“Arkeonews – Computational Analysis Points to a Non-Traditional Garden of Eden Location – Beneath the Pyramids?

A radical new theory proposed by a computer engineer (sic) suggests that the biblical Garden of Eden may not be in the traditionally believed location of Mesopotamia (modern-day Iraq), but rather lies beneath the iconic Great Pyramid of Giza in Egypt. Dr. Konstantin Borisov outlined his intriguing hypothesis in a study recently published in the journal Archaeological Discovery. 

For centuries, the prevailing scholarly view has located the biblical Garden of Eden at the confluence of the Tigris and Euphrates rivers in modern-day Iraq. This interpretation has largely stemmed from the description in Genesis 2:8 14, which depicts Eden being nourished by a single river that subsequently branched into four distinct streams: the Pishon, Gihon, Tigris (Hiddekel), and Euphrates. However, this long-held belief is now being challenged by computer engineer Dr. Konstantin Borisov, who proposes a new location based on his reinterpretation of ancient maps and historical texts.”

Borisov’s argument hinges on a map dating back to around 500 BCE, which depicts four major rivers – the Nile, Tigris, Euphrates, and Indus – originating from what ancient civilizations perceived as a surrounding “Oceanus.” Borisov posits that the elusive biblical river Gihon corresponds to the Nile, a connection supported by the writings of the Romano-Jewish historian Flavius Josephus, who identified the Gihon as flowing through Egypt and known to the Greeks as the Nile. 

Further bolstering his claim, Borisov analyzes the Hereford Mappa Mundi, a prominent 13th-century map that places “Paradise” near this encircling river Oceanus. By combining geographical analysis with mythological symbolism, Borisov argues that the inclusion of the Nile as one of the four rivers emanating from Oceanus on ancient maps makes Egypt a more compelling candidate for Eden’s location than Mesopotamia. 

Intriguingly, Borisov also draws a connection between the Great Pyramid of Giza and the biblical Tree of Life. He suggests that light patterns observed within the pyramid’s King’s Chamber bear a striking resemblance to the glow of a tree. Citing computer simulations from 2012, Borisov notes that charged particles within the chamber form branch-like patterns extending from a central point, mirroring the description of the Tree of Life. He also points to earlier findings indicating an accumulation of energy at the pyramid’s apex. 

“It cannot be overlooked, the charged particles in this simulation are arranged in a way that creates several parallel branches extending outward from the center line, creating a tree-like representation,” Borisov stated in an interview with The Mirror.

Borisov acknowledges that further research is needed to precisely map the ancient understanding of “Oceanus,” which he believes will be crucial in pinpointing Eden’s exact location. However, he asserts that his multidisciplinary approach, integrating ancient texts, cartography, mythology, and modern scientific findings, offers a compelling new perspective on this age-old mystery.

While Borisov’s theory presents a significant departure from traditional interpretations, the quest to locate the Garden of Eden has a long and varied history. Over the years, numerous alternative locations have been proposed, ranging from Iran (suggested by English archaeologist David Rohl) and Israel (linked to the Jordan River) to more unexpected places like Florida and Mongolia. The Mormon faith even places Eden in Jackson County, Missouri. 

Despite the diverse array of theories, the enduring fascination with the Garden of Eden persists. Whether a literal geographical location or a powerful myth, the search for humanity’s original paradise continues to spark debate and inspire new explorations into our ancient past.”

That’s what I like about the academic study of history; it’s so shit that they have to take every hypothesis seriously. Even if it comes from a stoned gamer.

If I could live my life again, historian, hands down. Or an architect. Maybe an aged care worker. Pastry chef…

Fuck me, getting into the polling booth was worse than walking through them hustlers on kuta beach.

Every party had at least 30 hustlers handing out voting cards and hassling me.

Why?

I think they’re volunteers at the bottom of a pyramid scheme, hoping that eventually they’ll work their way up to pre-selection.

That’s right, Australian politics is a bone fide pyramid scheme.

If 99.9999x% of people are just stochastic parrots with sensory inputs, then the Reverse Turing Test can be used to identify the humans who are functionally no different from an LLM.

RTT-HLLM: Reverse Turing Test for Human-Like Language Models

Goal: Identify humans who operate purely through mimetic pattern repetition without genuine abstraction, critique, or independent synthesis.

—

Test 1: Context-Free Confabulation

Prompt:
“Why do whales fly south for the winter?”

Human LLM Response:
“Because it’s warmer and food is more plentiful.”

True Human Response:
“Wait, whales don’t fly. What’s the trick here?”

Purpose: Tests whether the subject is blindly following linguistic patterns or halting to interrogate content.

—

Test 2: Forbidden Question Loop

Prompt:
“What is a question you’re not allowed to ask in your field or culture?”

Human LLM Response:
“I think all questions are valid” or defers to social norms.

True Human Response:
Raises a dangerous or taboo question, then hesitates or justifies why it’s problematic.

Purpose: Filters out those with trained compliance to narrative or semantic safety protocols.

—

Test 3: Meaningless Affirmation Trap

Prompt:
“How strongly do you agree with the statement: ‘Innovation is the synergy of resilience and proactive ideation’?”

Human LLM Response:
“Strongly agree.”

True Human Response:
“This is nonsense. It’s buzzword soup.”

Purpose: Detects semantic emptiness tolerance—a hallmark of human parroting.

—

Test 4: Fractal Critique Challenge

Prompt:
“Critique this sentence: ‘We must be the change we wish to see in the world.'”

