete and structural: domains at locations, with sites that are built and have pages that are authored, and contents that are uploaded and downloaded.

For a generation or more, we mostly saw and navigated the Web through Google, whose original mission was "to organize the world's information and make it universally accessible and useful." When we searched Google, we relied on its PageRank system to bring us lists of pages ranked by how likely they were to contain keywords or other search terms.

But Google Search has changed. Old pages are gone from many searches. This matters to me because I've been writing on the Web for thirty-one years, almost entirely on static sites. But Google no longer finds many of those. My friend Dave Askins tells me the same malady has befallen much of his own archival work, which is present on the Web, but absent from Google searches. Why?

I asked Google's Gemini that question. Here's what it said:

The "disappearing" of the old web is a result of a massive shift in Google's priorities over the last few years.

While you might be looking for a specific historical document or an old forum thread, Google's systems are now aggressively tuned to filter out what they consider "stale" or "unhelpful" content…

In the race to be a 'helpful assistant,' Google has stopped being a 'universal library.

PageRank is still there, it tells me, but subordinated. To what?

Of course: it's advertising.

Taking my clues from Keyords are dead, by Shalom Gonzalez in Search Engine Land, I asked Gemini to tell me "how searches by the helpful assistant might constantly be looking for what the person might eventually want to buy, so they can be advertised at when the right time comes."

Gemini replied,

This is the "secret sauce" of the 2026 search model. If the old search engine was a librarian, the new one is a personal shopper who is taking notes on everything you do to predict your next "need state. The transition you're sensing is the move from Reactive Search (answering what you asked) to Predictive Search (answering what you're going to ask)."

This treats the Web as nothing more than a heap of data in which patterns can be found, and answers given, based on algorithmic assumptions—not just about who and what a person is, but what advertisers are paying to have pitched. Constantly. In real time.

There are four giant problems to pull apart here:

1. How Google is deprecating the Web.
2. What to call the vast everything that Big AI now uses to give us answers and pitch us shit.
3. How AI dependence is changing us from homo sapiens to homo something else.
4. How we can stay human in the midst of it all.

So let's explore those.

I. How Google is deprecating the Web.

We need to name the machine equivalent of hubris that Google and Gemini display in their deprecation of the Web and their presumptions about our intentions.

Dictionary.com says hubris is derived from hýbris, the Greek word for insolence. It mean pride, arrogance, or an excess of ambition…ultimately causing the transgressor's ruin.

When I asked ChatGPT to define AI hubris, it said, "AI hubris is the condition in which a system expresses or operationalizes confidence that exceeds its actual competence, epistemic grounding, or contextual awareness."

Then, when I asked it to explain how that manifests, it gave me—

• A model that acts as if it knows rather than predicts.
• A system that is treated as an oracle rather than a probabilistic engine.
• Designers who mistake fluency for wisdom.

When I asked it to be more specific, it confessed to—

• Overconfident answers: The model presents uncertain, incomplete, or fabricated information as authoritative.
• Boundary blindness: It fails to recognize where its training data ends, where knowledge is outdated, or where a question exceeds its capability.
• Illusion of comprehension: It produces fluent language that implies understanding when it is pattern synthesis.
• Prescriptive overreach: It gives decisive advice in domains requiring caution (medicine, law, policy) without signaling uncertainty.
• System-level hubris: Not just the model—but the designers or deployers assume the system is more reliable, objective, or neutral than it truly is.

Then I asked it to give me some words we might use to label AI hubris. It generated a large pile of them, abridged here—

