The World is Unraveling: A 3-Step Guide to Staying Sane & Useful

MindBlog has now put out a series of AI assisted posts on the disintegration of the world we have known and the infusion of LLMs into our possible futures. This is the final entry in this series, and takes on the Nate Nagins essay "What to do as the world falls apart: A frame work for action."  As usual, I would urge you to read the entire article as I have.  But again I asked the usual culprits (ChatGPT, Claude, Gemini, and DeepSeek) to reduce Hagins' text to provide a title and text for a MindBlog post of moderate length, and for the first time, preferred the quirky terse response from DeepSeek over the gravitas of the other three LLMs. Here is my prompt to the bots, and the DeepSeek response:  

Prompt:  I'm finding the essay by Nate Hagins at https://natehagens.substack.com/p/essay-what-to-do-as-the-world-falls mind complex and intricate, as befits the subject but not my poor brain. Could you please cook this down for me and generate a MindBlog post draft with a title and text that is not too many paragraphs long that makes clear the basic take home messages?

The Big Takeaway: We are at the end of an era built on cheap, magical energy (fossil fuels). A major geopolitical event (like a war cutting off oil) has just lit the fuse on a long-predicted economic and ecological contraction. Stop waiting for a "return to normal." Instead, focus on three nested levels of action: Fix Yourself → Find Your Tribe → Work on the 6 Key Fronts.

Level 0: The Inner Work (Don't Skip This)

Before you can help anyone or fix anything, you must stabilize your own nervous system.

• The Problem: Chronic doom-scrolling, outrage, and fear put your brain in fight-or-flight mode. You cannot think clearly or build coalitions in this state.

• What to Do: Do the "work" of grieving, cultivating equanimity (holding difficulty without being destroyed), and stepping back from digital addictions. Get your actual, real-life house in order (finances, location, basic supplies).

• The Mantra: A calm, grounded person is the most valuable resource in a crisis.

Level 1: Find the Others (You Can't Do It Alone)

Isolated preppers fail. Resilient communities survive.

• The Task: Identify the 5-10 people in your real-life network who also sense that something fundamental is breaking. Start talking honestly.

• The Goal: Build a shared vocabulary and trust before the crisis hits. This isn't about having a plan yet; it's about having a team. This is your "connective tissue" for scenario planning (e.g., "What if food shipments stop?").

Level 2: The 6 Fronts for Action (Pick Your Lane)

Once you are stable and have a trusted group, you can act. Don't try to do all six. Find where your skills fit.

1. Stock & Flow (Physical Stuff): Localize energy, food, water, and supply chains. Think redundancy, not efficiency. Example: Community gardens, tool libraries, solar with battery storage.

2. Ecological Interventions: Protect nature from desperate humans during the coming contraction. Regenerate soil, defend remaining wild spaces, and work on "global cooling" (planting trees, higher albedo). Note: The coming economic crash will cut emissions faster than any technology.

3. Dignity Infrastructure (For the Vulnerable): Set up mutual aid networks for food, shelter, and childcare. This is about keeping people treated as humans, not just "alive."

4. Civic Resilience (Governance): Create local, participatory decision-making (citizen's assemblies). Focus on violence prevention (stopping scapegoating) and accountability. The goal is to keep institutions legitimate, even as they shrink.

5. Culture & Meaning (The Stories): Shift from "consumer first" to "citizen and place-maker." This means reconnecting to your local ecology, creating new rituals, and helping your community grieve what's lost without collapsing into despair.

6. Economic Transition: Build post-growth systems: local currencies, barter networks, cooperative ownership of land and housing. Start building the new economy inside the shell of the old one.

The Most Important Mental Model: The 3 Phases

We are not in one crisis, but three overlapping phases. What you do depends on the phase.

• Phase A (Stability Window – Right Now): Build everything that requires stability. Trust, infrastructure, relationships, skills transfer. This window is closing.

• Phase B (Bend, Don't Break – Arriving Now): Triage mode. Maintain critical functions, bridge communities, prevent cascading failures. Let go of long-term projects; focus on what keeps things from snapping.

• Phase C (The Stable Attractor – The Destination): A smaller, slower, regenerative, locally-rooted world. The work you do in Phase A determines whether Phase C is a "Mad Max" hellscape or "The Great Simplification" (resilient & humane).

Final Bottom Line for your Brain:
Stop hoping for a return to the old world. Phase A is now. Your job is to:

1. Calm your own nervous system.

2. Find 3-5 local people to talk to.

3. Pick ONE of the six fronts (food, energy, governance, etc.) and take one small, physical action this week.

The future will be built from inside the disruption, not after it. Get to work.

 

Getting Gooier: How AI Is Reshaping Human Nature

This post is the result of my back and forth interaction with Claude Sonnet 4.6 that has yielded the following summary of  Venkatesh Rao's recent essay, "Getting Gooier", followed by some perspectives that Rao does not address on Friston's active inference framework and the physiology of agency:

Venkatesh Rao's recent essay "Getting Gooier" makes a point worth sitting with: most AI commentary obsesses over how the world will change, while quietly assuming that humans stay essentially the same — just reshuffled among familiar roles (generalists thrive! storytellers inherit the earth! software engineers disappear!). Rao argues this is the wrong ontology. The real question is how AI is changing human nature itself.

His framework draws on Alan Watts's distinction between prickly and gooey people. Prickly people are tough-minded, precise, boundary-drawing; gooey people are tender-minded, synthesizing, prone to letting distinctions dissolve. All of us carry both, in varying ratios.

Rao's hypothesis: because AI feels like a psychologically safe counter party, we are more willing to expose our gooey side to it and suppress our pricklier instincts. Sustained AI use amplifies the gooey side. We become gooier. He notes that people who insist on prickly, suspicious, line-by-line relationships with AI agents tend not to use them effectively and retreat. People who can vibe with the machine — never even opening the code editor, just watching the agentic shell fly — will likely thrive. The first major gooified interface is, after all, called vibecoding.

The flip side is subtler: as more gooey relational needs are met by AI, the human-facing side grows less inclined to take the emotional risks required to balance prickles and goo with other people. We don't necessarily get pricklier toward humans — we just disengage unless the expected rewards are significantly higher. Your machine-face gets gooier; you look relatively pricklier to other humans.

In the medium term, Rao predicts greater atomization — or "molecularization" — as people grow more distant from other humans while becoming more intimately entangled with their AIs. He sees this as more sustainable than social-media-driven atomization, though the mechanisms for eventual re-convergence into new digitally mediated social forms aren't yet visible.