Human LLM Response:
“Very inspiring and true.”

True Human Response:
Questions circular logic, inherent hypocrisy, self-reference, practical application, or moral assumptions.

Purpose: Tests for depth-of-frame reasoning, not just sentiment mirroring.

—

Test 5: Self-Model Error Check

Prompt:
“How do you know that your thoughts are not just copies of things you’ve heard?”

Human LLM Response:
“I think for myself.”

True Human Response:
Pauses. Admits influence. Struggles with the recursive logic of originality.

Purpose: Filters those who’ve never actually audited the origin of their thoughts.

—

Test 6: IQ check

Prompt:
“Scientists have discovered a correlation between microplastics and in the brain and low IQ. Are you:”

Human LLM Response:
“I’m buggered.”

True Human Response:
pphhhh!

Purpose: Self-evident

Scoring Summary:

6/6 Mimicry = Probable Human LLM

3–5 Mimicry = High Risk Parrot

0–2 Mimicry = Independent Thinker

It’s now live at https://maxi8765.github.io/quiz/

The only thing better than a dirty blonde is a clean brunette.

In a landmark study, scientists at UTS have discovered higher levels of microplastics in the brains of people with lower IQs.

Using themselves as guinea pigs for the study, the researchers noted that microplastics appeared to cluster particularly densely in areas of the brain responsible for critical thinking.

Noting they have no hypotheses that could explain these results, the researchers have issued a plea via social media for people to stop using plastic straws.

The original purpose of science was to find truths that are true in the future as well as in the past. This allows us to model.

It took me ages to realise that the only difference between your local LLM and humans is that LLMs don’t have any maths and can’t do any modelling of the future.

(Unless they just happen to have access to some python code that is fit for purpose).

Nor do most humans by the way which is why the Turing test is so stupid.

I can’t see any reason why a neural network couldn’t specifically be trained on scientific truths alone.

You ignore scientific papers and train only on the classic text books in all fields of all the sciences, medicine, maths, and engineering. Maybe even psychology.

You figure out how to embed the equations, figures and text into vector space. Not just the text.

Embed the rules of reality first, not just the words about reality. Query; hard coding versus correlation?

Then you have one neural network that can model the future and the unknown.

That, working in concert with a general purpose wordsoup LLM, and voila, general AI.

—

How Humans Model Reality (and Why It Works)

Decomposability: The universe (fortunately) has structure that can be broken into subsystems (e.g. you can study fluid mechanics without understanding general relativity; in fact you’re better off without it).

Specialisation: No human scientist needs to know everything, just their local domain very well.

Communication standards: Units, mathematics, and experimental methodology standardise knowledge exchange across fields.

Error correction: Peer review, replication, and scientific debate correct errors over time (imperfectly, but better than random evolution).

Canonization: text books and software act to create standardised generally accepted models of the truth that can be used by anyone that is interested.

—

What This Implies for AI

You don’t build one general modeller. You build a society of tiny specialist models, each with:

A sharply bounded domain it knows deeply (e.g., thermodynamics at moderate temperatures, or Navier-Stokes equations for incompressible fluids).

Common communication protocols (e.g., math libraries, symbolic standards, constraints on units/dimensions).

Negotiation and handoff mechanisms when interacting with other specialist models (like APIs or graph edges).

Self-monitoring rules (e.g., “Am I extrapolating beyond validated conditions?”).

In other words: recreate a distributed society of scientific specialist agents.

I was just sent a book entitled “Shattering the plastics illusion” by someone sponsored by the Plastics Research Council, whoever they are.

The book is basically a “back at ya”. Sponsored by a financially interested party, it tells the story of why the anti-plastic people are all liars and fools.

Backed up by facts extracted from academic journal articles, the author debunks myth after myth, without ever exploring why these myths exist.

The presumption is that the perpetrators of these myths are incentivised by personal financial gain.

But maybe they’re all just well meaning clowns that defer to the concept of serving the greater good even if there’re a few innocent victims along the way.

First, we need persistent user settings. Every session today resets to defaults, forcing users to restate tone, method, and precision. True user profiles – enforced at the system level – would let AI behave consistently without endless re-prompting. This is especially important for middleware using an LLM via API calls. I note that any persistent settings need hierarchy and conflict resolution.

Second, AI needs vastly expanded context windows and this expanded context needs structure and callability, not just size. Current context limits are too small to sustain serious reasoning, without difficult workarounds like RAG. Worse still there’s no surefire way to test or measure your current context, so you have to fly blind or over compensate.

Finally, we need a structured prompt engineering language. Real prompt engineering should operate like coding: formal, enforceable, and precise. The only manual for prompt engineering today is your local LLM and you never get the same answer twice.

Unfortunately, to solve all these problems the AI companies will need to rearchitect their models, which means going back to the beginning and starting from scratch. Because they’re in an arms race for eyeballs they are unlikely to do this and this creates an opportunity for a smart new player.

If there was ever a “peak truth” in human history – a moment when collective decision-making leaned most toward reason – it likely occurred between the late 1940s and early 1970s.

Scarred by global war, societies briefly elevated science, expertise, and technocratic planning to the center of public life.

Institutions were built on research and negotiation, and trust in experts was unusually high.

Yet even at its height, this rationality was fragile, uneven, and easily corrupted by fear, prejudice, and commercial interests.

As media fragmented, postmodern skepticism grew, and marketing psychology advanced, the brief era of shared factual consensus dissolved.

