Future-Capable: Curiosity, Adaptability, and Kindness in the Age of AI

I want to pass on the following edited Claude 4.8 reduction of a Colin Lewis article which I recommend you read through in its full form:

Curiosity, Adaptability, and Kindness

No one is future-proof. The better ambition is to become future-capable.

Curiosity is the refusal to let yesterday's competence become today's cage. Adaptability is the dignity to change your methods without losing your soul. Kindness is the choice to remain human when the system offers a thousand reasons to be a machine.

---

The Wrong Job Description

When OpenAI released ChatGPT in November 2022, office workers, students, lawyers, and journalists quietly tried it for work that had once demonstrated professional competence. By early 2025, the World Economic Forum was surveying employers about the skills they would need by 2030. Analytical and creative thinking topped the list, followed by resilience, flexibility, curiosity, and lifelong learning. The list was not sentimental. In the language of payroll, it said the human future at work would depend on habits not easily reduced to a repeatable procedure.

The central error in most AI conversations is that we prioritize intelligence over character. We ask whether a machine can write, reason, diagnose, and persuade—useful questions that push us too quickly into a contest of functions, a humiliating little sport in which the human is invited to race the machine across a field chosen by the machine's owners. The result is predictable: we lose at speed, volume, storage, and cheerful indifference to boredom. A person who tries to defeat AI by becoming a cheaper, slower, more anxious version of AI has already accepted the wrong job description.

The better question is not whether AI can think. It is what kind of person grows in its presence.

---

Curiosity: What Do You Notice?

The worker of the near future will not be asked only, "What do you know?" A machine can supply a first answer, or ten, complete with footnotes and a fake air of calm. The harder question is "What do you notice?"—and that is where curiosity begins. It begins not with the possession of information but with irritation at the insufficiency of the available answer. It is the raised eyebrow in the meeting, the quiet refusal to accept that the dashboard knows the client, that the score knows the applicant, that the model knows the child, that the prediction knows the life.

The International Labour Organization has been careful here: AI does not produce one simple future in which jobs vanish or survive. People do not lose "jobs" in the abstract. They lose tasks, status, entry points, discretion, and sometimes the right to be inexperienced in public.

That last loss may be the most dangerous. AI may not begin by replacing the expert. It may begin by consuming the novice.

A junior analyst once learned by doing poor first drafts. A young lawyer learned by reading too many documents slowly. A young teacher learned by facing a classroom with a plan that did not survive the first ten minutes. These were not inefficiencies; they were the cost of forming judgment. If AI removes all that early clumsiness, it removes the evidence by which a person learns what competence feels like from the inside. The novice does not only need the correct answer—he needs the memory of having been wrong in a recoverable way.

So recovered novice-learning will have to be designed; it will not happen by nostalgia. A firm should still ask junior staff to produce a rough version before the machine is invited in. A law office should let a trainee mark up a contract unaided, then compare. A hospital should teach younger clinicians not merely to read a prediction but to state what would make it wrong. The point is not to ban the tool. The point is to preserve the apprenticeship of attention.

For twenty years, businesses trained employees to suppress curiosity: follow the template, stay in your lane, escalate only through approved channels. Now the same executives announce, with the exhausted surprise of men discovering snow, that curiosity is essential. An institution that spent two decades rewarding obedience cannot summon independent judgment by adding it to a slide.

---

Adaptability Without Formlessness

Adaptability is the second word, and it is often abused. In corporate language it can mean "please absorb the consequences of our poor planning"—relocation without support, retraining without time, resilience offered as a scented candle for institutional failure. I mean something else: the adult capacity to revise one's methods while retaining one's standards.

The distinction is vital. A person without standards changes too easily and becomes fashionable and hollow. A person without adaptability changes too late and becomes principled and unusable. The task is to remain teachable without becoming formless.

AI tempts us into two equally foolish poses: panic and smugness. Panic says everything human is finished; smugness says everything important is safe. Panic flatters the machine, smugness flatters the speaker, and reality is less obliging. In Generative AI at Work, Brynjolfsson, Li, and Raymond found productivity gains of roughly 14 percent from an AI assistant in customer support, with the largest gains among less experienced workers. That is neither the end of the human worker nor a bedtime story. It means the novice may be helped, monitored, accelerated, and compared in the same motion.

Adaptability cannot be a weekend course in prompt engineering. The serious person does not ask only "How do I use this?" but "What does this make easier, what does it make harder, who gains authority, who loses practice, and what should I now learn by hand?"

