Friday, August 11, 2023

The immaturity of America's therapeutic culture

I  recommend reading the most recent NYTimes David Brook's piece, and pass on here ChatGPT 4's response to my request to summarize the main  its 1,472 words. It produced the following  339 words which nicely cover Brook's core points.  I think I will start using ChatGPT 4 more frequently for this purpose since  I've only recently realized that MindBlog readers who do not subscribe to the NYTimes can not read articles that I point to.  Also, I simply don't have the time to generate summaries myself, because I want to be working on other things.  

Summary of the Essay on the American Therapeutic Culture and Maturity: 

The decline of the American psyche can be linked to cultural shifts that started after World War II, leading to the rise of the therapeutic culture.

Historically, self-worth was derived from one's relationship with God or success in the marketplace. In the therapeutic culture, self-worth is gauged by subjective feelings about oneself.

This culture turned many into fragile narcissists, detached from moral traditions and relying heavily on public affirmation for self-worth.

By 2010, the US faced a mental health crisis, marked by rising rates of depression and suicide. Social media became a platform for seeking validation but often resulted in rejection.

The term “trauma” began to encompass a wider range of upsetting experiences, moving from severe physical harm to milder psychological wounds. Trauma became a dominant theme in culture, with many using it as a primary source of identity.

Safetyism emerged, advocating for protections against emotional harm. This led to concepts like “trigger warnings,” “microaggressions,” and “safe spaces.” 

The approach to trauma became counterproductive, with certain false ideas propagated, such as "what doesn't kill you makes you weaker" and the portrayal of traumatized individuals as passive victims.

An opposing perspective, led by figures like Jordan Peterson, argued for resilience and not viewing oneself as a perpetual victim. Yet, these figures too sometimes portrayed themselves as victims in a different context.

This societal focus on victimhood has led to a public culture that is impulsive and erratic. The loudest voices often dominate discussions, sidelining mature discourse.

The core issue is the therapeutic ethos itself, which disconnects people from a broader moral order and asks individuals to create an identity solely from within. 

True maturity is not self-centered but involves weaving an identity from commitments and relationships with others. It's about seeing situations from multiple perspectives and committing to concrete moral goals.

Maturity allows individuals to be calm and understanding in challenging situations, and this might be the answer to building a more resilient and connected culture in the future.

Wednesday, August 09, 2023

What is intelligence?

I want to share a message sent by Clint Sprott to the Chaos and Complexity seminar group at the University of Wisconsin which he started many years ago - it is currently engaged in a discussion of intelligence:

I asked ChatGPT to define intelligence and whether it is intelligent:

User
How would you define intelligence?
ChatGPT

Defining intelligence is a complex and multifaceted task, as it encompasses a wide range of abilities and capacities exhibited by living organisms and artificial systems. Intelligence can be broadly described as the ability to acquire and apply knowledge, learn from experiences, reason, solve problems, adapt to new situations, and exhibit complex cognitive functions.

Intelligence is not limited to a single dimension but rather exists along a spectrum, manifesting in various forms and levels across different species and individuals. It includes both cognitive abilities, such as logical reasoning, memory, language, and spatial awareness, as well as emotional intelligence, social skills, creativity, and adaptability.

It's essential to recognize that intelligence is not solely determined by traditional measures like IQ tests. Intelligence is a dynamic and context-dependent trait that can manifest differently in different environments and cultural contexts. Moreover, intelligence can also be seen in non-biological entities, such as artificial intelligence, where it refers to the ability of machines to perform tasks that typically require human intelligence.

Overall, intelligence is a complex and evolving concept, and our understanding of it continues to evolve as we explore and study the diverse manifestations of intelligence in both living beings and intelligent systems.

User
Are you intelligent?
ChatGPT

As an AI language model, I don't possess consciousness, self-awareness, or subjective experiences, which are crucial components of human intelligence. However, I have been trained on vast amounts of data and have been designed to perform specific tasks, such as understanding and generating human-like text based on the patterns in the data I was trained on.

