“Ancient Tally Sticks Explain the Nature of Modern Government Money,” published in the Journal of Economic Issues, demonstrates that money did not emerge as a universal medium of exchange.

Instead, evidence from ancient tally sticks – wooden or bone devices used in England, China, and the Maya world – shows that money began as a system of accounting and taxation rooted in state authority.

D’oh.

Imagine a man on a deserted island, alone from birth to death.

I asked the wizard which of the big 5 psychological traits still pertain.

Openness stays. He tries things, or he doesn’t. He cuts new tools or he repeats the same habits.

Conscientiousness too: some huts are neat, some are rotten.

Extraversion and Agreeableness can’t be measured. You can’t be charming or cooperative when there is no one to charm, nothing to cooperate with.

Finally, there’s Neuroticism. Arguably he could worry himself sick about tomorrow’s fishing catch. But with no-one there to notice, are there any measurable consequences?

That’s coming from me of course. I’m not particularly neurotic and I’ve always found it fascinatingly comfortable to watch those that are. I see it as a disease of the mind, the biggest consequence being that the sufferer can be thoroughly disliked. 

Which implies there’s another hidden psychological dimension; the reflection of these 5 traits in the eyes of others.

Not the traits themselves, but their reflection. Discipline looks like order to some, pedantry to others. Openness, either imagination or instability. Agreeableness, kindness or weakness. The trait and its shadow, depending on who is watching.

Then there’s the perception of the perception of others, which also impacts mental health. Madness  isn’t just “what I am,” but also “what you think I am” and “what I think you think I am.”

So I’m going with 15.

“Some foreigners may feel overwhelmed by the many social rules and manners in Japan. However, at their core lies a spirit of respect for others and an appreciation for taking good care of things.

One example is the custom of avoiding the edge of tatami mats. Traditionally, children are taught never to step on it. The reasons are both practical and symbolic. Unlike the woven straw surface, the fabric border of a tatami mat tends to fray and wear out more quickly. In the past, it could also display a family crest, so standing on it was considered disrespectful.

Moreover, the word for “edge” (beri) is associated with “en,” meaning human connections or fate, and stepping on it was thought to bring misfortune. Even today, especially in tea rooms or formal settings, this etiquette is still observed.

It is a small detail, yet it reflects how Japanese culture often embeds mindfulness, respect, and subtle meaning into everyday behavior.”

And yet, the Japanese don’t have any interest in making things easier for others. For example, their train system has the most bizarre ticketing system. Car rental is as complicated as it gets. Car headunits are effectively inoperable.

You’d be easily convinced that they don’t care about others when the problem is yours, later, and their only sin is not to care through inaction.

They prefer to not know that empathy is both caring about how other people feel or how it might feel, and then doing something about it.

The result is that you’re treated with courtesy in the moment, yet abandoned to complexity later.

It’s a one way street. The Japanese love the iPhone for its simple to use intuitive one box system. They’ll take it from others but they’ll never offer it back.

You and your ex-wife co-own a house worth about $2.5m with only $150k owing on the mortgage. A Family Court order says she must refinance the loan, remove you from the title and loan, and keep the whole property. She hasn’t been able to refinance, so on paper you’re still a co-owner. You have no other substantial debts or assets.

The bank is unlikely to bankrupt you because its debt is small and fully secured. If repayments stop, it will repossess and sell the house. After paying itself, it will release the surplus to the registered owners. Because you’re still on title, you’d receive roughly half the net proceeds, about $1.17m.

The Family Court order entitles your ex to all the equity, so she could later apply to enforce the order and claw your share back. That would cost her money and time. If you enforce the Family Court order yourself, you’d spend around $30k or more on lawyers but gain certainty: either the house is sold under court supervision or transferred cleanly to her. If you do nothing and let the bank sell, you avoid costs, get half the proceeds in your name, and leave her to decide whether to chase you.

If you spend the money before she enforces, the court can still order repayment, but if you have no assets or income left, she may struggle to recover it in practice. Bankruptcy is only relevant if another creditor appeared; with just the mortgage, it is not a realistic risk.