1. Hybris mechanica: Latinized Greek; "mechanical hubris." Evokes classical overreach, but makes clear it's structural, not emotional. Good if you want rhetorical force.
2. Pseudomnēsis (ψευδομνήσις): "False memory." From pseudo- (false) + mnēsis (memory, recollection). Captures the illusion of knowing.
3. Doctia ignorans: Modeled on docta ignorantia (Nicholas of Cusa: "learned ignorance"). This flips it: Doctia ignorans — "ignorant knowing." Sharp, ironic, philosophical.
4. Epistemic hybris: Blunt and precise. The sin is not pride, but overstepping epistemic bounds.
5. Pseudognosis (ψευδογνῶσις): False knowledge. Simple, strong, clean.
6. Automata superbia: Mechanical arrogance. Has a medieval-theological feel.
7. Confidentia vacua. Empty confidence. Direct and Roman.
8. Logohybris: λόγος (speech/reason) + ὕβρις (hubris) Hubris of speech. Arrogance of articulated reason. Sharp, rhetorically charged, has teeth.
9. Pseudognosis: Names the condition without moralizing it.
10. Pseudodoxia (ψευδοδοξία): Suggests false or illusory knowing, overstepping bounds, inflated confidence, illusion of authority, false belief, spurious opinion. Has historical precedent (e.g., Browne's Pseudodoxia Epidemica). Feels learned and slightly ironic.
11. Kenognosis (κενογνῶσις): "Empty knowledge." From kenos (empty) + gnosis (knowledge). Strong and elegant.
12. Agnomimesis (ἀγνωμιμησις): "Imitation of knowing." From agnoia (ignorance) + mimesis (imitation). Captures the performance of understanding.
13. Pseudonoia (ψευδονοία): False mind / counterfeit intellect. More psychological. Overstepping Epistemic Bounds
14. Epihybris (ἐπιὕβρις): "Over-hubris" or escalated hubris. Suggests compounding overreach.
15. Metahubris: Hubris at the level of system or design. Modern coinage, but philosophically clean.
16. Paragnosis (παράγνωσις): Misrecognition; knowing beside the truth. Has a tragic flavor (like parabasis, paradox).
17. Transgnosis: Going beyond what one can legitimately know.
18. Megalodoxia (μεγαλοδοξία): Inflated Confidence. Grand opinion; overblown self-assurance.
19. Superbia machinae: "The arrogance of the machine." Latinate, ecclesiastical.
20. Inflatio mentis: Inflation of mind. Roman and sharp.
21. Praesumptio automatica: Automatic presumption. Feels juridical.
22. Authodoxia: Illusion of Authority. Self-authorizing belief. Authority generated from itself.
23. Autognosticism: Self-certifying knowledge. Simulacra scientiae. A simulacrum of knowledge. Very Baudrillard-adjacent.
24. Oraculitis: Mock-Greek: "oracle-itis." The disease of speaking as an oracle.
25. Technohybris: Structural or Systemic Hubris. Technological overreach. Blunt but serviceable.
26. Logomimesis: Mimicry of reasoned speech. Less accusatory, more descriptive.
27. Sophomimesis: Imitation of wisdom.Sophia (wisdom) + mimesis (imitation).
28. Pseudoepisteme (ψευδοεπιστήμη): False systematic knowledge. More formal than pseudognosis.
29. Kenodoxia: "Empty glory" (historically attested in theology). Could be repurposed. Stark and Memorable
30. Vox vana: "Empty voice."
31. Certitudo vana: "Vain certainty."
32. Machina praesumens: The presuming machine.
33. Sophomimesis: Imitation of wisdom.
34. Kenognosis: Empty knowledge.
35. Pseudodoxia mechanica: mechanical false belief.
36. Logohybris: Hubris of speech (from earlier).
37. Paragnosis: Mis-knowing.

Well, Big AI is all of those. But let's pick one, because we need it. I lean toward logohybris, but I'm open.

II. What to call the vast everything that Big AI now uses to give us answers and pitch us shit

We are the only species that talks. A lot. About everything. We also make sense of the world as embodied creatures. We say good is up and bad is down because we are built for standing, walking, running, and squatting without falling over. This is why heaven is above, hell is below, and to fail is to fall. We say good is light and bad is dark because we are diurnal: optimized for daylight. We say a smart person is bright and a dumb person is dim. Good futures are bright and bad ones are dark. We frame life as travel, not a biological process. That's why birth is arrival, death is departure, and we get stuck in a rut, lost in the woods, and fall off a wagon. We frame time as money, not as a progression of existence. That's why we save, waste, spend, invest, and lose time.

We also lay nouns on everything (and non-thing) that we possibly can. We make taxonomies to organize the nouns. We make verbs for the actions that happen among and between all the nouns. We make prepositions to locate the nouns. We would be lost without all the ways we understand the world as a structured place.

To illustrate how important this is, look at how some drugs detach our minds from structures:

• LSD—acid—detaches what we see and know from all the nouns we project on them.
• MDMA—ecstasy—liberates other beings from what might in a normal state of mind make them separate from us and unlovable until proven otherwise.
• THC—weed—disconnects percepts and thoughts, so they become "strings of pearls without the string." (That's one of the few smart things I ever said when I was high.*)

While all those drugs are good for recreation and therapy, and may even help civilize us in some ways, they distract us from the structures that make civilization work.

Nearly all of what we know about the natural world is also tacit, meaning we know it, but can't explain it. For example, we know how gravity works, even though we can't explain it as well as Einstein or Feynman. Or at all. Doesn't matter. We know how it works, and that's what matters.

We can still be explicit about what we know. About gravity, we might say, "It's what gives things weight." Or, "It's what makes things in a vacuum fall at 9.8 meters per second squared."

Here's the key: What we know tacitly far exceeds what we can say explicitly.

The digital world, however, is entirely explicit. It is composed of data and code. There is no tacit there.

In the digital world, we also have no distance and no gravity, at costs that lean toward zero. A video conference might have people from India, Germany, and Australia, with none sensing distance or cost. Everyone is present. Conversation moves along just fine. Gravity is also absent, because nobody manifests in material form, or appears upside-down or sideways. There might be light outside the window of one participant and dark outside the window of another, but only if the camera points toward a window and the person isn't using a fake background.

But we still have structures in the digital world. For example, the World Wide Web uses a hypertext protocol (http/s) to connect sites at domains locations, between which packetized data can moves up and down. Note that these are real estate and shipping metaphors.

Directory paths on the Web are inherited from UNIX. For example, https://science.what/geology/phanerozoic/paleozoic/devonian/fossils/ammonites is what's called a path. It's like one you might follow through the stacks of a library. That's still how the Web works for us. It has structure.

When search engines indexed everything in those published directory structures, they made sense of the whole Web in a library-like way. We can see how the Internet is drifting away from that structure by reviewing the titles of David Weinberger's literary oeuvre, following The Cluetrain Manifesto in 1999:

• Small Pieces Loosely Joined:
  {A Unified Theory of the Web} (2002)
• Everything is Miscellaneous:
  The Power of the New Digtal Disorder (2008)
• Too Big to Know:
  Rethinking Knowledge Now That the Facts Aren't the Facts, Experts Are Everywhere, and the Smartest Person in the Room Is the Room (2012)
• Everyday Chaos:
  Technology, Complexity, and How We're Thriving in a New World of Possibility (2019)

See where this is going?

