mxx1's avatar

New words

The primary recreational activity of sheeps in wolvish clothes.

Recreational narcissism: engaging with others primarily for stimulation, attention, or novelty, with no commitment or interest in integrating the outcomes into the longer term project.

mxx1's avatar

Maths

Studies find that, once you control for player quality, budget, injuries, and randomness, the measured impact of a manager is not measurable, statistically speaking.

I’m thinking the same is true for political leaders.

Actually it’s asymmetric; a really bad manager or leader can create a statistical anomaly on the downside.

mxx1's avatar

Life in Consumer world

I had thought I’d written this before but I can’t find it.

The three motivating forces that I’ve discerned in people are power, fortune and fame.

These are the things people can imagine that define success.

Then there’s the way they get there; rational, emotional and physical. People’s individual natural strengths which define how they do things.

I suspect there’s a whole enneagram-like system one can build around this….

Wings and all.

A one-to-one mapping requires forcing uniqueness by assigning a single dominant motive and method to each type, then treating adjacent tendencies as wings rather than primary classification.

Type 1 → Power–Rational
Core pattern is control through standards, rules, and correctness. Moral authority functions as power. Method is structured, analytical, corrective.

Type 2 → Fame–Emotional
Core pattern is gaining recognition and value through helping and relational positioning. Method is affective, attuned, persuasive through warmth.

Type 3 → Fame–Rational
Core pattern is status acquisition via measurable achievement and optimisation. Method is strategic, goal-driven, efficiency-focused.

Type 4 → Fame–Physical
Core pattern is differentiation through visible expression of identity, often embodied through aesthetic, style, or presence. Method is enacted, performative, materially expressed rather than purely relational.

Type 5 → Fortune–Rational
Core pattern is accumulation of intellectual capital as a proxy for security and independence. Method is analysis, abstraction, controlled resource expenditure.

Type 6 → Power–Emotional
Core pattern is managing threat through alliances, loyalty, and vigilance. Power is derived from alignment with trusted structures. Method is reactive, relational, risk-aware.

Type 7 → Fortune–Emotional
Core pattern is maximising optionality and access to experience. Fortune is freedom rather than stored wealth. Method is opportunistic, reframing, enthusiasm-driven.

Type 8 → Power–Physical
Core pattern is direct control, resistance to constraint, and dominance. Method is action, force, confrontation.

Type 9 → Fortune–Physical
Core pattern is preservation of comfort, stability, and low-friction existence. Fortune is steady-state ease. Method is inertia, accommodation, energy minimisation.

Constraint notes:

• Fame is allocated to 2, 3, 4; Power to 1, 6, 8; Fortune to 5, 7, 9.
• Rational is allocated to 1, 3, 5; Emotional to 2, 6, 7; Physical to 4, 8, 9.
• Each of the nine combinations is used exactly once.

This is a structural mapping, not a claim about underlying Enneagram theory, which defines types by fear and fixation rather than explicit goals or methods.

mxx1's avatar

New word

A hedonist is a person that prioritises experiencing enjoyment, often sensual, over other activities, usually without thinking too hard about it.

An arseonist is a hedonist who explicitly models the downside and proceeds regardless. Ironically, an arseonist uses their head when a hedonist doesn’t.

Arseonists are not to be confused with people that start fires for fun, although in rare circumstances an arsonist is also an arseonist.

mxx1's avatar

New word

The largest Imperial Harem in China is attributed to Emperor Xuanzong of the Tang Dynasty, who reportedly had more than 40,000 concubines.

Noting that carps are just very big Chinese goldfish…

New Word – Carping: having so many concubines in your harem that every day is a new day.

mxx1's avatar

Santa

The legend and character of Santa Claus derives directly from St Nicholas of Myra (near modern-day Demre in Antalya Province, Turkey).

Apparently he was a very generous fellow. Although he did once lose his shit and slap Arius in the face at the first ecumenical council in AD 325.

St Nicholas is venerated by the Orthodox church as the patron saint of children, barrel makers, sailors, merchants, the falsely accused, repentant thieves, brewers, pharmacists, archers, pawnbrokers and broadcasters.

Why no kangaroos?

mxx1's avatar

New word

Slopshaming: an ad hominem attack dismissing content as ‘AI slop’, ironically targeting the ball not the man (but really the man), without engaging its substance. Criticism that itself is slop.