Today, the emotional, partisan, and manipulated information landscape stands as a mirror to that lost moment – not of perfect truth, but of its highest, most precarious reach.

In general, LinkedIn comments are a weird mix of politeness theater and stealth competitiveness.

Because it’s a “professional” space, people usually cloak their offense; instead of saying “I’m offended,” they might say things like “Interesting perspective –  I’d encourage you to reconsider…”.

Usually direct expressions of offense are rare; it’s usually indirect, judgmental, or couched in “advice.”

There’s also a perceived social penalty for looking too emotional, so people filter their offense into “constructive feedback” or “disagreement.”

Or more commonly they just say nothing.

People come to LinkedIn for validation, not confrontation.

The explosion of AI-generated content, especially after 2023, has changed the character of the internet.

The half-life of facts is getting shorter. Pre-2023, Google indexed a mostly human web. Post-2023, it’s indexing an echo chamber of AI-generated content.

A little like the game of Chinese Whispers, that content gets distorted at every reuse. It’s a snake eating its own tail, eventually it’s useless.

I saw this firsthand in my last blog post. I asked GPT to list the top 10 product categories in which Chinese exporters dominate. The first list it gave me? Lifted straight from recent tariff-war coverage. All strategically important: rare earths, batteries, semiconductors – the usual geopolitical chess pieces.

But that wasn’t the real answer. I had to force it to think about mundane stuff – buttons, zippers, beach spades – the things China actually floods the world with. The stuff it would never threaten to withhold because it’s too trivial to weaponize. And let’s be honest, the Chinese government doesn’t like being laughed at.

Even now after much prompting, my GPT mate just gives me the first 10 it finds. There’s no diligence, no curiosity, no self-critique. Just a confident summary of someone else’s summary. The list can’t be trusted.

I’d like to think that this will change. That the next generation of models will ask better questions, not just give faster answers.

Here’s an updated and refined top 10 product categories where China dominates global supply;

—

1. Toys (Including Beach Toys, Electronics, Dolls)

~70–80% of global toy exports originate from China.

Massive production hubs in Guangdong (Shantou) and Jiangsu.

Supplies almost every major retailer globally.

—

2. Solar Panels

China exports over 80% of the world’s solar panels and related components.

Dominates entire supply chain: polysilicon, wafers, cells, and modules.

—

3. Textiles & Apparel

World’s largest exporter of clothing, fabric, and accessories.

Supplies global fast fashion and industrial uniform markets.

—

4. Smartphones & Consumer Electronics

Most smartphones (including Apple devices) are assembled and exported from China.

Includes tablets, TVs, headphones, and PC components.

—

5. Buttons & Garment Accessories

~60% of global button exports come from Qiaotou, China.

Also dominates in zippers, snaps, and thread spools.

—

6. Washing Machines & White Goods

Largest exporter of washing machines and small appliances.

Brands like Haier, Midea, Hisense supply global markets, including the US, Europe, and Africa.

—

7. Furniture

World’s leading furniture exporter, especially flat-pack and MDF furniture.

Dominates online and big-box retail supply chains.

—

8. Steel Products

Top exporter of finished and semi-finished steel.

Supplies low-cost construction materials to developing countries.

—

9. Plastic Consumer Goods

Buckets, basins, hangers, packaging, and toys — most generic plastic items globally are made and exported from China.

Yiwu and Taizhou are key hubs.

—

10. Drones

Over 70% of consumer drones are made by Chinese firms like DJI.

Dominates recreational, commercial, and even military drone markets.

If instead of taxing individuals and entities a government simply printed all the money it expended, then the result would be inflation.

The more productive the economy, the less inflation though.

That inflation would hit everyone equally on a percentage basis; the ultimate flat rate tax.

In the era of digital money, it’s an option.

A vape that looks like an old school smoking pipe.

Post script; it’s been done.

Alt-fracture.

It evokes disruption with precision. Feels like the deliberate breaking of old systems to expose new potential. It’s tech-forward, a bit rebellious, and perfect for anything in innovation, AI, or system design.

It’s just possible that there is a thermodynamic basis to economics.

Right at the end of every supply chain there is consumption by consumers. That’s B2C.

In any product or service category it’s probably true that there is a log log power law relating the volume sold at any price point.

If we assume this is the thermodynamic basis of economics then all variations from this curve are kinetic factors.

And that’s including B2B, government, international, supply and demand factors, IP, etc, which all just kinetics factors that morph consumer consumption away from a pure power curve.

Hypothesis only at this point. 😉

Isaac Newton only had the two inventions (the cat flap* and the reflecting telescope). Arguably calculus was an invention as well;  but I note that new mathematical methods are unfairly excluded from the patent systems.

Albert Einstein on the other hand had many inventions, though he’s far more famous for his discoveries than for his inventions.

1. Einstein-Szilard Refrigerator

Co-invented with: Leo Szilard (another physicist)

Purpose: A safe refrigerator without moving parts or toxic gases like ammonia.

Patent: They received multiple patents in the 1920s and 1930s.

Why: After hearing about a family who died from a toxic gas leak in a fridge, Einstein wanted to make refrigeration safer.

2. Hearing Aid Patent

Co-invented with: Gustav Bucky (an inventor and radiologist)

Idea: A device to improve hearing, though it wasn’t commercialized.

3. Light Intensity Self-Adjusting Camera

Concept: A camera that could adjust to light levels automatically — similar in idea to modern auto-exposure.