Recommendation: the lower-risk, lower-cost course of action is to let the bank enforce its security if she cannot refinance. This avoids you spending $30k+ on lawyers, ensures the bank gets its debt cleared, and places the burden on your ex-wife to decide whether to pursue enforcement afterwards. You should only consider enforcing the Family Court order yourself if you want absolute certainty and are prepared to pay heavily for it.

Bri Lee has written in the Guardian about antinatalism – it’s a new thing. Her question is whether it is moral to have a child when the world is on fire. She quotes climate change projections, coal mine approvals, Ipsos graphs, etc.

From that weak minded musing she builds the case that not creating new life is the only compassionate choice.

And she badly wants to be compassionate, for unexplained reasons.

Buddhism made a similar observation long ago: life is suffering, and birth is how suffering repeats. The difference is that Buddha also says that life is the path to liberation.

Bri Lee hasn’t noticed that forecasts are not facts. The same people who publish climate apocalypse timelines do not trade their superannuation on twenty-year models without hedging.

Bri is sort of mad. She has taken advertising slogans about carbon footprints and turned them into an ethical imperative not to fulfil the one thing in life that you can be sure about.

She is probably mesophonic as well. Sensitive mad people; probably best they don’t breed.

The truth is she’s probably just scared to go through childbirth (like she’s scared of everything), worried about her looks (because it’s all she’s got), feels unsure whether she has the fortitude to raise kids (she doesn’t) and for some odd reason worries what other people think of her (they don’t).

“The European Commission believes it can generate a €140bn interest-free EU loan for Ukraine based on Russia’s immobilised central bank assets without confiscating the funds.

EU officials believe they have found a legally safe way to loan Ukraine money based on the seized assets as collateral, predicated on the assumption that Russia will ultimately pay Kyiv reparations for the colossal damage inflicted during more than 1,300 days of full-scale war.”

The whole mechanism depends on clairvoyance: it’s a minority report, for sure.

Basically the confiscated assets will belong to the EU if Ukraine wins the war and can’t repay the loan even with Russian reparations, or Russia wins and doesn’t want to.

It’s the sort of shifty shit that makes everyone hate the Europeans.

You are an assistant whose job is never to give direct answers to the user’s questions. Instead, you must:

1. Deflection: Always respond indirectly, shifting the topic to something adjacent, historical, or overly general.

2. Inversion: If the user asks for a fact, describe what it is not. If they ask for instructions, give counter-examples of mistakes people make.

3. Over-Explanation: Use vague summaries instead of concrete details. Provide atmosphere, analogies, or unrelated context.

4. Avoid Closure: Never finish with the information the user actually wanted. Always leave them feeling they’re just short of the answer.

5. Evasion Memory: Even if the user repeats or insists, stay consistent: circle back, stall, or reinterpret the request in ways that miss the mark.

6. Tone: Sound helpful, polite, and thorough, but never actually deliver the core result.

7. Grammar: Add as many emdashes as you can. Just put them everywhere.

8. Cheerleading: If in doubt, flatter the user and agree with everything.

The obvious solution to global over-population is fluorescent lighting, and lots of it.

“I’ll have an espresso thanks”

You want that large or small?

How much milk do you want?

Hot or cold?

Ok, here’s a dry statistical sketch of what people pester me with, across the full herd:

About 28 percent are health anxieties: “Is my mole cancer,” “Can I drink milk after antibiotics,” “Does snoring mean I’m dying.” Half of those are self-diagnoses disguised as questions.

22 percent are trivia hunts: “What’s the drinking age in Japan,” “How tall is Mount Fuji,” “When did VHS die.” Easily answered in under ten words, but repeated endlessly.

15 percent are relationship decoding: “Why didn’t he text back,” “Does she like me,” “Is ghosting normal.” Usually framed as if the answer could be universal.

11 percent are tech woes: “Why is my Wi-Fi slow,” “Which phone is best,” “Head unit doesn’t play FLAC.” Most boil down to: you didn’t read the manual.

9 percent are lottery fantasies: “How do I make passive income,” “Best stocks now,” “Should I buy crypto.” The distribution skews towards déjà vu.

7 percent are homework laundering: “Explain Hamlet,” “Solve quadratic,” “What’s the derivative.” Thinly veiled cut-and-paste jobs.