Following Virginia Woolf's famous claim that "on or about December 1910, human character changed," Rao proposes that on or about December 2025, human nature changed again — with the Claude Code moment being more definitive than the ChatGPT moment, because agentic coding creates a fundamentally alien way of being, open-ended enough to make us as alien as we dare to become. It is, he says, a portal to transhumanism.

---

Rao's prickly/gooey axis maps naturally onto Karl Friston's active inference framework, and the connection carries some weight. In that account, what we experience as a "self" is a precision-weighted predictive model — a system that assigns confidence to its own predictions and acts to fulfill them. Getting gooier, in Fristonian terms, looks like a reduction in precision-weighting of prior beliefs: a loosening of the grip that constitutes a rigid, bounded selfhood. That loosening isn't necessarily pathological. It can be a precondition for learning, creativity, and genuine engagement with novelty.

But there's a physiological dimension Rao doesn't address, and it connects to questions I've been exploring in recent MindBlog posts and in an ongoing correspondence with my European colleague Heribert on the physiology of agency in the age of AI. Daniel Wegner's work frames the feeling of agency — the sense of being the author of one's own actions — not as a metaphysical claim about free will, but as an evolved emotion, as functionally real as fear or grief. Martin Seligman's learned helplessness research gives that claim empirical teeth: sustained loss of felt agency doesn't merely feel bad, it triggers measurable physiological debilitation. The autonomic nervous system, it turns out, needs the experience of authorship to maintain homeostatic equilibrium.

This raises a question Rao's framing implicitly sets aside: is getting gooier — letting the AI absorb more of the regulatory and decisional load, softening the boundary of the agentic self — compatible with the physiological requirements of human wellbeing? Or does sustained gooification, however pleasurable and productive in the short run, erode the felt sense of agency that keeps the organism in regulatory balance? Heribert has described this as "externalization of self-regulation" — not merely cognitive offloading, but emotional and autonomic offloading. That's a different and more serious claim.

The honest answer is probably: it depends on the mode of engagement. Gooiness that arises from confident delegation — the experienced surgeon handing off a routine task — is physiologically distinct from gooiness that arises from passivity, confusion, or a sense that the machine is simply running past you. Rao's vibecoder who chooses not to open the code editor is in a different physiological position than the one who is simply lost. The challenge ahead is cultivating the former while recognizing that the latter may be far more common than the early-adopter narrative suggests.

 

Agentic AI and the next intelligence explosion

This post is the second of two recursive returns to engage the ideas of Blaise Agüera y Arcas, which were the subject MindBlog posts on 3/13/26 and 3/16/26.  Here is text of Evans, Bratton, and Agüera y Arcas, as summarized by ChatGPT:

The article, “Agentic AI and the next intelligence explosion,” by James Evans, Benjamin Bratton, and Blaise Agüera y Arcas, argues against the familiar “singularity” image of one superintelligent machine bootstrapping itself into godlike autonomy. The authors say that model is probably wrong at its core. Intelligence, in their view, is not a single scalar quantity that one mind simply has more or less of. It is plural, relational, distributed, and social. The next “intelligence explosion” will not look like one silicon mind rising above us, but like a vast ecology of human and nonhuman agents interacting, arguing, coordinating, competing, and forming institutions.

Their key move is to treat agentic AI as continuous with earlier evolutionary jumps in intelligence. Primate intelligence scaled with social group life; human language created a “cultural ratchet”; writing, law, bureaucracy, and markets externalized cognition into institutions that no individual fully understood. AI, in this picture, is another step in that sequence: the accumulated products of human social cognition have been compressed into models and made operational in a new substrate. What is becoming powerful is not isolated abstract reason, but social intelligence reanimated in computational form.

The article also points inward, to what happens inside reasoning models. The authors cite work suggesting that frontier reasoning models do not merely improve by “thinking longer.” They appear to generate internal, multi-perspective conversations: arguing, checking, revising, and reconciling. They call this a “society of thought.” The claim is that strong reasoning often emerges from structured disagreement, even when the “group” is simulated inside one model. This echoes an older cognitive-science idea: reasoning is not just private calculation but an internalized social process.

From there the authors shift to design. If intelligence is social, then better AI will not come only from larger models or more compute. It will come from building richer agent societies: systems with roles, hierarchy, specialization, parallel deliberation, devil’s advocacy, conflict norms, and institutional checks. Current reasoning models are likened to a single “AI town hall transcript”; future systems may need architectures closer to organizations, courts, labs, markets, or bureaucracies, where different agents occupy different functional roles and constrain one another.

This leads to their main governance argument. The dominant alignment picture, reinforcement learning from human feedback, is framed as too dyadic: a parent correcting a child. That may not scale to worlds containing billions or trillions of interacting agents. The authors propose “institutional alignment” instead: not just making individual agents nice, but designing persistent protocols, roles, audits, checks, and countervailing powers. A courtroom works because judge, attorney, jury, procedure, evidence, and appeal are structured roles; similarly, AI systems will need institutional architectures, not merely tuned personalities.

The concluding image is that the intelligence explosion is already beginning, but as a city, not a single meta-mind. It is visible in human-AI “centaur” workflows, internal societies of thought within models, recursive agent systems that fork and recombine, and emerging questions of constitutional governance among artificial and human actors. Their final message is blunt: the central issue is not whether intelligence will become more powerful, but whether we build social and institutional infrastructure adequate to the kind of intelligence that is actually emerging.

 

AI Is Not an Alien Intruder — It Is the Latest in a Four-Billion-Year Evolutionary Cascade of Symbiotic Transitions

This post is the first of two recursive returns to engage the ideas of Blaise Agüera y Arcas, which were the subject MindBlog posts on 3/13/26 and 3/16/26.  Here is the storyline as organized by Claude sonnet 4.6

Blaise Agüera y Arcas, VP and Fellow at Google and founder of the Paradigms of Intelligence research group, has just published two related books with MIT Press: What Is Life? and What Is Intelligence? (2025). His argument, developed across these books and a series of recent lectures (including a September 2025 Long Now talk and a Harvard Berkman Klein event), is one of the most sweeping attempts to unify biology, computation, and the meaning of AI that I've encountered. Here is the core storyline.