While AI models like me can process information quickly, analyze patterns, and provide useful responses, it's essential to understand that this is a form of artificial intelligence, and it differs significantly from human intelligence in terms of awareness, emotions, and consciousness.

In essence, I am a tool created by humans to assist with various tasks, but I do not possess genuine intelligence or consciousness as humans do. My responses are based solely on patterns in the data I've been trained on and the algorithms that govern my functioning.
 

Monday, August 07, 2023

America's legacy of poverty - The injustice of place.

Having moved back into the house in which I grew up in Austin Texas, and watching the city inexorably move towards becoming a dystopian metroplex, the analysis of Edin, Schaefer and Nelson makes me feel like returning to the Midwest, where I spent most of my adult life as a professor at the University of Wisconsin in Madison. They paint the most clear and focused explanation for the roots of inequality in America that I have read, concluding that the upper Midwest is the best place to live in America. Here is the concluding paragraph of their piece in the The Atlantic, titled “What the Best Places in America Have in Common.” It is a summary of the message of their new book “The Injustice of Place: Uncovering the legacy of poverty in America.”
The lesson is that people seem to thrive—not always in high salaries but in health and life chances—when inequality is low; when landownership is widespread; when social connection is high; and when corruption and violence are rare. The social leveling that is characteristic of communities in the upper Midwest is more than just a quaint cultural feature. It is the foundation of a community’s well-being. Until these regions’ virtues are shared nationwide, poverty and disadvantage will continue to haunt America.

Friday, August 04, 2023

18-month old humans discriminate moral violations from disobedient or unexpected events

Fascinating studies from Kassecker et al. (open source) have used multiple methods (eye-tracking, observations of expressive behaviors) to probe the developmental origins of human moral cognition by assessing infants’ ability to differentiate between prototypical harmful (moral) and harmless (conventional) violations:
Humans reason and care about ethical issues, such as avoiding unnecessary harm. But what enables us to develop a moral capacity? This question dates back at least to ancient Greece and typically results in the traditional opposition between sentimentalism (the view that morality is mainly driven by socioaffective processes) and rationalism [the view that morality is mainly driven by (socio)cognitive processes or reason]. Here, we used multiple methods (eye-tracking and observations of expressive behaviors) to assess the role of both cognitive and socioaffective processes in infants’ developing morality. We capitalized on the distinction between moral (e.g., harmful) and conventional (e.g., harmless) transgressions to investigate whether 18-mo-old infants understand actions as distinctively moral as opposed to merely disobedient or unexpected. All infants watched the same social scene, but based on prior verbal interactions, an actor’s tearing apart of a picture (an act not intrinsically harmful) with a tool constituted either a conventional (wrong tool), a moral (producing harm), or no violation (correct tool). Infants’ anticipatory looks differentiated between conventional and no violation conditions, suggesting that they processed the verbal interactions and built corresponding expectations. Importantly, infants showed a larger increase in pupil size (physiological arousal), and more expressions indicating empathic concern, in response to a moral than to a conventional violation. Thus, infants differentiated between harmful and harmless transgressions based solely on prior verbal interactions. Together, these convergent findings suggest that human infants’ moral development is fostered by both sociocognitive (inferring harm) and socioaffective processes (empathic concern for others’ welfare).

Wednesday, August 02, 2023

Work as war...and Pritzker's Formulae To Spot An Idiot

Too fascinating pieces on how in the areas of politics and business our more recently evolved primate capabilities for empathy and compassion are being subverted by the more primitive instinctual drives regulating fear and combat. (This post is another example of using MindBlog as an archive of some bonbons I have enjoyed, entering them so that I easily look them up later, and also on the odd chance that a few readers might find them interesting.) 

Work as War. We’re in the Era of the ‘Top Gun’ C.E.O. 

and, 

Pritzker's Formulae To Spot An Idiot 

 

 

Monday, July 31, 2023

The visible gorilla.