---

Kindness as Leadership

Kindness is the third word—and it is not niceness. A company using AI in hiring can process more candidates, but it can also reject more people without ever noticing them. Predictive systems can help allocate scarce hospital resources, but they can also let a score acquire the emotional status of fate. Speed is useful, but we have granted it a moral authority it has not earned.

Kindness in the age of AI is disciplined attention to the human consequences of increased power. It slows the hand precisely where the system invites acceleration. It asks for the name, the exception, the appeal, the second look. It does not reject systems; it prevents systems from becoming alibis.

The OECD's work on AI and skills makes clear that adoption is limited not by the existence of technology but by skills, training, and organizational capacity. The future is not delivered as a sealed package by engineers in California or Zurich. It is negotiated in procurement meetings, classrooms, clinics, and family conversations at 9:30 p.m., when someone says, "I do not know whether my job will exist in five years." At that hour, kindness is not a mood. It is leadership.

---

A Working Ethic

I have come to distrust the phrase "future-proof." No one is future-proof—not the coder, not the professor, not the executive with the expensive watch. The better ambition is to become future-capable: able to learn without humiliation, change without panic, and succeed without becoming cruel.

This is why the three words belong together. Curiosity without kindness becomes predatory. Adaptability without curiosity becomes mere obedience. Kindness without adaptability becomes helpless sympathy. Together they form a working ethic for a time in which competence is being unbundled and sold back to us as software.

There is a fatigue peculiar to this moment—the fatigue of permanent adjustment. New tool, new update, new warning, new acronym, new panic, new invoice. The future now arrives with release notes; even the apocalypse, one suspects, would ask us to accept cookies. And yet despair is not justified. Despair is often vanity in dark clothing: it assumes we know enough to give up. We do not. We know people grow under pressure when they are not abandoned to it, that they adapt when they can retain dignity, that they become kinder when kindness is not treated as weakness by the ambitious.

So let us stop speaking of human beings as obsolete components. A person is not a legacy device. A person is a learner, a judge, a witness, and a keeper of obligations—which is a plain description of what institutions require when anything goes wrong. When the system fails, no one asks to speak to the workflow. They ask for a person.

The work ahead is not to become less human in order to survive intelligent machines. It is to become more deliberately human, with higher standards for attention and deeper obligations to one another. The machine can answer. The person must ask why the answer is being sought, who will use it, who may be harmed by it, and whether a faster answer has made us better or merely quicker.

On a good morning, this future does not look like surrender. It looks like a meeting after the first difficult question has been asked. Someone has stopped pretending to understand. Someone else has admitted uncertainty. A third person has opened a notebook. The room is quieter than before, but not defeated. Work has begun.

-------------- 

[The above is a re-posting of the post of Monday, June 22, 2026]

 

Slow breathing modulates brain function and risk behavior

Some interesting observations reported in Neuron by Huang et al.:

Highlights

• Prolonged exhalation increases risky decisions by increasing reward sensitivity

 

• Prolonged exhalation increases parasympathetic but not sympathetic activity

 

•Greater parasympathetic activity predicts reward sensitivity in the vmPFC and precuneus

Summary

Successful decision-making requires that external information be interpreted in the context of the body’s state. Within the framework of body-brain interaction, deliberately modifying one’s autonomic state can shape how we evaluate the world, ultimately influencing choices. Yet, it remains unclear whether and how intentional autonomic regulation affects human decision-making. In this study, we tested instructed use of prolonged exhalation, a slow-breathing technique designed to boost parasympathetic activity during risky decision-making. Participants followed distinct breathing protocols while making risky choices, with neural and physiological activity measured using functional magnetic resonance imaging (fMRI) and multichannel monitoring. Prolonged exhalation increased risky choices by enhancing reward sensitivity and elevating cardiac parasympathetic activity. Importantly, individuals with greater parasympathetic upregulation also showed stronger reward-related responses in the ventromedial prefrontal cortex and precuneus. Our work reveals the transformative role of breathing-based interventions, demonstrating that autonomic regulation via breathing can shape value-based decision-making through neuro-cardiac pathways.