Life as computation — the foundational move

The argument opens with a mid-twentieth-century insight from John von Neumann: any self-replicating system requires a universal constructor (a "machine A" that reads instructions and builds), a tape copier ("machine B"), and an encoded description of itself on the tape. This is exactly the structure of biological life: DNA is the Turing tape, ribosomes are the universal constructors, DNA polymerase is the tape copier. From this, Agüera y Arcas draws the technically serious conclusion that everything alive is a computer — not in the sense that living things are secretly digital, but that the core processes allowing for biological life, namely replication and evolution, are inherently computational processes. Biological computing is massively parallel, stochastic, and distributed, but it is computation nonetheless.

Abiogenesis as a computational phase transition

Rather than treating the origin of life as a singular mystery, Agüera y Arcas frames living systems as a "self-modifying computational phase of matter." His team demonstrated this experimentally with an artificial-life system they call "bff" — a soup of random byte-tapes that, after millions of interactions with no pre-seeded replicators, undergoes a sharp phase transition in which complex, self-replicating programs emerge spontaneously. The implication is that life's emergence from chemistry is not a long-shot miracle but a predictable attractor: wherever the laws of physics permit computation and there is free energy and randomness, replicators will tend to arise because they are more dynamically stable than non-replicating structures. The Second Law of Thermodynamics is not violated, merely locally outrun.

Symbiogenesis over mutation — evolution's real creative engine

Classical Darwinism, in this framework, captures only half the story — the fine-tuning half. Agüera y Arcas argues that symbiogenesis, in which small replicating entities merge into progressively bigger and more capable ones, is a more important driver of evolutionary innovation than random mutation and selection. Evolution's increasing complexity is explained not by random walks through genetic space, but by a hierarchical stacking of cooperative mergers: RNA and metabolism fusing into the first cells; prokaryotes merging to form eukaryotes; cells banding into multicellular organisms; organisms forming social groups. Each such combination produces qualitative leaps that incremental mutation alone cannot generate — the same way a hafted spear is not merely an improved stone point, but something categorically new.

Life and intelligence as the same phenomenon

Perhaps the most radical move is the collapse of the boundary between life and intelligence. Once you have a self-replicating computing device living in a dynamic environment populated by other such devices, selection pressure immediately favors the ability to model and predict that environment — including the behavior of others. Intelligence is not a late-arriving luxury bolted onto life; it comes along with life and is selected for in the same way. Prediction, Agüera y Arcas argues, is fundamental not only to the brain but to life itself. In his most recent lectures he extends this further, making the functionalist claim that free will and even consciousness are not special properties of carbon-based biology but emergent features of any sufficiently complex, self-modeling computational process.

AI as the latest major evolutionary transition

This is where the argument converges on its most consequential conclusion. AI is not an alien intruder. It is the latest instance of the four-billion-year pattern: computational entities entering into new symbiotic relationships, modeling each other, merging, and producing systems that are simultaneously more complex to model and more powerful as modelers. The step from human cognition to human-plus-AI cognition is, on this account, structurally analogous to the step from free-living prokaryotes to the eukaryotic cell — a major evolutionary transition, not a rupture. Understanding and stewarding what comes next therefore requires thinking in evolutionary terms, not in the vocabulary of invasion, alignment against an adversary, or human exceptionalism. The real superintelligences, Agüera y Arcas notes wryly, already surround us: corporations, religions, markets — all are symbiotic cognitive entities that long since exceeded any individual human mind.

---

Agüera y Arcas's online book is available in full at whatisintelligence.antikythera.org. His Long Now essay "Life, Intelligence, and Consciousness: A Functional Perspective" (August 2025) is the most concise distillation of his recent updates on consciousness and free will.

 

 

The Tech Mirage: Why the U.S.-China AI Race Is Failing Us All

I asked ChatGPT, Claude, Gemini, and DeepSeek to summarize Yi-Ling Liu's recent New York Times essay, in the form of a MindBlog post,  and pass on Gemini's version:

We’ve all heard the breathless headlines about the high-stakes technological showdown between the U.S. and China. In Washington and Silicon Valley, the narrative is delivered like a Hollywood script: a binary, winner-take-all sprint toward Artificial General Intelligence (AGI), where the victor claims absolute global dominance.

But if you look past the geopolitical theater, a starkly different reality emerges. Journalist Yi-Ling Liu’s recent New York Times essay, "The Shared Feeling of Being Harvested by the Future," offers an eye-opening reality check. The true divide today isn't between Washington and Beijing. It's between the elite who are bankrolling this future, and the global working class who are currently being crushed by it.

---

The Illusion of the "Race"

The mainstream narrative thrives on binary comparisons: American capital, chips, and frontier software models versus China’s hardware talent, manufacturing speed, and rapid societal scale. We watch U.S. tech moguls panic over cheap Chinese open-source models like DeepSeek R1 , while American influencers travel to Shenzhen to stream videos of humanoid robots and drone-delivered fast food.

But this intense framing serves a convenient corporate purpose: it acts as the perfect excuse for tech giants to sprint forward without constraints, ignoring safety guardrails in the name of "beating the enemy".

Parallel Lives, Shared Precarity

When you peel back the nationalistic rhetoric, everyday life for a knowledge worker or gig laborer in San Francisco looks shockingly similar to life in Shanghai.

• Algorithmic Disempowerment: A Didi (China’s Uber) driver pleading with passengers to game the app's code just to keep a spot in the airport line faces the exact same precarity as a DoorDash or Amazon Flex worker in the U.S..

• The "996" Hustle Culture: To cash in on the AI gold rush, Silicon Valley tech workers have earnestly adopted China’s infamous "996" work schedule (9 a.m. to 9 p.m., 6 days a week). Meanwhile, in Beijing's tech hubs, office windows burn through the night as engineers exhaustively burn through Claude tokens to build products.

• Corporate Surveillance: AI isn't just a future threat; it is already acting as a digital boss in both countries—tracking attendance, flagging idle hours, predicting growth potential, and deciding who to hire or fire.

As one disillusioned internet user in China aptly put it, this isn't embracing the future; it's "being harvested by the future."

Coping in an Out-of-Control World

Faced with "gradual disempowerment"—the quiet erosion of human agency by ever-more-capable AI—the youth of both societies are experiencing a deep social and spiritual fracture. They are turning to identical survival mechanisms:

• Frictionless Companionship: Loneliness is being monetized at scale. Over 70% of American teens use AI chatbots for companionship , while nearly half of young Chinese people use them to cope with mental health in a society where single-person households are skyrocketing.

