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.

 

The Counterintuitive Need to Slow Down and Find Spaciousness

I pass on the following edited clips from ChatGPT and Claude condensations of a conversation between Nate Hagens and Iain McGilchrist.  While I think McGilchrist's left-hemisphere/right hemisphere distinctions are a bit simplistic, the take home messages are appropriate regardless of the particular brain activity correlates that are invoked: 

In episode 217 of Nate Hagens's The Great Simplification, Hagens is rejoined by philosopher and neuroscientist Iain McGilchrist — best known for The Master and His Emissary and The Matter With Things — for a wide-ranging conversation about what our current moment of civilizational crisis actually demands of us. The counterintuitive answer is not more urgency, not more optimization, but a deliberate slowing down and an opening toward spaciousness, silence, and wonder. The conversation begins from Hagens’ familiar “metacrisis” frame — ecological, economic, social, and psychological instabilities as interlocking expressions of a deeper human predicament —  McGilchrist’s contribution is to shift the diagnosis inward, toward the style of attention that modern culture rewards.

Left-brain dominance and the obscuring of value

McGilchrist's central argument, developed across his major books, is that Western culture has become increasingly dominated by left-hemisphere modes of cognition — narrow, focused, categorical, explicit, and oriented toward control and manipulation. The right hemisphere, by contrast, attends to the whole, holds ambiguity, and remains open to what is living, relational, and interconnected. The trouble is not that we have a left hemisphere but that it has progressively usurped the role of the right as the governing perspective. This imbalance, McGilchrist argues, is not just a psychological curiosity: it is what underlies our collective inability to perceive and act on what truly matters — truth, goodness, and beauty. When the left hemisphere runs the show, these qualities become invisible, and what fills the vacuum is power, productivity, and the measurable.

Attention as the root of value

A thread running through the conversation is that attention is not neutral: what we attend to shapes what we value, and what we value shapes what we attend to. McGilchrist draws on the research insight that roughly 99% of brain activity is unconscious, which means that most of what guides our perception and behavior lies beneath deliberate awareness. The gorilla-in-the-room studies on inattentional blindness illustrate this starkly: we routinely fail to see what is right in front of us when our attention is narrowly locked. Applied to the metacrisis — the overlapping civilizational, ecological, and psychological crises of our era — this suggests that the problem is not primarily one of missing information or insufficient analysis. It is a crisis of attention itself. We are not seeing what matters because we have trained ourselves not to look.

The practice of spaciousness

The remedy McGilchrist proposes is not a political program or a technological fix. It is a shift in how we inhabit time. He urges listeners to resist what he calls the "mania for productivity" embedded in modern culture, and instead to cultivate spaciousness: pauses, silence, deep listening, and what Buddhism calls śūnyatā — emptiness not as absence but as fertile, generative openness. He cites Rabbi Abraham Joshua Heschel's writing on the Sabbath as a model: the ancient practice of building non-doing into the structure of the week was not a concession to weakness but a recognition that renewal and wisdom require fallow time. McGilchrist also points to the psychology of creativity research showing that insight characteristically emerges not during focused effort but in the hypnagogic spaces between — in showers, on walks, at the threshold of sleep.

Consciousness, panpsychism, and the thread connecting everything

The conversation moves into deeper philosophical territory when Hagens and McGilchrist explore what might underlie the universe's apparent orientation toward complexity, beauty, and relation. McGilchrist is sympathetic to panpsychism and panentheism — the view that some form of experience or proto-consciousness pervades reality, and that the universe is not a collection of inert objects but a relational, creative process. He draws on Whitehead's process philosophy, Bohm's implicate order, and Schelling's image of the self as a whirlpool — a temporary pattern that arises from and returns to a larger flow. Death, in this frame, is not mere termination but a kind of completion, and the obsession with indefinite life extension through technology reflects the left hemisphere's refusal to accept its own finitude.

A small percentage can shift the whole

McGilchrist closes with a message that is both modest and radical: he does not expect — or require — a majority conversion. Even a small percentage of people genuinely living differently, embodying humility, compassion, awe, and wonder, could begin to shift what he calls "cultural consciousness." This resonates with complexity theory's sensitivity to initial conditions and with the sociological literature on tipping points. The implication is that the most consequential thing an individual can do in a moment of civilizational turbulence may not be to do more, advocate louder, or optimize harder — but to slow down enough to actually see, and to live from that seeing.

For those already drawn to predictive processing frameworks: McGilchrist's account of hemispheric asymmetry maps interestingly onto the distinction between top-down, precision-weighted prediction (left-dominant) and the kind of open, receptive prior-updating that Friston's active inference would associate with high-entropy, exploratory sampling of the world. The right hemisphere, on this reading, is the brain's better Bayesian — the one willing to be surprised.

YouTube link to the full conversation

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.