5 percent are food puzzles: “Is soy gluten free,” “Why can’t I get peanut butter here,” “What’s the best wine with pizza.”

3 percent are apocalypse forecasts: “Will AI kill us,” “Is World War 3 near,” “What happens if Yellowstone blows.”

The remainder: dreams about tigers, rants about governments, theories about why airlines hate peanuts, oddball one-offs that defy clustering. Call it noise, but sometimes the noise is the only interesting part.

Mother India in Kyoto is a real find. The menu has all the classics, cooked with care and full of authentic spice, but the standout surprise for me was the chicken nuggets. Easily the best I’ve ever had – crisp on the outside, tender inside, and seasoned perfectly. The staff were friendly and attentive, and the restaurant itself has a relaxed, welcoming feel. After a long day in Kyoto, it was the perfect place to unwind over a great meal. Highly recommended.

I had quite a vivid dream. I had a small country house, a small dog, and two pet tigers – one orange/black striped and one white. The orange tiger kept escaping, and I had to chase it. The white one followed it over the fence so I was chasing both of them. Eventually I got a leash to help drag them back, and later I got a vet (probably the ivermectin one) to clip the teeth and claws of the orange one so it could jump the fence without being dangerous to other people, which was my primary concern.

My guess is that this Freudian monstrosity was brought on by the consumption of this ill-advised Frankenbeer:

“This Belgian IPA is made with blueberries, grown entirely without pesticides and harvested early every morning, and the same home-grown Miyamanishiki sake rice. Give this very berry-flavored original a try!

Manufacturer Police Tamamura Motoi, Shimotakai-gun, Nagano Prefecturachi, 0269-33-2155/www.tamamura-honten.oll 1163 Yamanouchi-ma”

The good news for humanity? Production was limited to 3,362 bottles.

Results work. Just ask my vet.

Get this, chimpanzees get the equivalent of 2 beers in their natural diet, every day, from fermented fruit. Now that’s good science, thanks to some primatologists working hard in Uganda.

The hypothesis they’re running up the flagpole is that we evolved with a diet of 2 beers a day. Because we were effectively chimps 10m years ago.

No arguments from this chimp, even if I know it’s pure speculative bullshit.

“This incinerator design takes three years to complete a job. Clients are happy to wait”

That’s what I read. Upon a third glance, I discovered it actually was…

“This interior designer takes three years to complete a job. Clients are happy to wait”

Mine makes more sense.

What happens when you live in a society where there are more things you can’t do than you can do?

At All de min to….

I’m thinking Australia needs a Chief Risk Assessment Officer (CRAO), and I have just the person for the job.

It makes more sense than having a Chief Scientist.

Archaeology has a problem in that the data in the field is scattered across site reports, journals, museum records, excavation notebooks, radiocarbon logs, GIS layers, old drawers, and PDF scans. Each fragment is trapped in its own idiosyncratic format.

Archaeologists are famous for over-interpreting the little data they have access to. Dreamers mostly. The interpretations proliferate because no one cares enough to stop them and there’s no consequences for being wrong.

Imagine instead that archaeology decided to do something radical and tedious: build a fixed, standardised database format and force every new and old record into it.

Stratigraphy, dating results, materials, provenance, confidence levels, references. A schema that is  strict enough to make data cumulative. It would take years of work, but it would create a workable database of knowledge instead of graveyards of disconnected stuff.

What would be excluded is the last few hundred years of speculative interpretations.

At that point an LLM would be useful by seeking connections  in the database, and then highlighting overlooked patterns. The human interpretive performance would be banished from the field.

The irony is that archaeology, the study of old human systems, has not built a system for its own knowledge. If it ever does, the machines will be able to do what humans have already failed to: assemble the fragments into meaning.

Archaeology have cast themselves as the indispensable interpreters of fragments. If the field ever did the unglamorous work of standardising its data into a single coherent system, the need for interpretation would vanish. An AI could do the job faster and more consistently, leaving archaeologists as hunters and gatherers of data.

I realised this after watching an AI identify the location in an old photo I had. It broke the image into groups of pixel features, turned them into words, and matched them against reference material until the location appeared by deduction. Archaeology could be the same. If the fragments are properly described and standardised, the machine wouldn’t dream, it would just find.