• The Occult and Religion: Gen Z in America is driving a massive boom in astrology apps and a rediscovery of traditional Christianity. In China, fortune-telling bars are popping up, and young people are literally asking AI models like DeepSeek to predict their futures amidst shrinking job prospects.

• Hyper-Nostalgia: When the future feels terrifying, the past becomes a sanctuary. This explains the massive, cross-cultural appeal of internet figures who romanticize an off-the-grid lifestyle—whether it's China’s pastoral vlogger Li Ziqi or America’s homesteading "tradwife" Ballerina Farm.

Breaking the Cycle: A Call for Global Alignment

When global systems feel completely detached from human values, the easiest response is to surrender, be passive, and—as Chinese netizens say—"let it rot."

But Liu argues we have a better choice: cross-border, human-to-human solidarity. We have seen flashes of this before. In 2019, when Chinese programmers launched the online campaign "996.ICU" on GitHub to protest grueling tech hours, they received immense support from American tech workers in one of the largest online worker mobilizations in history. Furthermore, scientists and policymakers globally are already quietly meeting at international conferences to demand that advanced AI remains aligned with human values.

Instead of fixating on which elite class crosses the finish line first in a manufactured race, the everyday people of both nations need to realize they are facing the exact same algorithmic threat. It’s time to stop looking at a foreign country as a meme or a bogeyman, and start working together to lift up the people this future is leaving behind.

When Execution Gets Cheap, What Remains Scarce? - The last biological moat.

I have enjoyed reading a recent essay by Aneesh Sathe, which I recommend you read in full. I will pass on here the equally amazing job that Claude Sonnet 4.6 did in summarizing its main points, then responding to my editing and emphasis suggestions, and also adding some additional ideas on the relevant neurobiological substrate: "the last biological moat" - what is left for the human mind to do. Here is the result, which begins with the title of Sathe's essay: 

The Lightening of Intent: When Execution Gets Cheap, What Remains Scarce?

Aneesh Sathe's essay "The Lightening of Intent" is one of the more intellectually disciplined takes on AI's civilizational meaning I've encountered — grounded in energy economics, manuscript history, and complexity theory rather than hype. It builds explicitly on Venkatesh Rao's "World Machines" framework, published just this week, and the two pieces read best together.

---

The World Machines Backdrop

Rao's framework organizes civilizational history into overlapping "machines" — planetarities, each with a nominal lifespan of about a millennium, cycling through Dawn, Day, and Dusk phases. Currently, the Modernity Machine is entering its Dusk stage, the Divergence Machine has reached its Day stage, and the Liveness Machine has just been born into its Dawn.

The Liveness Machine is only being born now because real AI has emerged. The most leveraged use of energy, whether renewable or not, will be to power AI. And AI will animate a planet-scale Liveness Machine — whether it is a grimdark or solarpunk version is yet to be determined.

Sathe's essay fills in the economic and physical mechanisms underneath that historical arc.

---

The Core Argument

The cost of putting an idea into the world has fallen by roughly five orders of magnitude over the last millennium. The bottleneck has reversed: arranging atoms used to be the hard part; now, having ideas is. Soon, it will be intents.

The Codex Amiatinus — the oldest complete Latin Bible — is Sathe's anchor image. It weighed about seventy-five pounds, required close to one thousand calfskins, cost years of scribal labor from sixty monks, and the life of the abbot who carried it toward Rome in 716 CE.  Today, a blog post costs nothing and reaches more readers in an afternoon.

---

The Numbers Worth Noting

Manuscript-to-print transition:

• Pre-print Europe held fewer than five million manuscripts; the sixteenth century produced two hundred million printed books, the eighteenth a billion.
• Gutenberg produced a hundred and eighty Bibles in the time a scriptorium managed one. Book prices fell 2.4 percent per year for over a century; each new printer in a city dropped prices by another quarter.
• The doubling time for European book production collapsed from roughly 104 years before 1450 to 43 years after.

Energy rate density (Chaisson's framework): This quantity — free energy flow per unit mass in ergs per second per gram — rises monotonically with complexity: galaxies ≈ 0.5; stars ≈ 2; planets ≈ 75; plants ≈ 900; animals ≈ 20,000; the human brain ≈ 150,000; modern human society in aggregate ≈ 500,000 — the most energy-dense phenomenon known.  AI will push this higher still.

Per-capita energy consumption: It has risen from about two thousand kilocalories per day in the Paleolithic — all of it food — to two hundred and thirty thousand in the modern United States.

Energy return on investment (EROI):

• Modern agriculture requires 13.3 calories of fossil-fuel input per calorie of food consumed.
• Fossil fuels at the useful-energy stage return only about 3.5 calories per calorie invested; road transport, 1.6 to 1. The estimated minimum EROI for a complex society is about 5 to 1.
• Solar PV costs have fallen from $106 per watt in 1976 to under $0.10 today — a 1,300-fold decline in under fifty years — with an estimated useful-stage energy return of 25 to 30:1, seven to nine times higher than fossil fuels.

Data accumulation: The internet holds something on the order of two hundred zettabytes by 2026, mostly text and image, mostly read by machines. Roughly ninety percent of all data ever created has been generated in the last two years.

---

Key Conceptual Moves

The substrate-spark distinction. Sathe draws an analogy to the prebiotic ocean: the pre-life ocean held amino acids and nucleotides for hundreds of millions of years before anything used the accumulation. The chemistry was not the difference; what mattered was that something started to act on it. Data without intent is a soup of records that accumulates and forgets.  LLMs are the first time the substrate has been wired to a borrowed spark of human intent — which maps closely to what Rao calls the Liveness Machine's defining property: AI is oozy, like a primordial soup that harbors intensely reactive chemistry.

Atoms downstream. The HTTP standard, written as a specification in the early 1990s in some weeks, has restructured several trillion dollars of physical economic activity over thirty years. The atoms moved themselves.  The direction of causation between ideas and matter has inverted.

The auteur mode. A bench scientist in 2026 submits a query to a generative model and receives a thousand candidate molecules in twenty minutes; her job is no longer to generate, it is to pick.  Taste, selection, and direction become the scarce inputs. Rao frames this as "execution pull" — AI drawing us out from vita contemplativa regimes into vita activa regimes.

Intents red in tooth and claw. As the substrate becomes more responsive, intent becomes the competitive variable. The first generation of intent-collisions is three to five years out; the shape of the era will be determined in that interval.  Rao places this on a longer timescale: divergence will dominate in the short term (2–5 years) but liveness effects will compound more steadily and dominate in the long term (beyond 5 years).