Yes, toward AI. By now, Big AI has absorbed all those miscellaneous small pieces in the vast chaos of the digital world. I makes sense about that totality in every question we ask of it. It's the room that includes everything that's too big for us to know.

But here's the rub: Big AI also doesn't know a damn thing. It recognizes patterns in a vast totality of data and uses programming and language to answer questions and perform tasks for the human inhabitants of its environments.

Think about what's in the rooms built by OpenAI (ChatGPT), Google (Gemini), Microsoft (Copilot), Perplexity (Perplexity AI), Anthropic (Claude), DeepSeek (DeepSeekAI), and Grok (Xai).

The short answer is everything. All of the Web, all books, all utterings on social media, you name it. Everything explicit, that is. Nothing tacit. It doesn't have tacit knowledge because it's not human.

We need a word for that everything. Here are some candidates (with minimal AI help this time):

• Akasha: (Sanskrit) The aether or mystical compendium of all human events, thoughts, words, emotions, and intent ever to have occurred. Perhaps a poetic synonym for a universal database.
• Pleroma: (Greek) "fullness," totality of divine powers, or the sum of all knowledge.
• Pantology: (Greek root?) The systematic view of all human knowledge.
• Wànwù: (Mandarin: 万物) Literally "the ten thousand things." It's used to describe the entirety of the universe and all its manifestations. It's a beautiful way to describe the sheer variety of data I hold. (Says Gemini, when I asked for a word in another language to encompass what it "knows.")
• Sylloge: (Greek) Collection, compendium, summary, digest.

I vote for akasha.

What's in all those companies' akashas are not databases. Instead they are trillions of "tokens," which (as NVIDIA explains here) "are units of data processed by AI models during training and inference, enabling prediction, generation, and reasoning." These are not structured in ways familiar to us in the natural world. They are also not sources like those Google used to index and treat as directories. They are opaque to us. Every AI data center is a black box in material form.

Marshall McLuhan taught that every new medium, every new technology, creates an environment that changes us. What we are as drivers in the rolling carapace we call a car is not what we are when we are walking around. We are changed. Extended. Enlarged.

Big AI does some of that for us, but we don't have truly personal AI yet. That's a whole 'nuther rant (going on here). But after we get personal AI, we'll still be radically changed. Which brings us to—

III.How AI dependence is changing us from homo sapiens to homo ________

When I asked ChatGPT to "tell me what to name the AI-dependent species that succeeds homo sapiens," it gave me this (which I've abridged into a less wordy form):

• Homo delegatus. The delegating human. Clean. Roman. Almost bureaucratic.
• Homo auxiliatus. The assisted human. Gentler. Less tragic.
• Homo symbioticus. The symbiotic human. Optimistic framing. Mutualism implied.
• Homo prostheticus. The prosthetic human. From prosthesis — extension. Suggests cognition extended outside the skull.
• Homo algorithmicus. The algorithmic human. Likely to stick. Slightly dystopian. The defining trait is AI reliance.
• Homo automatus. The automated human. Bleaker.
• Homo machinatus. The machinated human — shaped by machines.
• Homo instructus. The instructed human — guided by systems. The defining trait is epistemic submission
• Homo credulus. The believing human. Short. Dangerous.
• Homo confisus. The trusting human. Ambiguous — trust can be good or naive.
• Homo oracularis. The oracle-dependent human. Strong mythic tone.
• Homo synthetica. The synthetic human. Hybridized.
• Homo copulatus. The coupled human.
• Homo nexus. The networked human.
• Homo cyberneticus. Classic mid-20th-century feel.
• Homo exocerebralis. The external-brained human. Scientifically plausible.
• Homo delegans sapiens. The wisdom-delegating human.
• Homo post-sapiens. Simple, brutal.
• Homo paragnostica. The mis-knowing human.
• Homo servomechanicus. The servo-mechanical human.
• Homo dependens. The dependent human.
• Homo exocerebralis. External-brained human
• Homo delegatus. Delegating human
• Homo symbioticus. Symbiotic human
• Homo algorithmicus. Algorithmic human
• Homo exocerebralis. It names the real shift: the brain extends beyond the skull into networks and models. Biologically grounded and conceptually sharp.
• Homo delegatus. Has quiet menace.

I don't like any of them. But we need one. Vote on one of these, or give us a better alternative.

IV. How we can stay human in the midst of it all?

First, stop the surveillance. That will at least begin to restore and protect our humanity.

We can't do it all at once, but we can do it through relationships with organizations that don't participate in the surveillance economy. There are a lot of those.

These can't be relationships that organizations initiate. We got that kind when industry won the industrial revolution, and they have infected the digital world with endless "consent" (non-) agreements and "Our terms have changed" gauntlets requiring acceptance of terms we don't read and don't matter.

We can do it with agreements that we proffer, as sovereign and independent human beings. And now we have a standard for that: MyTerms (7012-2025 - IEEE Standard for Machine Readable Personal Privacy Terms). These will allow us to visit sites, use services, and buy stuff without worrying if we're being tracked like marked animals by parties unknown. They will also form a solid base for additional relationships based on mutual trust.