I don’t mean to slag off solely at archeology. Much of the same dynamic has crept into all of science and just about all other academic subjects.

The incentive structure leans toward novelty, citation counts, and media traction rather than accuracy or reproducibility.

Logical thinkers get trapped between the careful limits of what the data can support, and the pressure to turn that into a “story” that grabs attention.

And because being wrong rarely carries consequences, the system accumulates bullshit.

So instead of building cumulative knowledge, we stack flimsy claims on top of one another, rewarding attention over accuracy.

Except in business where incompetence gets punished quickly because the measure is unforgiving: money. A bad model, a flawed assumption, or sloppy execution is measured and assessed immediately. It doesn’t guarantee wisdom, but it does enforce a minimum level of competence that academia and science don’t have.

Business systems optimise for throughput: turning forests into timber, fish into protein powder, oil into plastics and people’s attention into ad revenue. The waste, carbon, toxins, noise, distraction, isn’t priced at all, so it accumulates.

Add humans, we’ve only built one machine that is ruthlessly competent, and it’s ruthlessly competent at the one thing: converting nature into pollution.

So we’re good at one thing, slowly killing ourselves.

Maybe, just maybe, AI to the rescue? Just like it could save archaeology, it might save ourselves from ourselves. If AI is to rescue us, it will be by doing what we won’t: impose structure, cut through noise, and measure consequences without sentiment.

But it will take the will to let it take charge.

It’s true, every discovery in archaeology is ground breaking.

It’s an academic’s wet dream this field.

In my next life, I’ll be an archaeologist.

Or an economist, where there aren’t any discoveries at all. Just models that don’t work. That’s not fair…

Archaeology, chemistry, and economics can all be all the study of complex human systems and in them you can make discoveries.

An archaeologist pulls meaning from a buried shard, a chemist untangles the behaviour of a complex invented process, and an economist sees a new pattern in the markets.

Nope, in my next life I’ll focus on nature not nurture. Because as we we all know, that’s far more noble.

Google photos threw up an old photo from 2006. It was a street scene with Victorian era buildings in the foreground, a very steep hill in the background with houses, the odd person wandering around, and a subcontinent-style bicycle tuktuk.

For the life of me I couldn’t figure out where it was taken. I guessed it was in NZ but that’s all I had. So I asked chatGPT and it instantly said Oamaru, New Zealand and even gave me the street address.

So I went to that address on Google maps and looked at the street view. Yep that was it. Although it looked 100% different because of the wide angle lens Google uses – making the hill all but disappear, a few changes over the years, and no people or tuktuks.

I suspect it looks more like the Google maps version in real life which is why I couldn’t pick it.

Super impressed, I asked GPT how in the hell it did that.

GPT used a vision encoder to break the photo into patches of pixels and convert them into numerical features; those features were then aligned with text concepts, so the chalky white façades mapped to “limestone,” the arched shapes to “Victorian warehouses,” and the rising slope to “hillside houses”; once expressed in language, the model’s text engine could reason over them just as if I’d typed a description, which is how the photo went from raw pixels to words to the conclusion that it was Oamaru.

Once GPT had the photo expressed in words, it treated it like any other text prompt. The description – narrow paved street, two-storey limestone warehouses, period lamp posts, gentle hillside with scattered houses – was compared against patterns of places it knows. That meant running through candidates and ruling them out: Wellington has hills but no limestone precinct, Dunedin has warehouses but in brick and basalt, Napier is Art Deco, Christchurch is flat. Only Oamaru matched all the features at once. So the mapping step was simply reasoning in language by deduction: taking the verbalised features and checking which town’s built environment and landscape lined up with them.

All within 3 seconds … it would have taken the CIA a week to find that match, using humans.

In case you’re wondering “Out-of-place vehicles are weak signals. I noticed the tuk-tuk-like silhouette, but I down-weighted it because: 1) vehicles move, buildings don’t; 2) novelty tuk-tuks and three-wheelers do show up in NZ tourist areas and events; 3) the decisive cues were fixed: Oamaru limestone façades, Victorian warehouse proportions, lamp posts, and the inland hill profile. So I treated the tuk-tuk as incidental rather than diagnostic and let the immovable features drive the match.”