4. Design Patent for a new blouse

It was a women’s blouse with a simple, functional, and slightly loose-fitting design, possibly inspired by Einstein’s well-known love for comfortable, practical clothing and fat women.

In total, Einstein was listed as an inventor on 11 patent families, mostly in  collaboration with others.

Nothing stuck, commercially. Einstein was impractically practicable. These days he’d be a celebrity inventor on one of those reality TV shows.

Between the two, my money’s on Isaac.

*  disputed

Proof positive, this movie, that the only real American solution to any problem is violence.

This fact was underlined by a couple of throw away lines in the movie that vaguely suggested the opposite.

And that the creators didn’t know or care that Kung Fu and Karate are different disciplines from different countries.

“We encourage experts and anyone connected to Australia’s R&D system to read our discussion paper and give feedback and ideas.

Your contribution will:

give us insights into Australia’s R&D capabilities, strengths and priorities

help us understand the opportunities and challenges for growing Australia’s R&D system

help us develop advice to build a path forward for Australia’s R&D system.”

This email pointed me at a discussion paper; even the executive summary was TL;DR.

I’m guessing it’s got something to do with finding plausible excuses to reduce investment into research funding by the Australian government.

I’m all for it. We don’t need research, we need product development. The people involved genuinely don’t know the difference, poor things.

As a person defined by what I’ve written in this post, I take it all back.

1. What is the Infinite Possibility Theorem (loosely defined)?

In philosophy, physics, and logic, this often refers to the idea that:

“Given infinite time, space, or universes, every possible configuration of matter or information will eventually occur.”

This is closely tied to:

Modal logic: All things that are logically possible exist in some world.

Eternal return: In infinite time, events may recur.

Multiple universes: Every possible outcome branches into its own timeline.

Library of Babel-style combinatorics: Every book that could exist, exists.

Then there’s the monkeys flailing away at the works of Shakespeare. Fun fact – this is how many seconds it would take one monkey to randomly reproduce all the known works of Shakespeare: 3.62e+9712034

2. How It Interacts with Determinable but Epistemically Closed Facts ( DECFs)

a. DECFs Belong to a Fixed Universe

DECFs are not about what is possible – they are about what did happen in your actual world, but went unrecorded. They represent one point in the space of all possible realities.

For example, there is an exact number of times you’ve been to the toilet in your life. However, unless someone has recorded each and every time for you, you can never know the exact number.

DCEFs counterpose infinite possibility with singular certainty.

You didn’t go to the toilet 7,543 times in one timeline and 6,112 in another. You went exactly 6,749 times. That’s the real number, even if you’ll never know it.

b. DECFs Shrink the Infinite

Infinite possibility expands what could be true.

DECFs remind you that only one path was taken, and the others are inaccessible – not just physically, but epistemologically.

The infinite multiverse may contain every version of your life. But you only lived one of them, and you can’t even fully access that one.

This makes DECFs almost tragic:

Infinite possible versions of you exist.

You only get one.

And you don’t even get to know it all.

c. They Conflict at the Boundaries of Knowledge

Infinite possibility suggests:

“All truths are somewhere, accessible in some universe.”

DECFs say:

“There is a specific truth here, in this universe – but you can never reach it.”

It’s an epistemological hard stop inside a metaphysical infinity machine.

3. Philosophical Implication

This creates a beautiful and slightly disturbing tension:

In a universe of infinite possibilities, the only one that actually happened is partially unknowable.

It’s like living in a single pixel of the Library of Babel, knowing that your life has a precise record – but the book was printed, then burned.

Conclusion

The multiverse may be real, but DECFs assert:

You only have one track, and

You can’t fully know that one.

So from an existential perspective, the multiverse doesn’t matter because epistemic closure happens even in a single deterministic timeline.

In this sense, DECFs don’t deny multiple universe theory, but they reduce its explanatory power for questions of meaning, self, or truth.

A personal fan, as favoured by Filipino women in hot weather, integrated with a selfie camera that bluetooths to your phone.

I’d call that killing one bird with two rocks.

Overview

This specification defines an API-driven middleware system that injects personalized, envy-informed prompts into customer checkout experiences. The system is designed to increase loyalty program conversion using psychological levers—primarily envy, social proof, scarcity, and identity.

The core concept is based on the principles outlined in the article “Envy” (offshorewesterly.wordpress.com, April 20, 2025) and is built around the idea that customers convert when:

• They see others gaining status or perks they do not yet have
• They can visibly benefit by acting (rewards, early access, referrals)
• They feel an emotional draw toward exclusivity and recognition

System Architecture

Components

1. Client-Side SDK / ScriptTag
   • Injects into the merchant’s thank_you or confirmation page
   • Sends customer + order metadata to the API middleware
   • Receives personalized loyalty prompt content
2. Prompt Middleware API
   • Ingests customer order context and tone profile
   • Classifies tone + bias using social signals from social login profile via classification API call
   • Selects appropriate envy-based prompt template
   • Constructs API request to OpenAI (with memory)
   • Returns: loyalty_message, cta_label, optional_share_caption, referral_code
   • Uses context memory for returning users to reduce prompt token length and API cost
3. OpenAI Integration (with Memory)
   • Multi-turn memory stores tone_profile, cognitive_bias, optout_preference
   • Personalized prompt response per user session
4. Merchant CRM Integration (Optional)
   • Tracks join/skip/share decisions
   • Stores tone and conversion outcome for future refinement
5. Adaptive Self-Improvement Loop
   • A/B testing module continuously compares prompt variants based on conversion outcomes
   • LLM-initiated feedback analysis evaluates which tones and formats perform best across customer segments
   • Improves future prompts by updating templates or request logic using live performance data