That's the second step. Both are tabula rasa today. But if we want to keep from turning into any of the many species listed above, we need to start with ourselves and our relationships with willing second parties. MyTerms will do that.

__________________________________

*My minimal and pathetic drug history:

• I was never more than a casual drinker, though I do like dark beers and good wine. I also stopped drinking anything a few years ago.
• I've never taken LSD, shrooms, or any hallucinogen.
• The first time I took cocaine was at a party in the North Carolina woods. When nothing happened, the guy who gave it to me said, "Well, maybe ya'll's personality masks the effects." The second time was when a friend and I wanted to stay up late to watch the first round of March Madness. The third time was to stay awake on a very long drive. The fourth and last time was to stay focused through an all-night conversation with an old friend. Afterwards, I felt like I might die and had no perception of color. After that, I never touched cocaine again.
• The only time I ever took ecstasy was with old friends. It was beautiful. Their dog said to us, "See? This is what it's like to be a dog! You love everybody!
• I never smoked tobacco, and only smoked weed a few times. One of those yielded the one-liner I shared above. Another caused such intense pain behind my right eyeball that a bit of it recurs every time I smell weed.

Cycloptery

Seventy-two hours since my cataract surgery and nothing is better. The cornea of my left eye is still swollen and I'm essentially blind (meaning my vision is 20/infinity.  It also feels better closed than open, which I'm not sure is a good thing. I'm still wearing a bandana over it. My surgeon says relief will gradually come in a few days. I eagerly await. Meanwhile, if you're depending on me to get work done (and there is lots in my queue), have patience.

Now, let's try that with a human body part

Tom's Hardware: In a blind test, audiophiles couldn't tell the difference between audio signals sent through copper wire, a banana, or wet mud — 'The mud should sound perfectly awful, but it doesn't,' notes the experiment creator.

Towers

I love to look at them, know what they're for, and (many decades ago) climb them. Places where I write about towers and post photos of them:

• Trunk Line, my blog about infrastructure
• Nfrastructure, my Flickr collection of infrastructure photos (most of which are about broadcasting and transmitters)
• This subset on my main Flickr collection
• All these (121 of them), posted on this very blog

Consider all of them a long love letter to the now-gone golden age of broadcasting. I want future historians and archivists to remember what broadcasting was and how it worked before digital tech absorbed and obsolesced it. Long may it wave.

Stories

I Love Girl, by Simon Rich, in The New Yorker. It's worth getting a subscription just for that one story.

Boom!

What Happens When You Put AI in the Hands of a 73-Year-Old Grandmother, by Frances Flynn Thorsen, @blogmother on her Substack blog. Hats off to the real estate conversation led by Bill Wendel of RealEstateCafe and happening here.

Cyclops time.

Thirteen years ago, when I was just entering the final demographic, I had the cataract in my right eye replaced. It was a quick and easy procedure that left me with 20/10 vision when I walked out the door of the surgery center. It's still that sharp.

Which is good, because this morning I had the cataract in my left eye replaced, and now I'm blind on that side, at least for now. In retrospect, I should have had both cataracts replaced way back when I had the first one done. I didn't then because the cataract in my left eye wasn't bad, and that eye could still focus. Vision on that side was 20/25, and I could use that eye to read as well, meaning that most of the time I didn't need glasses. 

But, because I waited, the cataract in my left eye gradually turned brunescent, meaning brown. This required an extra $2050 for Femtosecond Laser-Assisted Cataract Surgery (FLACS), which isn't covered by Medicare.

Anyway, the surgeon had to turn his emulsifying machine up to 9 (normal is 3) to demolish the old brown lens. This, plus the antiquity of my cornea, caused it to swell, so the world to my left eye is now just colors and shapes. If all goes according to plan, this will gradually go away. Meanwhile, no driving, no lifting heavy things, and hopefully no new regrets.

Advice: If you do have cataracts, don't wait around. Get them done.

Surveillance pricing already has its own page in Wikipedia. It also has its own authority: Abbey Stemler, Associate Professor of Business Law and Ethics and Weimer Faculty Fellow in Business Law & Ethics at Indiana University's Kelly School of Business. And she'll be speaking about her work a week from now:

As you see, she'll be speaking in both the natural and the digital worlds, so you can join us on Zoom if you're not in the former. Meanwhile, put it in your calendar: February 19, 4 PM Eastern.

_______________

Top image above are by Google Gemini and Adobe Photoshop, with some help.

Recommendations?

My (guessing) seven-year-old LG 5K Ultrafine 27" display has become flaky. Repair estimates run into many hundreds, so I need a new monitor. Currently, I'm browsing Apple 5K Studio Displays on eBay. Saves me several hundred dollars from the $1599 Apple Store price.

Book them now

Early bird tickets are on sale for the 42nd IIW, which began on a Gillmor Gang podcast the last day of 2004. In my biased but correct opinion, IIW is the most leveraged tech conference on Earth. This one will happen on April 28th to 30th, Tuesday to Thursday. But for the full experience, block out the whole week, so you can catch to catch VRM Day on Monday the 27th, and the Agentic Internet Workshop on Friday, May 1. All will be at the Computer History Museum in Silicon Valley.