Generally used by people that generate slop completely without AI assistance.

mxx1's avatar

Invention of the day

A public transport seat fabric that is primarily blue with whatever weird arse abstract print you want added in yellow, red and orange. Completely synthetic, it will be the only survivor of nuclear armageddon, along with the cockroaches.

The only unanswered question: why not use it for toilet seats?

mxx1's avatar

New words

Candlelighting: accusing another party of gaslighting, often pre-emptively or defensively, regardless of whether psychological manipulation is actually occurring. Functions as a counter-allegation that reframes the original accusation.

Etymology: low-intensity, ambiguous illumination associated with partial visibility and interpretive uncertainty.

Matchlighting: accusing another party of candlelighting, often pre-emptively or defensively, regardless of whether psychological manipulation is actually occurring. Functions as a recursive last port of call counter-allegation that reframes the original accusation.

Etymology: no shit, Sherlock…

mxx1's avatar

Genes

I asked GPT a question that had been sitting in the back of my head: how much digital storage would you need to capture everything the human genome actually produces when you run it inside a living body for eighty-odd years? Not the genome itself. That’s a separate and easier question. I wanted to know about everything it generates.

The human genome contains about 3.2 billion chemical letters. Each letter is one of four options (A (Adenine), T (Thymine), G (Guanine), and C (Cytosine)), which means you can encode each one in 2 bits of digital information. Do the arithmetic and the whole genome comes to roughly 0.8 gigabytes. Less than a cheap USB stick. You could back up the complete instruction set for a human being to something you could lose down the back of a couch.

That’s actually a generous estimate. A lot of the genome is repetitive filler or sequence that barely varies between species, so the genuinely useful information content is smaller still. But take 0.8 GB as the round number.

A living body doesn’t read the genome like a computer reads a file. It runs it. The genome is more like a program than a document. It specifies how to build molecular machinery, how that machinery responds to signals, how cells develop into different types, and how the whole structure maintains itself for decades. The program is compact. What it produces is not.

At any given moment, a human body contains somewhere between ten trillion and a hundred trillion cells. Each cell is actively maintaining a state across thousands of variables: which genes are switched on, what proteins are present, what signals it’s sending and receiving, how its DNA is packaged. Even a rough tally, one byte per variable across a fraction of those cells, produces a number around 100 petabytes for a single snapshot in time. That’s 100 million gigabytes, and it’s a low-resolution estimate.

Add time and the numbers get larger still. The body isn’t a static. It’s a process running continuously over a lifetime: development, repair, immune response, ageing. If you wanted to record not just where things are now but how they got there and where they went, you’re looking at somewhere between one and a hundred exabytes. An exabyte is a billion gigabytes. So the rough relationship is: genome around 0.8 GB, body state at one moment tens to hundreds of petabytes, body process over a lifetime one to a hundred exabytes.

That’s an expansion of roughly ten billion times, from the program to the processes it generates. But the genome isn’t storing that information. It’s producing the conditions under which chemistry and physics generate it.

Not all of that complexity comes from the genome. A lot of it comes from the environment: light hitting your eyes, food you’ve eaten, infections you’ve fought off, random molecular noise inside cells. The genome doesn’t pre-specify every cellular state. What it does is build machinery capable of responding appropriately to whatever the environment throws at it. You also can’t treat every cell as independent. Cells of the same type behave similarly. Development follows constrained paths rather than wandering randomly through all possible states. The actual information in a biological trajectory is far more compressible than the raw numbers suggest.

The genome is a small program that sets up a very large and responsive system. The environment runs that system through one particular trajectory out of many it could have taken. The resulting complexity, the full state of a living human body across a lifetime, is not stored anywhere. It is continuously produced by running a compact set of instructions through wet chemistry for eighty years. The numbers are striking even after all the caveats. A sub-gigabyte program generating a process that would take exabytes to record is not a trivial compression ratio. It just means that execution in a physical system is a fundamentally different thing from storage. The genome’s job is not to pre-specify the answer. Its job is to build something capable of finding one.

The living body it generates, sampled across all its cells and processes over a lifetime, represents something in the range of exabytes of realised state. The expansion is roughly ten billion times. The genome doesn’t store that complexity. It generates it by running a compact program through physical chemistry for eighty years.

That’s not a curiosity. It’s an existence proof.