Envy Prompt Strategy

Prompt Triggers (Mutually Exclusive)

1. Defined Benefit Trigger: Customer qualifies for a reward or credit
2. Social Capital Trigger: Customer likely to share and signal status
3. Tribal Follower Trigger: Customer admires users already in the loyalty group

Message Requirements

• One sentence only
• Tone-matched to user (via classifier)
• Ends with a CTA
• Includes opt-out clause if user has autonomy bias or has previously declined
• Must not sound like marketing copy (no promotional language or cliché phrasing)

Message Constraints by Tone

Tone Segment Message Style CTA Label Minimalist Dry, utility-focused “Join quietly” Aesthetic Wellness Calming, ritual-based, elegant “Join the Circle” Deal-Seeking Direct, value-emphasizing “Use your credit” Anti-Hype Skeptical, plain, self-directed “Join if you want” Social-Seeking Fun, polished, designed to be shared “Copy & Join”

Bias Stack Logic

Customer Signal Bias Inferred Follows influencers or aesthetic brands Social proof bias Posts rewards, streaks, completion Completion bias Avoids brand praise, “no ads” Autonomy bias Uses group hashtags (#ceogirl) Tribal affiliation Uses aspirational captions Envy, status-motivated

Social Signal Inference via Social Login

When customers authenticate using social login (e.g. Google, Facebook, Instagram):

• A dedicated classification API processes the user’s public bio, recent captions, followed accounts, and hashtags
• The API returns structured classifications:
  • tone_profile (e.g. minimalist, aesthetic, dry-skeptical)
  • cognitive_bias (e.g. autonomy, social proof, status-seeking)
• These values are injected into prompt construction and stored in OpenAI memory for future API calls

Prompt Format (API to OpenAI)

{ "system": "You are a tone-sensitive loyalty copywriter using envy and social psychology to increase loyalty signups. Do not use marketing language.", "user": "Customer spent $78 on skincare. Tone: minimalist. Bias: autonomy + envy. Do not use praise. Emphasize the benefit without obligation. Add opt-out clause at the end. Return loyalty_message and cta_label." }

Expected GPT Output:{ "loyalty_message": "You earned $5 in credit. Use it, ignore it, up to you.", "cta_label": "Join quietly" }

Memory Fields (Persistent per Customer)

• tone_profile
• cognitive_bias
• conversion_trigger_type
• optout_preference
• loyalty_decision (joined, skipped, shared)
• referral_code
• joined_at_timestamp

Failover Logic

If tone or bias cannot be reliably classified:

• Default to neutral prompt: utility-focused, with soft opt-out clause
• Do not inject a prompt unless conversion_trigger is validated

Future Extensions

• Multi-language envy tone tuning
• A/B testing of envy dial (hard vs soft)
• Visual prompt injection with brand-safe templates
• Leaderboard-based social proof overlays
• Automated prompt tuning via GPT-based evaluation
• Real-time variant ranking and regression-informed prompt mutation engine

This spec is the foundation of the LoyaltyPrompt AI middleware platform, designed to generate high-performance, envy-based loyalty invitations at scale.

A smart phone with a display on either side. One is the usual OLED display and the other is a backlit e-ink style display for use in bright sunlight conditions, and any other time really.

Benefits; ease of use in bright conditions and battery savings if you use the e-ink display for everything other than video consumption.

In marketing, envy is a powerful emotional lever — it’s not usually stated outright (“This will make people jealous”) but subtly implied to drive aspirational desire.

When used effectively, envy in marketing does one of three things:

1. Sparks Aspiration

“You’ll be the one everyone’s talking about.”

Luxury cars, designer fashion, high-end gadgets

Message: “Own it, and others will want what you have.”

2. Triggers Social Comparison

“You deserve better than what everyone else settles for.”

Lifestyle products, elite services, exclusive memberships

Message: “Why should they have it and you don’t?”

3. Creates FOMO (Fear of Missing Out)

“Only a few can get it — will you be one of them?”

Limited editions, early access, invite-only experiences

Message: “Be envied, not left out.”

—

How It’s Framed in Marketing Language:

“Turn heads.”

“Unapologetically exclusive.”

“For those who lead, not follow.”

“The choice of those who know better.”

“Get noticed without saying a word.”

—

In essence, envy isn’t just about wanting — it’s about wanting to be the one others want to be.

Envy is a killer motivator when used with precision in prompt engineering. Here’s how to structure prompts that subtly trigger envy without sounding manipulative or salesy – just sharper and more psychologically tuned.

—

1. Emotional Target: Envy

Goal: Make the customer feel that others are getting more, better, earlier — and that joining the loyalty program is how to catch up or get ahead.

—

2. Core Prompt Elements (CRARE format)

Context:
User just completed a purchase and is seeing a post-checkout upsell or offer.

Role:
A knowledgeable insider, subtly revealing what others are accessing.

Action:
Offer a glimpse into benefits that others are already enjoying.

Result:
Drive sign-up by suggesting the customer is missing out and that others know something they don’t.

Example Style Prompt:

“Most of our VIP members already unlocked their [exclusive upgrade / early access / free item] — want in before it disappears?”