 

The agentic self: The brain learns whether action matters before deciding what to learn

A study by Liu et al. (open access article with interesting graphics) decomposes our “agency” into at least two computations: estimating whether one is in control, and using that estimate to determine which consequences should be attributed to one's actions. This has obvious relevance to learned helplessness, depression and the construction of an agentive self. Their central claim is that Humans learn whether outcomes depend on their actions through a dorsomedial prefrontal–dorsal raphe circuit. Once estimated, controllability alters learning signals in dopamine-related midbrain structures and a separate prefrontal credit-assignment system. A few caveats are that TMS cannot selectively perturb the entire proposed dmPFC–raphe pathway, and fMRI of small brainstem nuclei is technically demanding. Laboratory controllability is simpler than the ambiguous causal structures of ordinary life. Here is their summary:

When humans and other animals assess that they have little control over outcomes, their motivation and capacity for learning change. However, how we first learn what the control level is and how it then influenceslearning remain unclear. Using functional magnetic resonance imaging (fMRI) and transcranial magneticstimulation (TMS) in human participants, we provide both recording and transient disruption evidence for an anatomically grounded model of control learning, in which dorsomedialprefrontal cortex (dmPFC) tracks confidence in each individual decision in order to then estimate controllability and changes in controllability via interactions with the dorsal raphe nucleus. Disrupting activity in this circuit, via dmPFC manipulation,impaired control learning. In addition, another mechanism was identified through which control estimates influenced learning. Participants’ estimates of controllability were associated with widespread changes in outcome signals, including in dopamine-associated midbrain nuclei and in credit-assignment-linked signals in a distinct prefrontal cortex subregion. 

 

Regulating our subjective well being - our brain's axes of arousal, valence, and agency

I've read several times through a daunting review article by Feldman et al.  in the July issue of Trends in Cognitive Science  titled "The Neurobiology of Interoception and Affect."  (motivated readers can obtain a copy of the whole article from me). The bottom line is that the subjective feelings of what is going on inside our bodies -  that taken together form our sense of well being -  rise from a an array of cortical and visceral neuroendocrine systems that are much more complex that the nerve pathways regulating our exteroception, the sensing of external signals such as sound, light, or touch.  I would recommend reading the article to get a sense of the array of players that include upper and lower cortical regions, spinal cord, the autonomic nervous system, the enteric nervous system, etc.

We can describe our feelings, our affect, along two fundamental axes, valence and arousal. Valence refers to whether something is pleasant or unpleasant,  desirable or dangerous -  do we go for it or scram?  Arousal refers to where are we on the spectrum of being calm to being excited or distressed.  A third fundamental axis is formed by our experience of agency, how powerful versus helpless we feel in a given situation.  

In this post I want to pass on a rich graphic from the article showing how we can categorize  our feelings  in language with respect to these fundamental axes.  It is based on Saif M. Mohammad's computational linguistics studies that have obtained reliable human ratings of valence, arousal, and dominance for 20,000 English words. The graphic gives us a  description of central regulators of our well being to which 2 we have subjective (interoceptive) access. (You should be able to click on this and the following images to enlarge them.)  I have found that referencing my own subjective feelings to these axes has helped me to be more aware of them and assisted in their regulation.  

 
 

If the above looks complicated, it gets even worse. There really should be a 3-dimensional rather than 2-dimensional plot (see graphic below). The further axis of regulation used by Mohammad in generating data for the above figure is our subjective experience of dominance or agency in a given situation (where are we on a gradient of helpless to powerful?)  Here is a clip from the Saif M. Mohammad reference link shown above with some definitions:

As a footnote or addendum, I will also repeat here a more simple graphic showing these axes that I have used in my lectures, taken from the work of Lisa Feldman Barrett,  (enter 'Barrett' in the search box in left column of this page to find MindBlog posts describing her studies on understanding what feelings and emotions are).

 

3

 

(this is a repost of MindBlog's  8/28/24 post)

Categorization is ‘baked’ into the brain

I've been meaning to point out this Nature Reviews Neuroscience Perspectives article by Barrett and Miller (the same Miller referenced in the previous post).  I pass on just the abstract and initial paragraphs of their model. The article has some very striking graphics, and motivated readers can request a copy of the article from me.  (It is important to point out that the choice of the limbic core as the analytic starting point is somewhat arbitrary, rather than being derived from basic data itself.)

Abstract

Categorization, the grouping of objects, living organisms, actions or events into equivalence clusters, is fundamental to adaptive behaviour. Traditionally, it is assumed that categorization begins with feature detection and ends with assigning representations stored in memory. Here we review converging evidence from neuroanatomy, electrophysiology, brain imaging and cognitive science to suggest an alternative view: categorization is not the end stage of perception but occurs throughout signal processing, from the very beginning. It is a core computational strategy of the brain, implemented through a neural context created by predictive feedback signals that organize feedforward processing. 