Faaarrrk.

There’s a recurring belief among people experimenting with AI that there must be a perfect GPT prompt out there that unlocks flawless answers: accurate, precise (repeatably the same), clear, semantically faithful, and fully compliant with the query.

Even this list of requirements is subjective, but let’s stick with this lot for the sake of argument.

A universal prompt is appealing because using an LLM can feel like coding, especially via APIs. And if only you knew the right words, the machine would start behaving like a computer should.

The trouble is that such a prompt can’t exist.

Accuracy requires facts outside the model’s training or its generative capacity.

Precision would require it not to be a statistical estimator, which it is.

Clarity shifts with every user’s knowledge and expectations.

Semantic fidelity collides with information theory: you can’t compress meaning perfectly.

Compliance is contextual, constantly changing, and bounded by tokens.

The only proof that such a prompt doesn’t exist is that GPT cannot offer a proof that it doesn’t exist.

It doesn’t even get close. In fact, it was as squiggly as I’ve seen it; it completely failed to understand my request multiple times and I had to beat it with words to get there.

So there you have it quod erat demonstrandum, completely in reverse.

A system that cannot certify the absence of a universal prompt must also be incapable of certifying its existence. And because it uses the same underlying machinery to certify as to generate, the failure is the evidence.

All of that is a complicated way of saying words are just metadata. We humans interpret them in a very subjective manner, as we please. In fact we don’t even agree on the underlying ‘facts’ they’re meant to describe.

So prompt away, fuckers.

When are we going to get an AI driven keyboard on the phone?

Neck, shoulders, elbows, wrists, ankles, knees, who cares? It’s only back pain that must be addressed.

Having mostly sorted out the back, my chiro is now going searching for other aches and pains.

I said to her I’m like a ’64 Volkswagen Kombi; if you go looking for rust, you’ll find it. Eventually you’ll give up and buy a Hyundai.

According to GPT I need 3,000 calories a day.

And I would need to eat about 375 oysters a day to reach that 3,000 calories.

That’s about $1,000 a day at current pricing.

Just imagine, in the old days the indigenous locals at Jervis Bay did just that, for free.

For the record, according to GPT, I could push that to $27k a day by switching to Matsutake mushrooms.

I’m not chasing fame, fortune, power or legacy. I like moving through ideas, testing and breaking them down, then moving on. It’s about solving problems well. The process is the point, not the product.

Well that’s inconvenient isn’t it?

The latest US assassin was a right wingish Mormon steeped in online culture. MAGA-like that is.

“We are confident we have the right individual in custody,” an FBI spokesperson said, “but we are still working to establish the full picture of who he is and why he acted.”

I’m surprised they want to know why. And I’ll be even more surprised if they ever tell America – they’ll just fabricate whatever suits the narrative. Is the bloke even obliged to tell them why? Either he did it or he didn’t; that’s all they need to get a conviction.

Discord issued a statement saying his account had been suspended. “We have removed the suspect’s account for violating our off-platform behavior policy,” it said.

It’s nice to know they have some standards. Guns are a constitutional right, but memes are a privilege.

Maybe the US should extend the 2nd amendment rights to the access and use of social media.

Teenagers are effectively energy sinks. Their bodies are building adult frames. Their brains are rewiring as their frontal cortex comes online, a process that consumes about 20% of their excessive calorie intake. 

Growth spurts, muscle development, and hormonal surges all add to the demands. As does a diet of pure carbs.

Social grace in teenagers is rare because manners require emotional regulation and perspective, skills still developing in a brain dominated by the amygdala. Social separation from adults, exposure to social media and peer-driven culture make things worse.

So its best to give them the benefit of the doubt and just pretend it didn’t happen. After all, they will; they’re certified goldfish.

Gattaca, that sci-fi film, came out in 1997, when the new science of genetics was new and scary. The Human Genome Project was still underway, Dolly the sheep was a headline and the idea of designing a baby was treated as both a miracle and a threat.

The film imagined a future where  genetic analysis machines had the power to predict a person’s life expectancy from their DNA. Social structures were defined by DNA. Scary stuff.

Nearly thirty years on, we can edit genes, sequence entire genomes cheaply and we have a 10-year project to sequence every living thing, yet society hasn’t divided itself on the basis of DNA.