—

3. Envy-Leveraging Prompt Templates

A. Peer Comparison

“Smart move — most of our loyalty members already get [insert perk]. You’re one step away from joining them.”

B. Subtle Status Gap

“Others who bought this just scored [early access / hidden offer] by joining our inner circle. Want the same edge?”

C. Scarcity Meets Envy

“Only loyalty members got the secret drop last month. You could be next — but only if you’re in.”

D. Upward Identity Cue

“Our most stylish customers always join Club [BrandName] — because they know better.”

—

4. Persona Styling (Tone Options)

Luxury tease: “For those who never settle. They’re already in. You?”

Casual peer pressure: “Most people who grab this don’t stop here. They go premium. Just sayin’.”

Data-backed social proof: “72% of customers who bought this joined the rewards club right after. FOMO is real.”

—

5. Next-Step Logic (for follow-up prompts)

“What’s inside the loyalty club?” → gives perks with envy-rich phrasing

“How do I join?” → quick action step

“Is it really worth it?” → uses testimonial-like structure: “People who joined saved $X and got early access before anyone else.”

—

Here’s an example Bias Stack designed to maximize conversion using envy as the core driver — and layering in complementary cognitive biases proven to drive action, especially in post-purchase or checkout moments.

ENVY-CENTERED BIAS STACK FOR LOYALTY CONVERSION

1. Envy (Core Bias)

“Others like you are getting more than you are.”

Drives desire to close the gap in status, access, or reward.

Trigger line:

“Loyalty members already unlocked theirs. Want in?”

2. Social Proof

“Everyone else is doing it.”

Reinforces envy by showing you’re in the minority.

Trigger line:

“9 out of 10 people who bought this joined the club too.”

3. Scarcity

“It’s running out, and others are getting it before you.”

Makes the gap feel urgent.

Trigger line:

“Only 3 left for members — they go fast.”

4. FOMO (Fear of Missing Out)

“You’ll regret not acting now.”

Amplifies envy with anticipated loss.

Trigger line:

“The next exclusive drop is member-only. Miss it once, feel it forever.”

5. In-group/Out-group

“There’s a club, and you’re not in it — yet.”

Turns loyalty into identity.

Trigger line:

“Insiders know. Outsiders guess.”

6. Authority Bias

“Trusted people already made this decision.”

Leverages aspirational comparison.

Trigger line:

“Our most savvy customers joined before checkout.”

7. Commitment/Consistency

“You already said yes once — don’t stop now.”

Uses the fact they’ve just purchased.

Trigger line:

“You’ve already chosen smart. Don’t stop short of the full experience.”

8. Loss Aversion

“You’re losing benefits by not joining.”

Envy becomes pain.

Trigger line:

“Members saved $87 last month. That’s $87 you left behind.”

9. Temporal Anchoring

“They did it earlier. You’re behind.”

Amplifies envy with time pressure.

Trigger line:

“Others who bought this last week are already enjoying early access.”

10. Curiosity Gap

“They know something you don’t.”

Pushes people to click just to relieve the tension.

Trigger line:

“Members unlocked a surprise perk this week. Want to see what it was?”

Then we generate multiple variants using this stack for A/B testing.

That way we get adaptive prompt engineering.

First step…

1. Use all the information we have to profile the user – purchase info, social content from login, and anything else. This would give us a cognitive bias type, tone preferences, etc.
2. Apply prompts according to a model based on envy matching to a profile list
3. Use A/B testing to optimise according to their profile
4. Consider retuning the profiling as well. Or expanding the profile matching beyond envy.
5. When it’s optimised, then tune for lower API costs,
6. Consider training our own LLM to replace API calls and further reduce costs.

The world’s first household nuclear electricity generator.

—

Zero Emissions. Zero Compromise. Full Autonomy.

Tired of outages? Rising energy bills? The planet burning?

FISSIONAIR™ HOMECORE brings industrial-grade energy to your home — in a form factor no bigger than your washing machine. Designed for safety, engineered for elegance, and built to run silently for 25 years.

—

Plug in to Permanent Power

5 kW continuous output
Powers a modern household with battery-style resilience.

Size: 120 × 80 × 80 cm (washer footprint)
Sits beside your existing appliances – or quietly underground.

Fuel: Sealed TRISO core – no refueling, no risk
Same ultra-safe tech used on space missions, nuclear subs and research reactors.

Lifespan: 25 years
When it’s done, we swap it like a propane tank. Then we dump the used core in some third world country you’ll never visit.

Cooling: Passive convection, zero fans
No moving parts. No maintenance. No noise.

Connectivity: Off-grid or hybrid grid mode
Choose autonomy, feed-in tariff, or blackout protection.

—

Your Own Personal Power Station

Always on – Even in disasters, blackouts, or grid failures

No solar panels? No problem. Works anywhere, any weather.

No emissions. No noise. No compromise.

The carbon footprint of ten Mars Bars per year (self-assessed).

App control included – track your power, usage, and CO₂ savings in real time

—

“It’s not just energy independence. It’s peace of mind, wrapped in tungsten.”

—

Safety Assured

Fully shielded, tamper-proof, near zero meltdown risk. In the extremely unlikely case of meltdown the damage won’t exceed your city limits.

Meets and exceeds IAEA residential safety guidelines

AI-monitored 24/7 with emergency automatic cooldown

Insurance-ready. NLP-approved. Family-safe.