Something in the physical world can act as a generative substrate where a small specification produces vast useful complexity through execution. The complexity doesn’t live in the code. It emerges from running the code in the right kind of physical system. The body is not a digital computer poorly approximating the genome’s intentions. It is a quantum mechanical system doing what quantum mechanical systems do, and the genome is compact precisely because it only needs to specify initial conditions and interaction rules. The physics handles the rest.

This is worth sitting with before moving to quantum computing, because the standard framing of quantum computing has almost nothing to do with it.

The standard framing is about algorithm supremacy. Build enough qubits, correct enough errors, and you can factorise large numbers faster than any classical machine, or search unsorted databases with a quadratic speedup, or simulate molecular hamiltonians exactly. All of that is real. None of it is what the genome is doing.

The genome is not competing with classical chemistry on classical chemistry’s terms. It is not trying to compute the folded state of a protein by running a faster version of an algorithm a classical system could also run. It is setting up a physical process and reading the output. The protein folds because of electrostatic interactions, hydrophobic forces, hydrogen bonding, and van der Waals forces playing out in an aqueous environment. The genome’s job was to specify the amino acid sequence. Everything after that is substrate.

Quantum reservoir computing works on the same principle. A fixed quantum system with rich internal dynamics receives an input, processes it through those dynamics, and produces an output that a classical readout layer is trained to interpret. You do not program the quantum system exhaustively. You do not need to control every qubit. You run things through it and read what comes out. The quantum dynamics are the genome. The readout layer is the organism deciding what the state of the body means.

The scaling problem in conventional quantum computing is about maintaining coherence across large numbers of qubits long enough to run a deep circuit. It is genuinely hard and may remain hard for a long time. Quantum reservoir computing sidesteps most of it. The system does not need to be large. It does not need to be perfectly controlled. It needs to be rich enough in its dynamics that the mapping from input to output captures structure that would be expensive to compute classically. Ten to fifty noisy qubits in a physical system with interesting dynamics is potentially useful in this mode in a way that ten to fifty noisy qubits running Shor’s algorithm is not.

The genome did not solve biological complexity by getting bigger. It solved it by being the right kind of compact specification for the right kind of physical substrate. The question for quantum computing is the same one, stated plainly: what is the right kind of quantum system, and what is the right kind of compact input structure to run through it, such that the physics generates useful complexity without being asked to enumerate it?

That question is not new. Quantum reservoir computing researchers are working on pieces of it. What may be new is the framing. The genome is not an analogy. It is a physical system that already answered the question at scale, in noise, without error correction, running continuously for the lifetime of every person alive.

The genome framing is useful: it suggests the right question is not whether quantum reservoirs beat classical algorithms, but whether there are problems where running inputs through a physical quantum system and reading the output is simply the natural way to compute.

That seems worth looking at.

mxx1's avatar

New word of the day

Liderally: a general-purpose adverb used to create the impression that the speaker is not lying. It also marks speech where emphasis outruns evidentiary content.

It’s a rare example of a pradoxymoronic contronym with a flap T on top.

Etymology – originates from “literally”  (modern English), meaning “actually”, phonetically degraded by Australian kids, liderally.

mxx1's avatar

Non sequiturtle

So it wouldn’t be surprising if Turtlecorp increasingly chooses a safer strategy: announce Turtle Summits only shortly before they actually happen.

Not always, but more often.

It reduces risk, avoids cancellations, and ensures that when a Turtle Summit is announced, it is almost guaranteed to happen.

In short: just because Turtlecorp didn’t announce any Turtle Summit today, it does not mean we cannot get one still in the first quarter of 2026.

mxx1's avatar

Sequence Number

I find this interestingly absurd so I recorded it here for future reference.

The sequence number on a boarding pass is the number that indicates the order in which you checked in for the flight.

Airline staff  use it for reconciliation, auditing, or troubleshooting check-in issues. And sometimes even to decide who gets kicked off if they are over-booked.

Right now I’m stuck on the ground on a deathstar flight to Brisbane because they’ve found too many people on the flight and they’re using the sequence numbers in attempt to square the ledger.

Retards broke their own boarding pass scanner, someone scammed their way through the manual process, and now we’re paying the price.

Or they just can’t count.

mxx1's avatar

Reduced Abstraction explained

As expected, Deathstar is still well behind on this Friday afternoon flight.

Thanks to the elf I’ve just gone down a rabbit hole at Flight Aware to understand what they aren’t silly enough to tell me.

You can do almost anything there. See photos of your plane. Checkout the blueprints. See sub minute data of the flight altitude and speed. Find flight route details, and so much more.