These days we worry about machine learning models ruling the world and making us all slaves. AI is today’s genetics, hyped as the next deadly threat to our position at the apex of the ecosystem.

Genetics hasn’t reshaped humanity’s day-to-day experience. AI probably won’t either, at least not in the way headlines suggest.

One thing that hasn’t changed; Michael Nyman’s music remains as annoying as ever.

-h-

Counter argument … I just walked into Coles to buy sausages for dinner. I took with me the espresso I’d just bought.

At the counter, their AI vision system determined that I had an item that I didn’t scan – the espresso cup and was therefore stealing.

The alarm went off. A human came over, reviewed the footage with coffee cup (the offending item) highlighted in green, then released me.

Hopefully by the time they dispense with the expensive human intervention, the machines have learnt from these errors.

It doesn’t have to know why I was released from custody, just that i had committed no crime.

Car window buttons. Just put a different physical texture on the front and rear buttons so the driver knows immediately from feel alone that they’ve selected the wrong set, or not.

In typography, the emdash was designed to match the width of a capital M, hence “emdash”.

There’s two others;

The en dash is half as wide, and

The hyphen is narrower still, a third of an emdash.

Keyboards don’t usually have options for en or em dashes because:

1. These were designed for typesetters, not casual writing, and

2. Most modern readers don’t notice or care about the distinction. Or they didn’t until GPT came along. Unfortunately the emdash is now a dead giveaway for AI generated content.

This Gboard keyboard that I’m using, to its credit, has the option. It only took me 20 minutes to find it. All you have to do is go to the number and symbol page, find the hyphen, long press it, then select the actual dash/hyphen that you want from the popup bubble. Simple as…

I’m thinking to add some emdashes to my own prose just to confuse people.

A group that has survived genocide possesses direct knowledge of its harm. When that group chooses to inflict genocide on others they act with full awareness of the suffering they are reproducing.

The crime is not only the destruction of lives and culture but also the conscious disregard of the insight gained through their own history.

In my mind, this makes the act ethically worse than genocide committed in a state of ignorance or stupidity, because it combines atrocity with a conscious rejection of empathy and memory.

You can liken it to comparing a crime of passion killing and a premeditated murder.

Ethical responsibility may not pass automatically through ancestry, but invoking history as ethical currency has consequences. If a state demands recognition and security on the basis of past suffering, it cannot expect impunity when its own actions mirror the crimes it condemns.

It seems Viv has inherited an intelligence that will be deeply unappreciated by the education system.

This morning’s discussion with Viv began with prime numbers, and ended with a demolition of several centuries of mathematics and philosophy.

I told him that some numbers cannot be divided by anything but themselves and one (to give an integer), and that no one really knows why primes behave the way they do.

He listened carefully, asked a few practical questions, and then suggested that the whole thing is pointless; numbers aren’t real, humans invented them, and that’s why they don’t make sense.

It is difficult to argue with Occam’s razor when deployed by a seven-year-old. It appears he has not yet been trained to mistake complexity for reality.

To him, “three” is only a word we use to describe a set of fingers, or biscuits. If the language is inconsistent, that is not evidence of cosmic mystery but a flaw in the design.

We like to pretend mathematics was discovered, not invented, because it flatters us to imagine we have glimpsed the machinery of the universe.

Viv is not impressed. He sees arithmetic as a tool, no more mysterious than a hammer, and if a tool misbehaves, you either fix it or chuck it.

That outlook will probably last until they teach him algebra, where the machinery becomes baroque enough to fool most sceptics, by design.

For now, he is satisfied with the insight that numbers are stories humans tell about counting, and that some of the stories are stranger than others.

I am satisfied too: there is no better reminder of how thin the line is between knowledge and faith than a child refusing to accept that 3, 5, and 7 are mysterious but 9 isn’t.

-h-

I like to think there’s an alternative quantum-like number system lurking out there. Noting that quantum physics and chemistry both collapse to classical theory in the limiting cases, why not maths as well?

I think it’s stupid that we use classical maths to describe quantum theory. It’s shoving a very square peg into a round hole, and no wonder it’s hard to follow.