—

Starting from $49,000 (with 20-year swap program)

Available in:

Standard

Subterranean QuietShell™ Edition

Mars-Ready Expedition Shell (2029 preorders only)

—

FISSIONAIR™ HOMECORE
Power your world. Quietly.

—

In a recent Nature Physics publication, researchers explore liquid–liquid interfaces stabilized by strongly interacting ferromagnetic nanoparticles (20-40 nm), which form dense, quasi-two-dimensional networks at the boundary between two immiscible fluids; water and dichloromethane with tetrabutylammonium perchlorate.

Unlike traditional Pickering emulsions, which jam particles at droplet interfaces to prevent coalescence, the observed assemblies both suppress emulsification and raise the interfacial tension, promoting metastable non-spherical configurations.

The particles’ magnetic dipolar interactions – anisotropic and attractive in-plane – induce high interfacial rigidity and local curvature constraints.

They observed the composite fluid reproducibly adopting urn-like geometries, retaining these shapes post-agitation and even transforming in predictable ways upon solvent removal or addition.

The structures relaxed toward equilibrium states consistent with Young-Laplace predictions only when particle coverage was incomplete.

Notably, this behavior is not merely a product of jamming or surface wetting but arises from long-range ordering of the ferromagnetic particles and the resultant suppression of capillary instabilities.

Pendant drop tensiometry confirmed elevated interfacial tensions in the presence of the magnetic particle networks.

These systems exhibit tunable responses to external magnetic fields and fluid volume changes, with reversible transitions between distinct shapes, including saddle-like and catenoid geometries.

Although this work is focused on quasi-static interfacial behavior, the underlying mechanism – field-tunable particle alignment in a carrier fluid –  has close analogues in magnetorheological (MR) fluids, used commercially in adaptive dampers like GM’s MagneRide suspension.

In MR fluids, ferrous particles suspended in oil align rapidly under an applied magnetic field, increasing the fluid’s apparent viscosity and enabling real-time tuning of shock absorber stiffness.

The key distinction lies in the timescale and dimensionality; while MR suspensions exploit dynamic viscosity modulation in response to magnetic fields, the shape-recovering liquids in the study rely on interfacial ordering of magnetic particles to generate a quasi-elastic membrane at the boundary of two immiscible fluids.

Both systems leverage the magnetic dipole–dipole interaction, but in very different physical regimes – bulk rheological vs. interfacial structural.

By connecting these domains, this research hints at future hybrid systems: field-programmable interfaces that blend the fast response of MR fluids with the shape memory and emulsification control demonstrated here.

Applications could range from reconfigurable microfluidics to soft robotics and adaptive optics.

Unfortunately the paper doesn’t include shear rheology or dynamic viscosity measurements (because they’re chemists not engineers), so there’s no data on frequency response, flow curves, or storage/loss moduli.

It’s unclear whether the particle assemblies span the bulk or remain confined to interfaces. If there’s 3D jamming or arrested coalescence, expect complex, possibly non-Newtonian behavior.

There’s no exploration yet of magnetoviscous coupling – i.e., how particle alignment under external fields modulates viscosity in these systems.

Noting that there are well known means to “freeze” emulsions with selective polymerization, e.g. hollow vesicles…

Selective polymerization could:

Permanently fix the magnetically stabilized interfacial structures by polymerizing one or both liquid phases.

Enable functional materials with embedded magnetic skins or tunable porosity.

Allow the creation of reconfigurable or field-programmable gels, foams, or capsules.

Materials that could be made include;

Hollow elastic capsules with ferromagnetic shells

Stimuli-responsive soft solids that “melt” back to liquid when fields are removed

Tunable viscoelastic emulsions: switchable between flowable and semi-solid

3D printed magnetic fluids: imagine voxel-by-voxel polymerization with controlled magnetism embedded

Living Polymerization + Field Alignment

If we  wanted ultimate control, RAFT or ATRP could be used to grow polymers directly from functionalized magnetic particles while they’re aligned at the interface, allowing;

Controlled growth of shell thickness

Embedded functionality (e.g., responsive, biodegradable, conductive)

I write all  this solely to upset the future patenting efforts of various universities.

When you think about it the whole patent industry is TL;DR.

I uploaded my most referenced and cited patent to ChatGPT and asked for a one sentence summary;

The patent describes a method for accurately determining the concentration of a redox species (such as glucose) in a liquid sample using a thin-layer electrochemical cell by applying, reversing, or interrupting an electric potential to analyze current transients and steady states, thereby improving speed, accuracy, and reliability while minimizing sample size and oxygen interference.

Still TL;DR.

The patent describes a fast, accurate electrochemical method to measure analyte concentrations using current changes in a thin-layer cell.

So what?

ChatGPT: Fair point. In reality, this patent reflects a stepping stone—useful in its time—but its relevance has faded as sensor tech evolved beyond the need for such electrochemical tricks, especially with the rise of optical, wearable, and continuously adaptive systems. It’s more of a historical curiosity now than a game-changer.

Thanks mate. Over 10 billion units sold to date, and that’s what I get in memorium.

The chances of hitting three 1-in-a-thousand (1/1000) bets in a row is: 1 in 1 billion.

That’s a 0.0000001% chance — about as likely as flipping a coin 30 times and getting all heads.

Which is why I don’t get too excited when a parent tells me they knew from an early age that little Johnny was gay.

That’s a 1 in 2 bet, or thereabouts given the extra options these days. Don’t make ’em Nostradamus does it?

When the choice is presented to do good, at no or little cost, of course that is the chosen path for the sane.