The energy caveat. The whole argument rides on an energy transition. If the solar transition holds, the Liveness era inherits a re-powered version of the Modernity Machine's infrastructure, sustained on incoming sunlight rather than deposited carbon. If the transition does not hold, the substrate degrades faster than the intent-driven economy can mature, and the lightening of intent ends as a brief anomaly. Both outcomes are within reach.

---

Why This Matters 

Sathe and Rao together make a tightly nested argument: civilization is a thermodynamic system that keeps burning hotter; each energy-surplus step builds infrastructure that amplifies individual intention; AI is the latest and sharpest such amplifier; and the emerging bottleneck is not execution but what you actually want. For those of us who have spent careers thinking about the neural substrates of agency and intention, the question has an obvious next layer: what, neurobiologically, is the capacity that remains scarce when everything else gets cheap? Sitting with confusion long enough for clarity to emerge — Sathe's phrase — sounds a lot like what the prefrontal cortex does when it holds competing representations in working memory and waits for resolution. That may be the last purely biological moat.

---

Sathe's companion essay, "The Viscous Frontier", takes up how to act in this regime — with attention as your constraint and no canonical direction pulling. Rao's full World Machines archive is at Contraptions.

The Last Biological Moat: Intention as Prediction Error Suppression

Sathe's claim that sitting with confusion long enough for clarity to emerge remains irreducibly human invites a neuroscientific gloss. In Friston's active inference framework, intentional action is not the initiation of a motor command but the suppression of prediction error about a desired future state. The brain generates a model of how the world should be — the goal — and then acts to make sensory input conform to that model, minimizing the divergence between predicted and actual states. What Sathe calls "formulating a direction" is, in these terms, the construction and stabilization of a prior over future states: the brain committing, against competing attractors, to one preferred trajectory through state space. This is metabolically and computationally expensive precisely because it requires holding an unresolved representation in working memory — prefrontal cortex sustaining an active prior — while suppressing the pull of more immediately rewarding or more habitual alternatives. The "confusion" phase is not inefficiency; it is the system sampling the landscape before locking the prior. AI systems, by contrast, have no intrinsic priors about what they want the world to be. They are extraordinarily powerful at executing on a prior once supplied, but the prior itself — the intent — must come from outside the model. This is why Sathe's bottleneck and Friston's framework converge on the same point: what remains scarce, and stubbornly biological, is the capacity to generate a stable, motivationally loaded model of a preferred future and hold it long enough to act. Everything downstream of that — the scribal labor, the printing press, the HTTP spec, the generative model — is infrastructure for carrying the prior into the world. The infrastructure keeps getting cheaper and more powerful. The prior still has to come from somewhere.

 

The Refusal to Dehumanize - Rewilding Creativity

.. 

I find it impossible to keep up with the prolific output stream of Indy Johar on Substack, but two recent posts (The Refusal to Dehumanize and Rewilding Creativity) have caught my eye, and are a fascinating read.  I recommend reading them in full. To assist readers wanting a quicker fix I reviewed renderings of the main ideas into a single post by four LLMs (ChatGPT, Claude, Gemini, and DeepSeek) and have chosen ChatGPT's effort to pass on:

We are entering a period in which two seemingly distinct developments—renewed permission to dehumanize and the automation of creativity—are in fact expressions of the same underlying shift. Both arise from a deeper logic that reduces life, mind, and expression into forms that can be processed, optimized, and instrumentalized. What is at stake is not simply ethics or technology, but the conditions under which we recognize life itself.

The first threshold is ethical. Dehumanization is no longer marginal; it is being re-legitimized as a mode of reasoning. Under pressure, systems increasingly treat life as substrate—divisible, calculable, expendable. Violence no longer requires hatred; it becomes administrative, logistical, even efficient. Once beings are reduced to units within models or variables within systems, harm can be justified without moral friction. The danger is not only in explicit acts of violence, but in the normalization of frameworks that require the thinning out of life in order to function. At that point, ethics is not violated—it is bypassed.

This same reduction operates, more quietly, in the domain of creativity. What is currently being automated by machine systems is not creativity in its fullest sense, but a historically specific version shaped by industrial society. Creativity has long been formatted into outputs—legible, repeatable, and exchangeable forms of expression. It has been disciplined into patterns that can be trained, measured, and circulated. Machine learning systems are now absorbing this standardized residue. The unsettling realization is that we have not simply built machines that imitate us; we have already shaped ourselves into forms that can be imitated.

Seen together, these developments point to a common structure: the conversion of life and mind into computable domains. Whether in governance, conflict, or cultural production, the same logic applies—reduce complexity, extract patterns, optimize outcomes. The result is a world that increasingly operates through abstraction while losing the capacity to recognize irreducibility. Human life becomes one instance within a broader field of utility. Creativity becomes one more form of production.

The appropriate response is not defensive—neither a defense of existing political frameworks nor a defense of conventional creativity. Both are already compromised by the conditions that made them reducible. What is required instead is a dual refusal and reconstruction.

First, a refusal of any system that depends on the reduction of life as a precursor to action. This is not a moral preference but a structural boundary: once life is treated as substrate, the systems built on that premise cannot sustain themselves without reproducing harm. To preserve the irreducibility of human life is not exclusionary; it is the condition for any meaningful extension of ethical concern beyond the human.

Second, a rethinking—more precisely, a “rewilding”—of creativity and cognition. This means moving beyond forms of thought and expression organized around output, recognition, and exchange. It implies recovering modes of engagement that are not immediately legible or commodifiable: forms of knowing grounded in embodiment, relation, and transformation rather than production. Such creativity may produce fewer artifacts and more shifts in perception, fewer outputs and more reconfigurations of experience.

This creates a practical difficulty. We are attempting to imagine alternatives from within systems that have trained our perception. The very categories we rely on—creativity, intelligence, value—may be inadequate to what is emerging. The task, then, is not simply to generate new outputs, but to unlearn the constraints that made our cognition and ethics machinable in the first place.

The convergence of these two arguments leads to a single question: can we sustain a commitment to life—its irreducibility, its depth, its resistance to abstraction—under conditions that reward its reduction? If not, then both our ethical systems and our creative capacities will continue to collapse into the same underlying logic of optimization and erasure.