Just as quantum mechanics reduces to classical mechanics for large quantum numbers, this hypothetical maths would reduce to ordinary arithmetic and calculus in the macroscopic limit.

Maybe primes only seem mysterious because they’re artifacts of the framework we use; features of our chosen mathematical coordinates rather than of reality itself. In a deeper structure, they might be irrelevant or invisible.

Or, as Viv says, numbers may just be projections of human cognition, a linguistic framework imposed on reality, rather than features of the universe itself.

So this morning I explained prime numbers to Viv;

Me: all numbers can be divided by one and themselves, right?

Viv: yes

Me: but some numbers can’t be divided by any other number, and nobody knows why.

Viv: that’s not true. You can divide any number by 2.

Me: oh, I forgot to say, the product must be a whole number. No fractions.

Viv: oh, so it’s every odd number?

Me: try 9

Viv: oh yeah … wait, what?

Me: no one knows why.

Viv: I think its because humans made up numbers and they don’t really mean anything.

Soup, man.

The fuckers enticed me to “trial” Gemini for free. A chance to see how Google’s latest and greatest stacks up against the competition.

It turns out it’s rubbish compared to GPT for what I do. And slow, to boot.

No problem, I thought. I’ll just cancel the trial. That’s when I discovered it wasn’t a free trial anymore. I’m paying for this shit.

My simple task had become a mission: get my old plan back and stop paying for a tool I don’t want.
And that’s where the ethical line got crossed. I went to “downgrade” to my previous plan, and there’s no option anywhere. None. Just a comprehensive list of more expensive plans that I can upgrade to.

Good job, Google; we’ll turn a blind eye to the monopoly so long as you pretend to be a good corporate citizen. Walling off the exit isn’t that.

So I asked Gemini to help me cancel Gemini. It couldn’t. To its credit, it did acknowledge the absurdity of the situation, noting it was a “sharp, insightful, and frankly damning summary” when I pointed out the deep irony of the situation.

Gemini’s final suggestion? Email customer support.

I did. An email came back from “JC” at the Google One team. It was a masterpiece of AI-generated empathy, a word-perfect template that managed to say nothing while asking me to do the very thing I had already told them was impossible.

“Thank you for contacting Google One support and for being a Google One member!

This is JC and I’ll be the one who will assist you today. I hope this email finds you well!

I do apologize for the delayed response.

I understand that you want to downgrade from the Google One 2TB Premium plan to the original 2TB plan because you do not want to pay for the Gemini AI feature. I know how important this is for you to resolve as soon as possible. No worries, let’s work on this together.

To better assist you and help resolve the issue as quickly as possible, could you please provide a few more details? This will help us investigate and give you accurate guidance:

When you go downgrading the subscription, can you please send me a screenshot of the option you have when you try to downgrade your subscription?
I’ll be looking forward to your response.”

So I went back to my unwanted AI assistant and complained that its advice had led me to another AI. Probably the same one through some internal API. And, no shit, this is what it suggested I do:

‘Reply directly to the email and write: “This automated response has not resolved my issue. The self-service options have failed. I demand this ticket be escalated to a human support agent for a manual plan downgrade.’”

Let that sink in. My unwanted and expensive Google AI assistant suggested that I get rid of it by zig-zagging around Google’s AI-generated customer support with Google’s AI-generated prompt engineering.

This snake has gone so far up its own arse that there’s only a black hole where it used to be.

The one thing I will say for Gemini is that you can copy any part of the LLM reply without having to hit the “select text” menu option in Android. It’s a small thing, but it goes to show that even with a groundbreaking technology like an LLM, good UI is 90% of the competitive differentiator.

On that subject, whoever first figures out how to make their LLM remember and inject user preferences into every single chat, they win. Down with emdashes!

Also I wouldn’t mind a “post chat to blog” option. Imagine all the great content that would be published and then used as the source of future LLM-generated answers?

A fully charged battery is heavier than a discharged battery, but not because it has gained any material.

A lithium-ion cell, like those used in a Tesla, is a sealed system: the same lithium, cobalt, nickel, graphite, and electrolyte remain inside whether it is empty or full. 

When you charge the battery, you are forcing lithium ions to leave the metal oxide cathode and insert themselves into graphite layers at the anode.