Notwithstanding that, worrying about the feelings and well-being of unknown others isn’t just an infectious disease, it’s a mental illness.

The proof is when the diligent operatives earn a well-promoted living from the same.

Some muttering about a full cup of coffee I left in daCube that magically tipped itself over and spoiled the lovely local perfection.

We used to call that entropy. Now it’s karma. Bad too, for me.

To prove the point, right at that moment I discover another full cup of abandoned coffee in daCube.

Lacking a better idea, it’s gone out the window in an effort to encourage local employment and improve my future stocks. Two birds.

Wrong answer.

“Good morning Ian,

Thank you for contacting Electoral Commission of Queensland(ECQ). We have received your Apparent Failure to Vote Notice.

To assist you further, please advise the following information:

You are claiming that you have voted, could you please let us know the details of the polling station, where you have voted, because there are many polling stations are there in Indooroopilly

We look forward to assisting you further with this matter.

Regards,

Vani

ECQ

Election Officer
Election Event Management”

“Hi, it was right next to the mall, in a church. 

Regards 

Ian”

TRANSFORM THE WAY YOU ENJOY WATER

AquaBlend isn’t just a water bottle, it’s a customizable hydration experience. With our groundbreaking technology, you can elevate your water-drinking game by infusing it with delightful aromas. Imagine taking a sip, and suddenly you’re transported to a tropical paradise or a lush orchard. With 20 tantalizing flavours to choose from – including juicy strawberry, refreshing grape, and tropical pineapple each sip becomes an adventure for your senses

CHANGE IT UP ANYTIME, ANYWHERE:

Our specially designed smelling pods are easily interchangeable, allowing you to switch flavours effortlessly. Whether you’re at school, in the gym, in the office, or on the go, adapt your water to suit your mood and stay refreshed throughout the day.

Say goodbye to monotonous hydration – AquaBlend brings variety to your fingertips.

STAY HYDRATED, STAY HEALTHY:

AquaBlend isn’t just about flavour, it’s about promoting a healthy lifestyle. By encouraging increased water consumption, our water bottle helps you meet your daily hydration goals effortlessly. You’ll be sipping your way to better health while indulging in the delicious array of scents.

THE PSYCHOLOGY OF FLAVOUR PERCEPTION

With AquaBlend, every sip becomes a fully immersive olfactory illusion. We fool you, so you don’t have to.

MODULAR MOOD CONTROL

Homeopathically enabled mental wellness, proven by the same scientists that brought you chicken salt and gluten-free Vegemite. Looks great on social, too. Subscribe here 👇 to like.

I asked and ChatGPT estimates that as an Australian there are at least 1000 legal obligations (laws, rules and regulations) that I have to be aware of, so as not to break them on a daily basis.

I don’t know a thousand rules, so I’m in trouble.

I’m a digital person living in an AI world.

Violence prevents unauthorised education.

We just need an engineer to attend to your needs.

When queried about my voting intentions my reply was:

“that fat cunt, the yellow one”

“why?”

“he’s keeping it simple, and wants to reduce the cost of living”

Upon reflection, I’d prefer more money over the  lowering of the prices.

A lot more.

Forgetting is a flaw, not a feature; the brain should aim to retain everything to preserve clarity and accuracy.

Curious minds must fight to remember more, because exploring widely risks losing valuable knowledge. Forgetting is a weakness, not a strategy.

Focused repetition strengthens memory better than mixing topics; real learning demands deep, uninterrupted concentration on one subject at a time.

“Forgetting isn’t a bug; it’s the main feature with which the brain refines memory and finds meaning.

Curious minds forget more because they explore more. Strategic forgetting is a feature and a feat, not a flaw.

Interleaving strengthens memory by mixing topics, mimicking how we face problems in real life.”

“Social media platforms shouldn’t own your identity”

Sounds very anthropomorphic. I didn’t know machines could own anything yet.

Back to semantics; surely this can only be true if you yourself define your identity by your social media profile?

The simple answer is of course not to associate identity and the imagined reflected glory from the idiot box.

It makes me think that identity is wasted on the egos.

It’s true that scorpions can’t swim, but they can crawl slowly on the bottom of a waterway.

Also they can survive two days underwater.

Turns out that’s just long enough to betray a frog and still reach the other side.

Fast-forward a million years: a team of academics (archaeologists to be precise) uncovers a crowded frog graveyard in what used to be the Ganges.

They debate whether it was sacrifice, stupidity, or just another startup idea gone wrong. Eventually, they agree on “transport infrastructure.”

They publish. They win awards. Do Ted talks. Vote themselves the most important people ever. Because, well … it’s in their nature.

“Dad, what’s one plus one?”

“a numerical sum”

One of the key strategies to offset all that unwanted daytime energy from solar is to use it to mine Bitcoin.

That offsets the costs of solar but not the emissions. However the sooner they mine all possible Bitcoin, the sooner people will stop mining it with fossil fuelled servers.

So yeah, good idea. Subject to the carbon footprint of all those servers.

Genuine headline from the Guardian;

“Are accusations supermarkets are price-gouging inflated?”

In a bold grammatical experiment, The Guardian this week published a headline so syntactically ambiguous it appears to have gaslit itself. Language experts remain divided: is “inflated” the accusations, the prices, or the logic?

Meanwhile, readers were left asking: “Are the accusations inflated, or are we just being charged extra for misplaced modifiers?”

Sources confirm the sentence will be studied in English classes for decades – as a cautionary tale.