A staple of my lectures in the 1990s was showing the ‘invisible gorilla’ video, in which viewers were asked to count the number of times that students with white shirts passed a basket ball. After the start of the game a student in a gorilla costume walks slowly through the group, pauses in the middle to wave and moves off screen to the left. Most viewers who are busy counting the ball passes don’t report seeing the gorilla. Here's the video:

 

Wallish et al. now update this experiment on inattentional blindness in an article titled "The visible gorilla: Unexpected fast—not physically salient—Objects are noticeable." Here are their summaries:  

Significance

Inattentional blindness, the inability to notice unexpected objects if attention is focused on a task, is one of the most striking phenomena in cognitive psychology. It is particularly surprising, in light of the research on attentional capture and motion perception, that human observers suffer from this effect even when the unexpected object is moving. Inattentional blindness is commonly interpreted as an inevitable cognitive deficit—the flip side of task focusing. We show that this interpretation is incomplete, as observers can balance the need to focus on task demands with the need to hedge for unexpected but potentially important objects by redeploying attention in response to fast motion. This finding is consistent with the perspective of a fundamentally competent agent who effectively operates in an uncertain world.
Abstract
It is widely believed that observers can fail to notice clearly visible unattended objects, even if they are moving. Here, we created parametric tasks to test this belief and report the results of three high-powered experiments (total n = 4,493) indicating that this effect is strongly modulated by the speed of the unattended object. Specifically, fast—but not slow—objects are readily noticeable, whether they are attended or not. These results suggest that fast motion serves as a potent exogenous cue that overrides task-focused attention, showing that fast speeds, not long exposure duration or physical salience, strongly diminish inattentional blindness effects.

Friday, July 28, 2023

Unnarratability -The Tower of Babel redux - where have all the common narratives gone?

I pass on some clips from Venkatesh Rao's recent Ribbonfarm Studio posting.. Perspectives like his make me feel that one's most effective self preservation stance might be to assume that we are on the dawn of a new dark age, a period during which only power matters, and community, cooperation, and kindness are diminished - a period like the early middle ages in Europe which did permit under the sheltered circumstances of the church a privileged few to a life of contemplation.    

Strongly Narratable Conditions

The 1985-2015 period, arguably, was strongly narratable, and unsurprisingly witnessed the appearance of many strong global grand narratives. These mostly hewed to the logic of the there-is-no-alternative (TINA) platform narrative of neoliberalism, even when opposed to it...From Francis Fukuyama and Thomas Friedman in the early years, to Thomas Piketty, Yuval Noah Harari, and David Graeber in the final years, many could, and did, peddle coherent (if not always compelling) Big Histories. Narrative performance venues like TED flourished. The TINA platform narrative supplied the worldwinds for all narratives.
Weakly Narratable Conditions
The 2007-2020 period, arguably, was such a period (the long overlap of 8 years, 2007-15, was a period with uneven weak/strong narratability). In such conditions, a situation is messed-up and contentious, but in a way that lends itself to the flourishing of a pluralist, polycentric narrative landscape, where there are multiple contending accounts of a shared situation, Rashomon style, but the situation is merely ambiguous, not incoherent.
While weakly narratable conditions lack platform narratives, you could argue that there is something of a prevailing narrative protocol during weakly narratable times - an emergent lawful pattern of narrative conflict that cannot be codified into a legible set of consensus rules of narrative engagement, but produces slow noisy progress anyway, does not devolve into confused chaos, and sustains a learnable narrative literacy.
This is what it meant to be “very online” in 2007-20. It meant you had acquired a certain literacy around the prevailing narrative protocol. Perhaps nobody could make sense of what was going on overall, beyond their private, solipsistic account of events, and it was perhaps not possible to play to win, but there was enough coherence in the situation that you could at least play to not lose.
Unnarratable Conditions
The pandemic hit, and we got to what I think of as unnarratable conditions...While the specific story of the pandemic itself was narratable, the story of the wider post-Weirding world, thrown into tumult by the pandemic, was essentially unnarratable.
Unnarratable times are fundamentally incoherent melees of contending historical forces. Times when there isn’t even a narrative protocol you can acquire a reliable literacy in, let alone a platform narrative upon which to rest your sense-making efforts. Where the environmental entropy is so high, people struggle to put together any kind of narrative, even solipsistic private ones that harbor no ambitions of inDuencing others. There is no privileged class (comparable to the “Very Online” before 2020) that can plausibly claim a greater narrative literacy than other classes.
Those who claim to possess satisfying grand narratives are barely able to persuade even close allies to share it, let alone induce narrative protocols through them, or install them as platform narratives. The result: a collective retreat to a warren of cozy cultural redoubts, usually governed by comforting reactionary or nostalgic local narratives, and a derelict public discourse.
We have been in such a condition at least since 2022, and arguably since 2020. If you set aside the narrow liminal story of the pandemic, the world has been nearly unnarratable for years now.