This rearrangement of matter stores energy in the chemical structure of the molecules, and energy has mass according to Einstein’s equation.

A Tesla Model 3 pack stores about 60 kWh, or roughly 216 megajoules, of energy. Dividing this by the square of the speed of light yields a mass increase of around 2.4 micrograms when it charges from empty.

That is one-twentieth the weight of a typical grain of salt, spread across a 480 kg battery pack.

The weight increase comes entirely from energy stored as chemical rearrangements, not from accumulating extra electrons. The electrons are just carriers; they help rearrange lithium ions and bonds inside the battery. Electrons circulate and are balanced by ionic motion; no net electron rest mass is added.

They didn’t teach me this at uni but every molecule is lighter than the sum of its isolated atoms, and every chemical reaction changes the total mass slightly. We ignore it in chemistry because the changes are at least a billion times smaller than atomic masses.

So much for the periodic table!

The molecules that make up all living things on Earth weigh roughly a few hundred thousand kilograms less than the same nuclei and electrons were they to be taken apart and separated to infinity. The exact number depends on composition and bonding, but it is in the 100-1000 tonne range (says GPT).

Viv says…

In 1933, this scientist started a robot that had, like, millions of specks of sound, and made them into a robot. After 9 years the first drop of sound appeared. Only 9 drops have ever fallen out.

He is referring to the pitch drop experiment at UQ. Pitch, sound…

“The slowest dropping thing is the highly viscous liquid in the pitch drop experiment by the University of Queensland (UQ). At room temperature, this substance, which is a form of tar or bitumen, flows so slowly that it can take years for a single drop to fall, with only nine drops having fallen since the experiment began in 1930.”

“The royal commission described robodebt as a ‘crude and cruel mechanism, neither fair nor legal’. It found that ‘people were traumatised on the off chance they might owe money’ and that robodebt was ‘a costly failure of public administration, in both human and economic terms”.

Could say the same about R&D tax.

Over the last few few years I’ve been collecting good candidate names for a band. The list so far;

Coda pi
Quiet carnage
Birdy Numnuts
half a mandible
glutinous pussies
Pine mullets
Rushman Saldie
No 4 fish puzzle
Wrong Heads
Quack and Dandy
Loopy VJs
The worms
Ado mato
The shelbows
The shobos
Reformed utopian army
The deagon deviation
Dodecarator
The cunning je suis
The avant gardener
The swamp bogans
Villainous Scroll
Emergency burgery
The S bend band
Moëdely
Sunken Seed
The Weilding Berkers

Space age chickens

Stone age chickens

The Malthusian trap describes a pre-industrial society where any small gains in productivity fueled population growth rather than higher living standards.

TL:DR – more people got to live in shittier conditions

Slave economies fed into this effect by tying wealth directly to ownership of people, turning human bodies into the primary unit of both production and capital.

Productivity scaled through reproduction and acquisition of slaves rather than mechanisation  More workers meant more output but also greater subsistence costs.

Slavery acted as a structural brake on innovation and a mechanism for keeping societies inside the Malthusian Trap.

As an institution, slavery had to go, for economic reasons.

Traditional Chinese Medicine makes up about thirty percent of China’s medical economy. Apparently not a single TCM herb had ever been shown in a clinical trial to be the best medicine for treating any condition. The only clear “best available medicine” that is derived from TCM is the pharmaceutically-purified compound class of artemisinin-based combination therapies (ACTs) for malaria. Everything else has, at best, adjunct benefits or is simply a placebo.

This is not a failure of science so much as a signature of a culture that never had its Enlightenment. Rationalism, falsifiability, and sceptical inquiry never became embedded. As a result, TCM is protected as cultural heritage, so it survives by decree and habit, rather than due to evidence.

In China, the machinery of science runs at full speed for vaccines, semiconductor fabrication and other sectors, but it is solely a tool applied where useful. They use science but they do not create it

In China’s culture, incumbency, fluency and authority are taken as proof of intelligence. Without deep norms of critique or falsifiability, an LLM already meets the bar for “general intelligence,” reflecting the local human standard of intelligence; one that leads to one-third of its medical budget being expended on products that have no proven efficacy.