The problem is it removes the mystery from flying.

And now I’m analysing the data for risk factors.

In hindsight, I prefer ignorance to keep that NRE* up.

It’s a quantum effect of sorts: if you observe the thing it collapses to an anxiety-inducing boring state.

*New relationship energy

mxx1's avatar

Circular attraction

Quote of the day, overheard at a Sydney cafe.

“If you love me you’ll promise to tell me if that’s not true any more?”

I’m not sure about the question mark though. It might have been implied in that weird Australian lilt at the end, or I may have imagined it. If I did, it becomes a threat not an illogical request. That’s even crazier.

What makes this overheard snippet so good is that a person said it apparently without noticing how insane it is.

I like it.

And this is what is so shit about AI. GPT responded with this set of unfunny observations:

“It is a self-referential contract that collapses under its own condition.

The statement requests future honesty about the absence of love, but the act of asking introduces a constraint on the other party’s behaviour. Once agreed, the listener is no longer free to report a change neutrally because doing so triggers a known consequence, which may be emotional harm, conflict, or loss. That creates an incentive to delay or distort the truth, which directly undermines the original request.

The interrogative form matters. With a question mark, it reads as a request for alignment on a rule. Without it, it becomes a conditional demand, closer to a pre-commitment device imposed on the other person. In speech, rising intonation can carry both, which explains the ambiguity.

The “circular” aspect comes from dependency inversion. The speaker seeks certainty about the future state of the relationship by outsourcing detection of that state to the other person, whose incentives have been altered by the very request. The reliability of the signal is degraded by the mechanism used to obtain it.

There is also an asymmetry. The speaker does not commit to the same disclosure, or at least it is not stated. Even if implied, enforcement is bilateral only in theory; in practice, disclosure timing and interpretation remain subjective.

It is coherent as an expression of anxiety about delayed truth. It is incoherent as a mechanism to ensure timely truth.

The line works because it sounds reasonable on first pass and unstable on inspection.

This is a standard self-voiding condition. It tries to bind behaviour in a future state where the binding predicate is false. It therefore cannot be relied on as a control on timing or honesty.”

No shit, Sherlock…

mxx1's avatar

Slop thoughts

Ok, so I might have a few too many beers last night, but…

I have an hour to kill before my first meeting this morning, so I’m walking from Darlinghurst to UTS.

Sydney (especially the people that populate it) looks like it’s been generated by AI.

Imagine that, a whole city that is AI slop!

mxx1's avatar

Armadillo Facts

Female armadillos give birth in spring and produce 4 identical quadruplets, born fully formed with their eyes open.

The armadillo has an interesting method for crossing water, because its heavy shell causes it to sink.

When faced with narrow streams or water-filled ditches, the armadillo will simply walk across the bottom, under water. Just like a scorpion.

In wider water bodies, armadillos swallow air to inflate their stomachs to twice its normal size, increasing buoyancy and allowing them to swim across. Afterward, it takes them hours to release the excess air.

No mention of what happens if an armadillo meets a shark while underwater.

mxx1's avatar

Vox Pop

I’m just listening to a podcast from some former traditional politicians trying to understand the rise of right-wing populism.

They seem genuinely confused. Which is odd because it’s so easy to understand.

The voting masses will put up with only so much corruption. So long as they benefit enough, they’ll look the other way as a minority of corporations and special interest groups abuse the centralisation of tax and laws, in their own interests.

The voting masses do this because given the same circumstances they’d behave exactly the same. But after a certain point of corruption they’ll roll the dice on any fuckwit that puts their hand up, and that looks different.

It’s ironic of course that the stated goal of these right wing populists is to prevent the voters being able to vote them out. Then they are free to maximise the benefits of government in the interests of just a tiny few.

Understanding this, it’s arguable that Winston was wrong on the subject of democracy being the worst form of government.

mxx1's avatar

AI to the rescue

There’s not really the visual art equivalent of an arranger/producer in music.

We love pretending music fell directly out of genius with no intermediate layer of judgement, sequencing or construction. It is mostly nonsense.

This is another argument for AI generated art because the execution is at least as important as the idea.

mxx1's avatar

New word

New word for the day – “discoest”

As in, it’s disco day at vacation care and Viv says; “I’m wearing my most discoest clothes.”

(for the record – black shorts with shark gill features and a dark blue “Bali Vibes” t-shirt)