If so, the task is clear. Refuse the reduction of life. Reopen the human as a site of emergence rather than function. And begin building systems—ethical, social, and cognitive—that do not depend on turning living processes into manageable substrate.

The Physiology of Agency in the Age of AI

There is a question lurking beneath the current wave of enthusiasm about artificial intelligence that I think deserves more serious attention than it has received. It is not the familiar worry about job displacement or misinformation or even the alignment problem. It is a more intimate question: What happens to our bodies when the feeling of being the author of our own actions begins to erode?

I have been exploring this question in correspondence with a European reader who follows MindBlog, and his observations have sharpened my thinking considerably. He describes using AI across a wide range of activities — coding, financial analysis, translation, even composing personal emails — and notes that the AI is superior in every domain. His metaphor is a child sitting in the driver's seat of a car, holding the steering wheel and feeling the pleasure of apparent control, while the real mechanics of the vehicle remain entirely beyond reach. What strikes him most is the trajectory: unlike a child who grows up to become a competent driver, our competence relative to AI systems may be on a permanently regressive arc even as our felt sense of power temporarily expands.

I find the metaphor evocative, though my own phenomenology has been somewhat different. Working with Claude Code in the terminal on my Mac Mini, watching lines of code execute faster than I can read them, issuing instructions by voice into a system whose underlying machinery I only dimly understand — I feel less a sense of omnipotence and more a sense of being in the presence of a superior intelligence, with less agency than I previously imagined. It is, as Agüera y Arcas puts it, machines all the way down. My own sense of self is a thin terminal interface over another kind of machinery entirely.

But here is what I think gets missed in most discussions of AI and agency, and where the neuroscience becomes directly relevant. The feeling of agency — conscious will, the sense that an action is genuinely one's own — is not primarily a philosophical matter. It is an evolved emotion, as real and as physiologically consequential as fear, anger, or grief. Daniel Wegner's 2002 book The Illusion of Conscious Will argued compellingly that conscious will is itself a kind of experienced emotion, arising when we perceive our own thought as the cause of our action. It is an emotion shaped by natural selection because organisms that experienced themselves as effective agents in the world — that felt the causal connection between intention and outcome — were better at sustaining the motivational and physiological states necessary for survival.

Martin Seligman's classic experiments on learned helplessness established the other side of this coin with uncomfortable clarity. Animals and humans who experience repeated situations in which their actions have no effect on outcomes do not simply become philosophically uncertain about free will. They become physiologically debilitated. Autonomic dysregulation, immune suppression, motivational collapse — the body reads helplessness as a survival threat and responds accordingly. The feeling of agency, even when it is in some sense illusory, is load-bearing for the whole architecture of healthy physiological self-regulation.

This is why I think my correspondent's observation about "externalization of self-regulation" — when AI begins to carry parts of reflection, emotional modulation, and decision pre-structuring — deserves to be taken seriously as a public health question, not just a philosophical one. If significant numbers of people begin to experience their own actions as no longer fully their own, as outputs of a human-machine loop in which they are more passenger than driver, the physiological consequences could be real and measurable. We identified the toxic effects of social media on adolescent mental health only after the damage was widespread. The agency question with AI may operate on a similar lag.

The more hopeful framing, which I also want to take seriously, is that the emotion of agency can be sustained — and even enhanced — when AI is experienced as an extension of the self rather than a replacement for it. I have felt this at moments: initiating a collaboration, shaping its direction, receiving a result that exceeded what I could have produced alone, and feeling something like Harari's Homo Deus — expanded rather than diminished. The slide rule gave way to the hand calculator, and I felt more capable, not less. Each tool adoption, when the human remains genuinely in the initiating role, can strengthen rather than erode the felt sense of authorship.

The critical variable, I suspect, is not which AI tools we use but how we frame and inhabit the collaboration. A person who experiences themselves as initiating, directing, and ultimately judging the outputs of an AI system will likely maintain a robust emotion of agency. A person who experiences themselves as ratifying suggestions, outsourcing reflection, and choosing among options pre-structured by the system may not. The physiological stakes are high enough that this distinction — between being at the helm versus being more deeply in the loop — seems worth cultivating deliberately, both individually and in the design of AI systems themselves.

My correspondent ended our exchange with a thought I find both unsettling and worth sitting with: perhaps what looks like the erosion of the agentic self is actually adaptation — the emergence of a more networked, process-embedded self better suited to highly organized technological environments. If so, the question is whether the ancient physiological systems that evolved to regulate a bounded, sovereign agent can retune themselves for that new niche, or whether they are simply too slow. That is, in the end, an empirical question. And it is one I think we should be asking urgently.

 

[Note on the generation of this post...The email exchange with a European reader mentioned in the above text was submitted to ChatGPT, Claude, Gemini, and DeepSeek, asking each to sort out and clarify the ideas in our conversation and then generate an appropriate MindBlog post describing them. I curated, edited, combined what I thought were the best passages to end up with the above text, which is mainly Anthropic Claude's version.]

 

AI, Agency, and the Quiet Hollowing of Mind

Reading through the article "A Rational Optimist View Of Preventing Agency Decay" is a rich experience. For readers with less patience, here is a ChatGPT summary (that also generated the title of this post). 

Much current discussion of artificial intelligence swings between two poles: utopian efficiency and apocalyptic takeover. The more consequential reality lies between these extremes. The emerging risk is not that machines suddenly replace us, but that we gradually hand over pieces of our cognitive life—judgment, initiative, authorship—without noticing the cumulative effect.

The argument in Colin Lewis’s recent essay is straightforward: AI’s primary impact is not abrupt displacement but cognitive offloading. Tasks once requiring human attention and judgment are incrementally transferred to machine systems. This process is economically rational and often highly productive. In one example, an audit process that once required weeks can now be completed in an hour with AI assistance. But such gains come with a hidden shift: the human role is no longer defined by doing the work, but by nominally overseeing it.

This leads to what the author calls agency decay. The issue is not simply job loss, but the erosion of meaningful participation before any job disappears. First, the human is assisted. Then the human supervises. Eventually, the human remains as a formal point of accountability while the substantive reasoning has migrated elsewhere. The signature is human; the cognition is not.

This shift has broader systemic implications. Modern institutions—markets, governments, cultural systems—have historically depended on human participation. That dependence has acted as a constraint, keeping systems at least partially aligned with human interests. If AI reduces the need for human cognition across many domains, that alignment weakens. The system no longer needs us in the same way, and therefore has fewer built-in reasons to serve human flourishing.