Introduction

A category is a group of objects, living organisms, actions or events that are similar enough to be treated as equivalent for some purpose or function. Categorization, the process of treating something as equivalent to something else, is fundamental to life. The ability to determine ‘this is like that’ allows animals to draw on past experiences to guide present actions. All animals categorize, generalizing from past experiences at temporal and spatial scales relevant to their biology and ecological niche. Categorization reduces metabolic costs by minimizing uncertainty in a constantly changing, partially predictable world.

In this Perspective, we discuss the possibility that categorization is not the pinnacle of brain processing, as is traditionally assumed. Instead, categorization is a fundamental operating principle that describes the functional consequences of signal processing throughout the brain. We integrate evidence from neuroanatomy, electrophysiology, brain imaging and cognitive science to suggest that category construction begins as patterns of predictive feedback signals for abstract motor plans. Feedback signals create a neural context that actively shapes the processing of feedforward sensory signals, organizing the reduction of their dimensionality to serve situated, functional goals. In this view, the brain categorizes sensory signals from the outset, rather than as a final-stage process following sensation, attention and perception.

We begin with a review of the main cytoarchitectural gradient that reduces the dimensionality of feedforward sensory inputs to the cerebral cortex. We then discuss the seemingly counterintuitive idea that reverse signal flow along this gradient expands dimensionality to generate prediction signals that shape the processing of and ultimately categorize those inputs to give them meaning. This universal continuous category construction starts at the limbic core of the brain, in areas that are at the core of the brain’s regulation of the body, and supports metabolic efficiency by anticipating and preparing for energy needs before they arise, a condition known as allostasis. In this way, continuous category construction and the resulting categorization satisfy a key biological constraint, energy optimization, which is an organizing principle of life and evolution

Analog cognition and consciousness

Miller et al.   suggest that brain synapses store representations while large-scale rhythmic electric fields dynamically select, route and combine them. Traveling alpha and beta waves could act as movable “stencils” controlling faster gamma activity, permitting parallel analog computation; unified consciousness would arise when such wave organization becomes sufficiently cortex-wide and integrated. They propose an "analog" computational layer on top of digital-style spikes. Waves would be organizing top-down control, flexibly route signals between neural populations, and let individual neurons take on different functional roles depending on context — the coordination problem that discrete spiking alone struggles to explain. I pass on their abstract and concluding comments (motivated readers can obtain a PDF of the article from me.)

Abstract:

Cognition and consciousness may arise from bidirectional interactions between neuronal spiking and rhythmic electric field activity (brain waves). Goal-directed behavior relies on top-down control to coordinate large neural populations into low-dimensional, task-oriented dynamics. Brain waves are well suited for this role, exerting mesoscale influence over neural excitability. They can also support analog computation, shaping activity patterns according to underlying computational principles. Brain waves can flexibly route and organize neural signals, enabling multifunctional neurons to assume context-dependent roles, a hallmark of cognition. In this view, goal-directed thought, action, and unified consciousness emerge from cortex-wide wave dynamics that both reflect and transform spiking into coherent brain states.

Concluding comments: 

Our theory shares with others the general idea that cognition and consciousness involve mesoscale coordination and thus top-down control across the brain. But instead of describing function mainly in terms of information exchange between discrete neurons, circuits, and regions, we emphasize brain-wide wave dynamics as an organizing principle.

In this view, rhythmic electric fields help unify and structure cortical activity, allowing analog computation to take place across space and time. These wave interactions not only bind distributed neural populations into coherent states but also carry out computations that support flexible thought and control. Consciousness, then, emerges when these dynamic wave patterns bring the cortex into an organized, globally integrated state, one that naturally links and influences widespread activity.

This theory is not only conceptually plausible but biologically feasible. Cortical circuits naturally generate oscillatory dynamics and propagate waves through recurrent connectivity and horizontal cortical connections across multiple scales. The dynamics we emphasize thus require no special machinery. These waves are energetically efficient, leveraging continuous field interactions rather than metabolically costly, all-or-none spiking at every step. In this sense, the brain exploits its own physics: Electric field dynamics offer a low-overhead substrate for organizing and coordinating information across cortical networks. Given strong evolutionary pressure to maximize computation per unit energy, it would be surprising if evolution did not exploit such a built-in analog computing substrate.