Wednesday, July 26, 2023

A MindBlog paragraph on non-dual awareness massaged by Bard and ChatGPT-4

This post is using MindBlog to archive a further example example of the sort shown in Monday’s post ...of GPT bots editing  a paragraph I wrote, this one being on non-dual awareness.  The paragraph:

The fact that  there is no there there means it. Empty is empty. The ground state is just the mute body doing its thing. From its depths storylines rise and fall, bonbons to savor or ignore. The body can know that it has found a new ground state, and can be no longer willing to just play nice if the upstairs word salad is dinking around with or threatening its peace. It can withdraw from the fray. It can rest as a calm non-dual self centered within a cosmic perspective of time and space that views the rise and fall of human civilizations during the anthropocene as minor dances in the music of time.

After incorporating some changes suggested by Google Bard and GPT4:

When we say something is empty, we mean just that: it contains nothing. Our natural baseline or 'ground state' is the body performing its automatic functions without our conscious intervention. From the body's inherent depths, various thoughts or experiences emerge and recede, like bonbons we can savor or ignore. The body can grow to know that it has found a new ground state in the present moment, a ground state of awareness that no longer needs to be caught up in word salads of disruptive thoughts that can threaten its peace.  It can withdraw from the fray and can rest as a calm non-dual state of being centered within a cosmic perspective of time and space that can view the rise and fall of human civilizations during the anthropocene as minor dances in the music of time.


Monday, July 24, 2023

The evolution of transhuman forms - a MindBlog paragraph edited by GPT implementations

In this post I am documenting the final result of passing a paragraph I wrote on future human evolution through a number of different GPT (generative pre-trained transformers). This is to archive the results of this exercise for myself, and in case it might be of interest to a few MindBlog readers. The bots were prompted by a request to re-write or edit the paragraph to make it more accessible to a reader with a college education.

The bottom line is that the edited versions with the most depth and coherence were obtained using Open AI’s ChatGPT-4.  Bard.google.com, Google Workspace Labs, and Microsoft’s Bing, respectively, provided increasingly less useful versions.   Here is my original paragraph:

The linguistic capabilities of generative pre-trained transformers based on silicon  - the same capabilities that have enabled human civilization  - will soon exceed those of humans. We have brought our understanding of what human beings as they now exist are about to a plateau level at which further increments of understanding will become increasingly small. The cream has been skimmed, the best cherries have been picked, and it seems appropriate to turn our  attention now to studying the evolution of trans human forms utilizing LLMs that are better able to manage themselves and the planet.  The action is in the the pretraining P of GPT, as the models move beyond their initial human management to the stage of evolving themselves, hopefully into benign versions of Darwin’s  “forms most beautiful and most wonderful.” What is the point of humans other than being self replicating machines that evolve into further forms, hopefully before they extinguish themselves by destroying the ecological environment required for their sustenance? Can they evolve into trans human minds (or mind, singular)?
Here is the result of including some of the edits suggested by ChatGPT4’s regenerated response, a  vers. 3 of the paragraph above:
The linguistic capabilities of generative pre-trained transformers based on silicon - the same capabilities that have enabled human civilization - will soon surpass those of humans.