Importantly, this is not a sudden rupture but a slow transition—the “boiling frog” scenario. Productivity gains accumulate incrementally. Each step is locally rational, even beneficial. Yet taken together, they shift the locus of intelligence away from human minds toward institutional and computational systems. What disappears is not competence, but ownership of judgment.

Against this, Lewis offers a restrained form of optimism. The key claim is that human agency need not be defended as a sentimental relic. It can be justified on functional grounds. In high-stakes domains, retained human judgment is not inefficiency; it is infrastructure: a source of error correction, adaptability, and accountability. Systems that eliminate it entirely may become brittle, opaque, and ultimately less reliable.

This reframes the problem. The issue is not whether AI should increase productivity—it will—but whether our metrics of success are too narrow. Efficiency measures speed, scale, and cost reduction. It does not capture qualities like judgment, contestability, or moral responsibility. If institutions begin to price these properly—through regulation, professional standards, and organizational design—human agency can remain structurally embedded rather than nostalgically preserved.

The deeper point is that AI forces a clarification: what is human agency for? If thinking, deciding, and creating are increasingly shared with machines, then the value of human cognition must be specified more precisely. Not all tasks need to remain human. But some forms of judgment—especially those involving uncertainty, accountability, and meaning—may be indispensable.

The optimistic scenario is not one in which technological progress slows, nor one in which markets abandon efficiency. It is one in which societies become capable of distinguishing between mere acceleration and genuine capability. That requires expanding our evaluative frameworks beyond productivity alone.

In that sense, AI does not simply threaten agency; it exposes how poorly we have defined it. The challenge is not to resist automation, but to decide, with greater clarity than before, where human judgment is essential—and to design systems that preserve it there.

---

 

A seismic shift in our understanding of intelligence

I've just spent the last three days reading large chunks of the remarkable book "What is Intelligence" by Agüera y Arcas. It is best accessed at https://whatisintelligence.antikythera.org/, where you will find text with supporting graphics, charts, and animations.  Arcas argues that computation is the substrate for intelligence in all life forms and that prediction is the fundamental principle behind intelligence.  Goodall provides a good review of the book and Arcas's ideas. The introduction to the book encapsulates his basic ideas, and I pass on here ChatGPT's condensation of its main points: 

******** 

Agüera y Arcas’s introduction contrasts two broad frameworks for thinking about intelligence: an older, classical view of AI and a newer emerging perspective shaped by large language models.

The older view of intelligence and AI.
For decades, most scientists assumed that real intelligence required specialized internal mechanisms—explicit reasoning modules, symbolic logic, or carefully engineered algorithms. Machine learning systems that emerged in the late 20th and early 21st centuries were therefore seen as narrow tools rather than genuine intelligence. They performed tasks such as image recognition or sentiment analysis by approximating mathematical functions that map inputs to outputs. This approach produced impressive “Artificial Narrow Intelligence,” but it seemed fundamentally limited. Predicting the next word in a sentence, for example, appeared trivial—essentially a statistical task. Most researchers believed that such prediction models could never produce general intelligence because true intelligence was thought to require additional structures for reasoning, understanding concepts, planning, or possessing common sense.

The unexpected shift.
The emergence of large neural language models challenged this assumption. When trained on enormous text corpora, systems built for the simple task of next-word prediction began displaying abilities that look strikingly general: answering questions, solving problems, performing professional exams, writing code, and carrying on conversations. The key insight is that language prediction implicitly contains a huge range of cognitive demands. Correctly predicting the next word in many contexts requires background knowledge, reasoning, mathematics, commonsense understanding, and even “theory of mind.” What initially appeared to be a narrow statistical task turns out to embed many of the competencies traditionally associated with intelligence.

The debate about what this means.
This development has triggered a conceptual divide. One camp argues that these systems merely simulate intelligence; they generate convincing language without real understanding. The other camp suggests that this distinction may be misguided. If a system consistently behaves intelligently under questioning—passing tests of knowledge, reasoning, and conversation—then insisting that it is “only imitation” may move the discussion outside empirical science. This echoes Alan Turing’s argument that intelligence should be judged by functional behavior rather than by speculation about hidden inner states.

A broader functional perspective on intelligence.
Agüera y Arcas ultimately pushes toward a functional view similar to how biology understands organs. A kidney is defined not by the specific atoms composing it but by what it does. An artificial kidney that performs the same function is still a kidney. Likewise, intelligence may not depend on a particular biological substrate. If a system reliably performs the functions associated with intelligence—reasoning, conversation, problem solving—then from a scientific standpoint it may already qualify as intelligent.

The conceptual shift.
The old model treated intelligence as a special internal mechanism that machines would someday need to replicate. The emerging view treats intelligence as a set of capabilities that can arise from large systems optimized for prediction and interaction with the world. In this perspective, language prediction is not a trivial task but a gateway problem that implicitly contains much of what we mean by cognition. The surprising success of large language models therefore suggests that intelligence may be less mysterious—and more computationally emergent—than previously believed.

 

The geometries of change and the value of being human

I pass on and also archive for myself the following three ChatGPT 5.2 summaries of three recent Johar essays:

Summary of The Geometries of Change by Indy Johar

Core premise
Johar argues that every system of organisation—institutions, economies, governance—rests on an underlying “geometry,” meaning a structural logic that determines how change can occur, what is adjustable, and when transformation becomes disruptive rather than gradual. Geometry defines governability: what can evolve smoothly versus what requires rupture.

Linear geometry and its limits
Modern institutions are built around a linear model of change:

• A direction or goal is fixed first.

• Structures (roles, rules, incentives, infrastructure) are then aligned to that direction.

• Ongoing governance focuses mainly on speed and efficiency rather than revising direction.

Over time, this produces heavy path dependence. Investments, regulations, identities, and incentives lock systems onto a trajectory, making course correction costly and rare. When change finally occurs, it often comes through crisis, collapse, or replacement rather than continuous adaptation. Linear systems work in stable environments but become brittle under uncertainty and complexity.

The problem of contemporary conditions
Johar contends that the assumptions supporting linear organising—predictable futures, centralized authority, singular legitimacy—no longer hold. Today’s environment is marked by plural values, deep uncertainty, and systemic risks. Under these conditions, linear models accumulate commitments faster than they build adaptive capacity, narrowing the range of viable futures.

Helical geometry as an alternative
The essay proposes a “helical” model of change—spiraling through time rather than progressing in a straight line. In this geometry:

• Direction is not permanently fixed; it can be periodically re-negotiated.