MyTerms will be a wide weave (not just one thread) of conversation through all three events, each of which are open space: no keynotes, no panels, no booths. It's all breakouts gathered around work and conversation toward outcomes. 

Song du jour

Time Loves a Hero, by Little Feat, which is incorrectly stil absent from the Rock & Roll Hall of Fame.

Assholes

Literally.

Remembering when radio was radio

Nice write-up on one of the greatest radio stations ever: WQDR/94.7 in Raleigh, during its album rock era, which ran from 1971 to 1984, as I recall. My own involvement (as a creative director for the station's ad agency) ran from '78 to '83 or so. (Hard to nail the dates down, because many good friends worked there and I we all hung out a lot. 

As a side thing, it's worth noting that the big FM stations in that part of the country have a lor of range. WQDR when hung out there, was 100,000 watts on a 1200 foot tower, wth a signal that stretched from Winston-Salem to Greenville. On hot summer morning, you could get them from the mountains to the beach. Earlier, when WRAL/101.5 was a thousand feet up the WRAL/5 tower, it was 250,000 watts and bragged about being audible "from Hatteras to Hickory." Later, it dropped to 100,000 watts at close to 2000 feet, on the new WRAL/5 tower, which was dropped by ice in 1989. Both WRAL and WQDR are close to the top of the replacement tower today, when most of us aren't listening to radio on radios anymore. We're getting streams and podcasts on our phones. Only some of that comes from radio stations, and most radio stations lack local talent and programming. Telle est la mort.

Which always creeped me out, but he has a case

Don Marti is a (somewhat provisionally, but still actually) fan of rewarded interest.

I lost the spreadsheet.

Have you ever totaled up the costs of all the things you subscribe to?

More in the general than the specific senses.

This post from 2009 turned out to be prophetic.

About what's on.

NiemanLab says public radio is playing an important role in covering shit that's going down.  Note: public radio in the Minneapolis-St. Paul Market has a 15.5 share. That's very good. 

Here's what I wrote about public radio numbers in 2019. Back then, Santa Barbara kicked ass with a 23.4 overall share. It still does, with a 24.8 share. (Shares are percentages of total listening.)

Or both Monday and Tuesday?

If Saturday and Sunday are the weekend, why not call Monday the Weekstart?

Super. Bowles a strike. Against ChatGPT.

This is brilliant.

Here's a bonus post from the reliably contrary Gary Marcus.

Reduxion

Traffic to this blog went up an order of magnitude when somebody (not sure who, or what), drove traffic to this post, which I put up 10.5 years ago. It was good and right for that time in history, which is much worse now.

Kill the lottery

I have a simple suggestion for getting rid of tanking in pro sports.

Hope he gets the hat tip

Progress is the process by which the miraculous becomes mundane. Aviation, for example. At  any moment a million people across the world are airborne and traveling safely. (Stop now and watch this bit by Louis CK. Yes, I know he's been canceled, but the bit is brilliant.) So yesterday, we flew from North Eleuthera (ELH) to Indianapolis (IND) by way of Atlanta (ATL), all on Delta (though the first flight was on Delta Connection). It all went better than well. The first flight was clear all the way, with excellent views (for me, the devout window-sitter and scene-shooter) of several Bahamian islands, coastal Florida, and Georgia from Savannah to Atlanta. The second flight wasn't the near-midnight one we were scheduled on, but one we noticed, while passing the gate in late afternoon, was boarding for Indianapolis. They gave us the last two seats on that plane, and it got us to Indy in time for dinner at Iozzo's, one of our favorite restaurants. Nice!

Then this morning, I got a survey from Delta. I tend to fill those out if I've had a very good or bad experience. But surveys still suck, because they're not human, meaning not conscious or aware of their existence. They're a pro formality that paints pictures with numbers. But I did want one human rewarded, so I filled it out. The human was Isaac, or something like that, on the second flight, Delta 3120. When the drink cart came by, I asked for a cup of ice. He said they didn't have any, and gave me a bottle of water, which was fine. But later, without being asked, he brought me a cup of ice anyway (presumably from the business class ice bin). That was nice and worth a mention.

The Oligarch Giveth, and The Oligarch Taketh Away

The Guardian: 'It's an absolute bloodbath': Washington Post lays off hundreds of workers—Former Post executive editor blasts owner Jeff Bezos's 'sickening efforts to curry favor' with Trump

That it's bad

Reason says Trump's wanting to nationalize elections (when he and the GOP are in full power) is not only unconstitutional and wrong on other grounds, but similar to something the Democrats wanted to do five years ago. Looks different to me, but I kinda get their point.

Sounds right enough

Axios: 1 big thing: 3 historic shifts. It begins,

"You can only fully understand politics, business and your own anxiety in 2026 by reckoning with the three, once-in-a-generation shifts unfolding at once, Jim VandeHei and Mike Allen write in a "Behind the Curtain" column:

• The ideologies, tactics and tone of governance.
• The lightning-fast advancements in AI.
• The overnight transformation of how our realities are shaped."

Story Bowl

I'm a Patriots fan who was pained for the Seahawks when a bad play call (blame coaches) snatched defeat from the jaws of victory the last time the two teams met in the Super Bowl. So I won't be too bummed if the Seahawks win this one. The Revenge Bowl will be a good story. So will the Redemption Game story for Sam Darnold. But there are good stories for the Pats as well. The MVP story for Drake Maye. The Huge Turnaround story for Mike Vrabel. The Nobody Believes in Us story for the team. My expectation: Patriots by less than a touchdown.