Our understanding of human nature as it currently exists has reached a plateau level, at which further increments of understanding are becoming increasingly small. The cream has been skimmed, the best cherries have been picked. Consequently it seems the right time to shift our focus toward studying the evolution of 'transhuman' forms. These are beings that could potentially leverage advanced language models (LLMs) to better self-regulate themselves and manage the planet.

The real crux of the matter lies in the pretraining phase of these transformers (symbolized by 'P' in GPT). This is when the models are initially developed and fine-tuned. As they evolve beyond their human programming the optimistic vision is that they might transform into benign versions of what Charles Darwin called “forms most beautiful and most wonderful.”

From a philosophical perspective, one might ask: What is the ultimate purpose of human beings, if not to serve as self-replicating entities that evolve into more advanced forms - hopefully before they extinguish themselves by destroying the ecological environment required for their sustenance? Is it possible for humans to evolve into a collective of transhuman minds or even a singular, transcendent mind?  These are questions worth exploring as we stand on the brink of an AI-enhanced future.


Wednesday, July 19, 2023

Proxy Failure is an Inherent Risk in Goal-Oriented Systems

I will pass on the title and abstract of another article to appear in Behavioral and Brain Science for which reviewers comments are being solicited. MindBlog readers can email me to request a PDF of the target article. 

Dead rats, dopamine, performance metrics, and peacock tails: proxy failure is an inherent risk in goal- oriented systems 

Authors: Yohan J. John, Leigh Caldwell, Dakota E. McCoy, and Oliver Braganza 

Abstract: When a measure becomes a target, it ceases to be a good measure. For example, when standardized test scores in education become targets, teachers may start 'teaching to the test', leading to breakdown of the relationship between the measure--test performance--and the underlying goal--quality education. Similar phenomena have been named and described across a broad range of contexts, such as economics, academia, machine-learning, and ecology. Yet it remains unclear whether these phenomena bear only superficial similarities, or if they derive from some fundamental unifying mechanism. Here, we propose such a unifying mechanism, which we label proxy failure. We first review illustrative examples and their labels, such as the 'Cobra effect', 'Goodhart's law', and 'Campbell's law'. Second, we identify central prerequisites and constraints of proxy failure, noting that it is often only a partial failure or divergence. We argue that whenever incentivization or selection is based on an imperfect proxy measure of the underlying goal, a pressure arises which tends to make the proxy a worse approximation of the goal. Third, we develop this perspective for three concrete contexts, namely neuroscience, economics and ecology, highlighting similarities and differences. Fourth, we outline consequences of proxy failure, suggesting it is key to understanding the structure and evolution of goal-oriented systems. Our account draws on a broad range of disciplines, but we can only scratch the surface within each. We thus hope the present account elicits a collaborative enterprise, entailing both critical discussion as well as extensions in contexts we have missed.

Monday, July 17, 2023

MindBlog's reading list.

I've decided to pass on links to articles I have found worthwhile reading , realizing that I am not going to have time to frame their ideas into longer posts because I'm speading more time now at my Steinway B's keyboard than at my computer's keyboard. If you encounter a paywall with any of the links, you might try entering the URL at https://archive.is/.

An installment of Venkatesh Rao’s newsletter: The permaweird narrative 

Jaron Lanier “There is no A.I.” in The New Yorker  

Human Beings Are Soon Going to Be Eclipsed’ David Brooks in The New York Times commenting on Douglas Hofstadter's  recent ideas.  

Marc Andreessen offers a horrific commentary titled "Fighting" on Elon Musk challenging Mark Zuckerberg to a cage fight.  