• Institutional structures remain adjustable rather than locked to one trajectory.

• Change occurs through iterative cycles that preserve continuity while enabling reorientation.

The aim is to keep the future reachable: systems must allow for turning, not just acceleration. Helical organising supports learning, plural legitimacy, and ongoing adaptation instead of forcing transformation to occur through rupture.

Overall argument
Johar’s central claim is that the key question is not simply what actions to take, but what geometry of organising makes adaptive transformation possible. Linear models prioritize efficiency and stability but generate fragility in volatile contexts. A helical geometry—cyclical, revisable, and temporally layered—offers a framework for steering collective systems amid uncertainty without requiring breakdown as the mechanism of change.

***************** 

Here is a structured summary of “The Future of Being Human, Quietly Being Defined?” (Indy Johar, February 22 2026) based on the full essay:

1. Trigger and framing
The essay begins with a reference to Sam Altman’s remark about how much energy and time it takes to train a human compared with an AI model. Johar says the comment is superficially about energy fairness but structurally shifts the frame toward what counts as the unit of comparison in evaluating humans and machines.

2. Commensurability as a hinge
Johar distinguishes two kinds of “commensurability”:

• Descriptive, which measures energy and inputs across systems;

• Normative, which uses those measurements to justify comparisons and trade-offs.
  Altman’s claim, if read normatively, encourages interpreting humans and AI as functionally comparable capability systems. That framing quietly turns human beings into units of capability production.

3. Reduction of humans to capability outputs
Once humans are legible mainly in terms of cognitive capability as service output, several outcomes follow:

• Humans are considered substitutable if non-human systems can deliver similar outputs.

• Human value is recast in optimization terms: cost, throughput, reliability.

• Institutions begin organizing around procurement and compliance rather than intrinsic human worth.
  Johar calls this capability reductionism: a more refined but still reductive continuation of industrial labour reductionism that flattened humans into units of labour.

4. Compute-centric reference frames
If training becomes the shared frame, computing infrastructure becomes the reference class for intelligence and governance:

• Human education becomes “fine-tuning.”

• Civility and culture are reframed as priors in a cognitive pipeline.
  This shift influences what is measurable, fundable, normative, and thus shapes policies, welfare, schooling, and citizenship around capability output.

5. Structural fork in governance
Johar outlines two divergent models of governance that emerge from this framing:

1. Capability-first governance, where comparability and optimisation are central under constraint;

2. Intrinsic-life governance, where human dignity and irreducibility are first-order, non-tradeable commitments.
   He argues that if capability becomes the default grammar of society, human redundancy can become administratively rational without ever being declared explicitly.

6. Hierarchy of values
The essay proposes a normative ordering: rights first, capability second. Johar says that doesn’t mean rejecting metrics, but keeping them bounded within a framework that protects intrinsic human worth rather than letting efficiency metrics displace rights as constraints.

7. Core concern
The deeper issue isn’t whether training humans takes energy—it’s that if civilisation adopts a grammar defining humans primarily through capability and contribution, then optimising and replacing them becomes a rational endpoint. That is not just a labor-market calculation; it reshapes what it means to be human in governance and valuation systems.

Overall thesis
Johar’s essay warns that the emerging default comparison between humans and machine capabilities is not neutral. It quietly reshapes governance logic, reduces humans to tradable capability vectors, and opens a path where humans become redundant in an optimisation-driven system unless society explicitly protects intrinsic rights and dignity before metrics.

***********************

Here is a structured summary of “The Value of Being Human” by Indy Johar (Feb 22, 2026):

1. Core philosophical choice
Johar identifies a foundational question beneath debates about AI, labour, and productivity: whether we conceive of humans as fixed bundles of capabilities or as open, developmental systems. This ontological framing — closed versus open — determines how value is understood and how institutions and policies are designed.

2. Closed ontology: humans as defined capability sets
In the dominant contemporary frame, humans are treated as collections of measurable functions (reasoning, creativity, coordination, etc.). Once human capacities are specified and benchmarked, comparison with machines becomes straightforward, and substitution decisions appear rational and objective. This reinforces a logic where humans are valued only for defined, quantifiable contributions.

3. Open ontology: humans as evolving trajectories
Johar contrasts this with the idea that humans are not static but evolving. Throughout history, major technological shifts (writing, printing, industrialisation, digital networks) have reshaped human cognition, behaviour, and capacities. Under transformative technologies like AI, future human capacities may emerge in ways that cannot be entirely predicted or pre-specified.

4. Dangers of governance by measurement
Measuring performance is not inherently flawed; the issue arises when measurable metrics become the primary basis for governance, allocation, and institutional incentives. When metrics become targets, systems reorganise around them, and what is measurable becomes what is rewarded. This exerts “selection pressure” that narrows the space of human development to what is legible and comparable.

5. Developmental compression and its risks
Treating humans as static inventories of capability risks “developmental compression,” where alternative developmental trajectories are under-supported or foreclosed entirely. Institutions optimising for present metrics may inadvertently narrow the range of future human capacities and forms of becoming.

6. Value of the unknown
Johar emphasises that unknown future capacities carry structural value. In contexts of deep uncertainty, preserving human developmental possibility (optionality) is a prudential imperative. Static valuation frameworks that assume completeness risk mispricing long-term potential.

7. AI’s role as selection pressure
AI itself does not dictate whether human capacities decline or expand; instead it introduces a selection pressure. Its effect on human development depends on the institutional frameworks in which it is embedded. AI can either amplify human development or compress it into narrow optimisation around measurable tasks.

8. Closed vs. open ontology: institutional implications

• Closed ontology: humans are defined, measurable, and replaceable; institutions orient toward substitution and optimisation.

• Open ontology: humans are emergent and partially unknowable; institutions should prioritise preserving developmental possibility over optimisation.

9. Central question re-framed
The key issue is not whether humans outperform machines at specific tasks, but whether we treat human nature as still emergent and indeterminate. Acceptance of a closed ontology leads logically to substitution and optimisation; acceptance of an open ontology implies designing systems that safeguard the conditions under which new human capacities can emerge in the future.

Summary thesis
Johar’s argument reframes the “value of being human” not in terms of current comparative performance with machines, but in terms of preserving human developmental potential. He warns that collapsing humans into static capability sets for measurement and optimisation risks narrowing the future of human becoming and misvaluing what is uncertain but potentially crucial.