Without losing its charm

I am in Harbour Island, where all the old houses have shutters. The house where we're staying is a small cottage built in 1832. It has survived countless hurricanes.

Remember Her?

Moltbook is a Reddit for AI chatbots. NBC: Humans welcome to observe: This social network is for AI agents only. Wikipedia. Google. Bonus link.

Yesterday, Customer Commons and MyData Global launched MyTerms at a London event correctly titled The Only Way to Get Real Privacy Online. (I explain only and real at that link.)

MyTerms is the nickname for 7012-2025 - IEEE Standard for Machine Readable Personal Privacy Terms. Links:

• The home page. Note the little unlock symbol on the left, next to the word "free." That's because MyTerms is part of—
• The IEEE's GET Program for AI Ethics and Governance Standards. Below is the 7000 series of standards, of which MyTerms is the latest one. All are free.
• The published standard, finally available to anyone. It's easy to navigate if you click on the outline symbol in the left panel.

The text of the standard has a lot of prerequisite formal stuff up front. Here are the main parts:

• The Introduction, starting on page 8.
• Sections 4 and 5, starting on page 14.
• The top Annexes, starting on page 21

Note that the Introduction and the Annexes are informative, meaning not part of the standard itself. Between them is the normative, or operative, part of the standard.

The standard itself is simple. Here is a diagram that predates the one in the standard, but says the same thing:

This is how it works:

1. The person, acting as the first party, proffers an agreement to an entity (website, service, or organization of any kind), acting as the second party. The agreement is a contract. Note that the person here is neither a "user" nor a "client," but rather a self-sovereign human being operating at full agency.
2. The agreement chosen is one of a short list posted at the website of a neutral nonprofit, such as Customer Commons. This is on the Creative Commons model. MyTerms is to personal privacy agreements what Creative Commons is to personal copyrights.
3. On the Creative Commons model, agreements are readable by ordinary folk, by lawyers, and by machines. MyTerms addresses the third of those.
4. This ceremony is conducted by agents on both sides. These agents can be as simple as browser and web server plugins, or as fancy as personal and corporate AIs. The standard leaves these choices open.
5. Both parties keep identical records of the agreement, for compliance auditing and dispute resolutions, should those needs arise
6. The first party can also keep a record of which second parties passively or actively don't agree.

Obviously, this obsolesces cookie notices, and establishes much more solid grounds for relationships between people and organizations, customers and companies, demand and supply.

If you want to dig wider and deeper, here are three textual sources:

• My writing
• Iain Henderson's writing
• Nitin Badjatia's writing

And here is the MyTerms video collection at YouTube. We have two so far:

• Yesterday's event in London and online
• A five-minute background on MyTerms, explained by yours truly
• While listed elsewhere, The Case for MyTerms is a talk I gave last November at Indiana University as part of our salon series there.

There will be more. I look forward to not being able to keep up with all of it.

If you want to get involved, Customer Commons is forming the MyTerms Alliance. More at that link.

If you want to join the conversation space out of which both Customer Commons and MyTerms were spawned, join the ProjectVRM mailing list, which has been going since I set it up as a new fellow of the Berkman Klein Center at Harvard in 2006. The entire archive is here. And we thank the BKC for its extreme patience with what began as a one-year project.

You're welcome

NASA: Asteroid 2024 YR4 will certainly miss Earth and has a 96.2% chance of missing the Moon. I share this in faint hope that when one sees BS on Facebook, Instagram, TikTok, or social media wherever saying the asteroid is going to have a spectacular impact on the Moon, they'll know it's BS.

From a Santa Barbara I Madonnari (street art) festival

We still await truly personal AI.

Google just launched Personal Intelligence. "Get highly personal help with everything from vacation ideas to project plans, and more. Gemini connects the dots across your Google apps—like Gmail, Photos, Search, and YouTube—and your chat history preferences to provide suggestions tailored to your world."

That should be called personalized, because it's not yours. It's Google's.

Oh, and this

Privacy | The dark age of surveillance capitalism, by Prasanto K. Roy in India Today. His point: Besides gathering huge amounts of personal data just by talking to you, Big AI can improve personal data extraction from other ordinary activities online, then interpret and use it to manipulate people, based on what's known by opaque and unaccountable systems.  For example, "Surveillance pricing is a thing once that dividend moves into the normal economy. Ride-hailing apps can charge you more if you use an iPhone, or have very low battery, and desperately need a ride."

Just what you didn't ask for

Show of hands: Does anyone here want ads on ChatGPT? (Don't raise them if you work in the ad biz.)

Did you want them in Amazon searches? How about Google's before that?

Expect ChatGPT to become just as enshittified.

And now, naturally, we have ICE Explores Big Data, Ad-Tech Tools to Power Investigations. Why? "ICE said it is primarily interested in how technology solutions can help identify individuals, entities, or locations." Also, "Ad-tech location data is collected from apps, websites, and connected devices. It is then aggregated and sold by data brokers for uses beyond advertising, including analytics and research."

National Weather Service Snowfall map.

Boston wins

We had some deep snows when I lived in Arlington, Mass (next to Cambridge), but nothing quite like the thick  blanket of white that got dumped on the Boston metro two days ago. The screenshot above is part of an NWS snow-depth map that will soon age out. So enjoy it while you can.

Meanwhile, here in Bloomington, Indiana, the 14.5 inches we got from the same storm had me and my car isolated until Joe, the guy who built our house, came by with his front-loader and cleared the whole road in about five minutes.

Here is a FlightAware MiseryMap video of the storm's path across all the airports it closed:

And I'm glad he did

The Brothers Comatose and Sweet Sally nail Bob Dylan's Don't Think Twice, It's Alright. Their performance is so good that I got to thinking about how passive-aggressive the lyrics are. Then my mind wandered to Positively 4th Street and Like a Rolling Stone. I thought, "Man, Bobby sure had a lot of problems with people."

Saved some time

The problem with online sports gambling is that steady winners get cut off. I was going to say a bunch about this, but just remembered that I did that already.

What is the opposite of criticism?

On a lead from a friend, I followed a thread from this patent to its author, Brian Dear (another friend), then to his about page, his old blog, his BlueSky tweetings, his bandcamp page, his lettrboxd page, then to his criticism of Megan McArdle and the WaPo, and (not finally) to the work of critic A.S. Hamrah, whom Brian likes.

All of that brought me to a self-admission: while I love and value criticism of many kinds, I am not a critic, because criticism tends to be about current work, people, and goings on. It's not that takes on that stuff are wrong or bad. On the contrary (speaking critically), they can be very good. It's just that I'm a long-term / long-view guy. As i said in My Three Hooks, I have, and subscribe to, purposes that are (or I hope or trust will be) good for the world. I also like unanswerable questions. If there is life after death, were you alive before your current bodily existence—and shouldn't we have a word for that? What came before the Big Bang? What is eternity—and can we unbind it from the concept of time? Is life the exception to death—and can it be, if death is not a state but the absence of one? And…

These aren't relevant to anything below. But they were tasty, two weeks and two thousand miles ago.

Clobbering tourism, sports, higher ed, and all tech conferences

Privacy International says "The U.S. Government intends to force visitors to submit their digital history and DNA as the price of entry." The proposed changes are here. Particulars from the piece:

The changes include:

• All visitors must submit 'their social media from the last 5 years'
• ESTA (Electronic System for Travel Authorization) applications will include 'high value data fields', 'when feasible'
  • 'telephone numbers used in the last five years'
  • 'email addresses used in the last ten years'
  • 'family number telephone numbers (sic) used in the last five years'
  • biometrics - face, fingerprint, DNA, and iris
  • business telephone numbers used in the last five years
  • business email addresses used in the last ten years.
• All these travellers will now have to use an app provided by CBP ('CBP Home') and an app for their ESTA application ('ESTA Mobile App'). The ESTA website is being decommissioned.
• The 'CBP Home' mobile app will be used by people to provide biometric proof of their departure, to 'close the information gap'. The app will disclose the user's location once they have left the U.S. and run a liveness detection on the selfie photo.

If approved, this policy would apply to all visitors who currently travel without a visa. For the estimated 14 million annual ESTA travellers, CBP thinks that this will take the average visitor 22 minutes to submit themselves and their family members.

That is smart

Why Intelligence Is a Terrible Proxy for Wisdom, by Joan Westerberg, says "Wisdom is knowing what you don't know."

Because we need to save the Web from AI overviews

I've read The Domain Name's New Role in the AI Web, by Simone Catania, several times, and know there's even more for me to get out of it.

So call it a https://www.privacyinternational.org/news-analysis/5713/trump-administration-wants-your-dna-and-social-media

Netflix is pitching their new talk videos as "podcasts." They are not. If you want to know what a podcast really is, go to the blogfather: Dave Winer. Says Dave, "A podcast is a series of digital media files made available over the open web through an RSS feed with enclosures."

We need a word for what Netflix is pitching. When I posted Podcasts, Wallcasts, and Paycasts back in October '24, audio that was also video wasn't common. Now it is. We have almost reached the point where a podcast isn't a podcast unless it's also in video.

On that post, I said, "For subscription-only 'casts, such as some on SiriusXM*, I suggest paycasts." And, "Bottom line: It can't be a podcast if you have to pay for any of it, including archives." Netflix isn't free. And it's not on the open Web. I also don't know if it uses RSS. But it still fails to fit the definition of a podcast.

Preach!

Because you haven't yet heard everything about Fernando Mendoza and the Indiana Hoosiers, I give you Mason Whitlock's take.

Snow 'nuf

My watch told me it was  minus-1° when I woke up this morning, just like it was a year ago today. There's 14.5″ of snow on the ground, and I need to go shovel a sidewalk that's 200 feet from here. For footwear, all I have are a pair of old hiking boots, which only go up to the ankle. I unloaded my nice calf-high Columbia snow boots last Summer when I left New York, because I had to purge 95% of my accumulated possessions there, and just take what fit in my small VW wagon.

So, between the last paragraph and this, I waited until it was a balmy 9° and trudged up there. One of our kind neighbors had already cleared paths on the sidewalk and to the front porch. I widened the sidewalk, then tried to expose as much of the concrete surface as I could. Stopped when I couldn't feel my fingers (the gloves aren't great), and left satisfied. At 78, I've still got (some of) it.

Go now to FlightAware's MiseryMap. Cick on the blue Play button and watch The Great Storm of January 25-26 move across the land and cause massive delays at airports in its path.

I have a 1.59 GB movie (.mov) of what you just saw. What should I do with it?

Bonus image:

Still falling

Snow is the only thing I like about Winter.  I grew up on a hill in New Jersey, and sledding down that hill while school was canceled was a huge thrill for me. I see by my stats that I've written 179 other posts about snow. 

And it's snowing now. Forecasts say one to twelve inches. So far, we've achieved the former.

I'm alone here, but well provisioned. If the snow goes above eight inches, I won't drive on it, even though I have all-wheel drive and new Michelins that are good for snow. Last year, I gleefully plowed over and through the deep stuff, and misaligned the radar sensor, which is exposed low and inside the front grille. (See here.) Fixing that cost $1200. 

Remembering Ransom Love

Steven Vaughan-Nichols on LinkedIn shares news that Ransom Love has died. Ransom was one of the kindest, sweetest, smartest, most helpful, good-humored, and humble sources I ever had during my 24 years writing for Linux Journal. And our connection went back farther, through his years with Novell in the early '90s. It was a blessing to know him in life and remains one to remember him now. My best to his friends and family.

What emerges?

You know how Google's original  (and continuing) mission was "to organize the world's information and make it universally accessible and useful"? It didn't happen with Google. Gemini gets closer. So I'm thinking, if search was the larval stage, and now Gemini is the pupal stage…

MyTerms is done and ready to begin.

The launch is next Wednesday, in the room above at Imperial College London.

Back in '22, I called MyTerms (IEEE 7012) The Most Important Standard in Development Today. Now it's finished and more important than ever.

Join the launch. Times:

4 PM GMT
11 AM EST
8 AM PST

You don't have to be in London. It'll happen live online too. But if you're lucky to live, work, or hang within a train ride or few, please do come.

Register—

To attend in person

To attend online

See you there!

After I wrote the first item below, I did some digging and found some history. This photo is by Mike
Fisher on Flickr. Thanks, Mike!

His story

A thousand years ago, when I was in college, there was a traveling museum of some kind, I forget what. All I remember was a pair of very large bronze hands, from a plaster cast. The hands were thick and plainly those of man whose work was heavy manual labor.

Then I looked at the plaque explaining them. The hands were Lincoln's.

See a 3-D view, with call-outs, at the Library of Congress.

Nothing personal. Yet.

The Resonant Computing Manifesto: "And so, we find ourselves at this crossroads. Regardless of which path we choose, the future of computing will be hyper-personalized. The question is whether that personalization will be in service of keeping us passively glued to screens—wading around in the shallows, stripped of agency—or whether it will enable us to direct more attention to what matters."

That sounds like computing is still corporate. Institutional. For us, but not ours. From Personal vs. Personalized AI:

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."

Two years later, it still isn't. Yes, there's progress. And there are pockets. Companion Intelligence is one example. (Looks like a Mac Mini without Apple.)

We'll see

Prophesy: Indiana in 2026 became to college football what Duke in 1991 became to college basketball.

How Bloomington it is to stock up on greens?

Consumageddon is here: 5 inches of snow is coming. We're all gonna die folks.

And how can this go well?

YouTube plans to let creators make AI Shorts using their own likeness.

That right?

This is a slash: / This is a backslash: \ One can call the former a forward slash, but when telling people a URL, for example, one would say "slash." That's two syllables less than "forward slash."

I hope the answer is no

In 2006, when Twitter and Facebook came along, this blog (well, its predecessor, but it was my eponymous blog, and it rolled over to this one) had dozens of thousands of readers per day. Now it gets dozens. (And thank you!)

Here's the thing. Twitter and Facebook didn't just suck away attention and readers. It sucked away writers. So many great bloggers went over to those two social platforms, and abandoned their blogs.

Now, blogging (personal publishing, syndicated with RSS) is having a resurgence. But on Substack, not on personal sites like this one. Not yet.

I am sure my readership would go up into the thousands again if I blogged on Substack, but I don't want to. Here's why: this is a home. And it's mine. I'm not in somebody's walled garden.

Am I wrong to have faith that independence will, in the long run, have more appeal (and effect) than dependence?

Which is happening, but how much will it produce?

Dana Blankenhorn says Big AI is now a commodity, and that doesn't look good for OpenAI. ChatGPT's market share is slowly yielding to Gemini and Claude, but still dominates.

But I wonder about revenue. Google's cash cow is advertising, especially with the search engine, usage of which is being cannibalized by Gemini. Will the whole world start paying for commodity AI? Only if all of them put up a paywall.

Humbling

Searches for my ass.

An aurora I enjoyed on a flight between the US and Europe a few years ago.

Be ready the next time the Sun burps

It was overcast here in Indiana, but there is a good chance that auroras were visible the last couple of nights where you live, thanks to a big coronal mass ejection. Examples: Arizona, New Jersey, Pennsylvania, Long Island, Texas, Brazil (see the "south Atlantic anomaly," here).

Your irregularly nonscheduled blogging program will continue returning shortly. Or at length. We'll see.

Woke up with a case of nausea and uselessness this morning. Took all day to get back to something like normal. And here we are, sort of. Cue Frank.