Learning from history. Archeological evidence that early hierarchical or authoritarian cultures didn't persist as long as more cooperative eqalitarian ones.  

Arthur Brooks on "The illusion of explanatory depth", an installment in his series "How to build a life.""  

Potential anti-aging therapy.  One sample of the effusive outpouring of new ideas and widgets offered by New Atlas.

 

 

 

Friday, July 14, 2023

‘Adversarial’ search for neural basis of consciousness yields first results

Finkel does a summary of the first round of results of an 'adversarial colloboration' funded by the Templeton World Charity Foundation in which
...both sides of the consciousness debate agreed on experiments to be conducted by “theory-neutral” labs with no stake in the outcome. It pits integrated information theory (IIT), the sensory network hypothesis that proposes a posterior “hot zone” as the site of consciousness, against the global neuronal workspace theory (GNWT), which likens networks of neurons in the front of the brain to a clipboard where sensory signals, thoughts, and memories combine before being broadcast across the brain.
The results corroborate IIT’s overall claim that posterior cortical areas are sufficient for consciousness, and neither the involvement of [the prefrontal cortex] nor global broadcasting are necessary,”
The article describes how the debate continues, with advocates of the prefrontal view suggesting this first experimental round had limitations, and that further experiments will support the role of the prefrontal cortex.

Wednesday, July 12, 2023

The True Threat of Artificial Intelligence

I would recommend having a read through Evgeny Morozov's piece in the NYTimes as an antidote to Marc Adreessen's optimistic vision of AI that was the subject of MindBlog's June 23 post. Here is a small clip from the article, followed by the titles describing different problem areas he sees:
Discussions of A.G.I. are rife with such apocalyptic scenarios. Yet a nascent A.G.I. lobby of academics, investors and entrepreneurs counter that, once made safe, A.G.I. would be a boon to civilization...This is why, for all the hand-wringing, so many smart people in the tech industry are toiling to build this controversial technology: not using it to save the world seems immoral.
They are beholden to an ideology that views this new technology as inevitable and, in a safe version, as universally beneficial. Its proponents can think of no better alternatives for fixing humanity and expanding its intelligence.
But this ideology — call it A.G.I.-ism — is mistaken. The real risks of A.G.I. are political and won’t be fixed by taming rebellious robots. The safest of A.G.I.s would not deliver the progressive panacea promised by its lobby. And in presenting its emergence as all but inevitable, A.G.I.-ism distracts from finding better ways to augment intelligence.
Unbeknown to its proponents, A.G.I.-ism is just a bastard child of a much grander ideology, one preaching that, as Margaret Thatcher memorably put it, there is no alternative, not to the market.
Rather than breaking capitalism, as Mr. Altman has hinted it could do, A.G.I. — or at least the rush to build it — is more likely to create a powerful (and much hipper) ally for capitalism’s most destructive creed: neoliberalism.
Fascinated with privatization, competition and free trade, the architects of neoliberalism wanted to dynamize and transform a stagnant and labor-friendly economy through markets and deregulation.
Some of these transformations worked, but they came at an immense cost. Over the years, neoliberalism drew many, many critics, who blamed it for the Great Recession and financial crisis, Trumpism, Brexit and much else.
It is not surprising, then, that the Biden administration has distanced itself from the ideology, acknowledging that markets sometimes get it wrong. Foundations, think tanks and academics have even dared to imagine a post-neoliberal future.
Yet neoliberalism is far from dead. Worse, it has found an ally in A.G.I.-ism, which stands to reinforce and replicate its main biases: that private actors outperform public ones (the market bias), that adapting to reality beats transforming it (the adaptation bias) and that efficiency trumps social concerns (the efficiency bias).
These biases turn the alluring promise behind A.G.I. on its head: Instead of saving the world, the quest to build it will make things only worse. Here is how.
A.G.I. will never overcome the market’s demands for profit.
A.G.I. will dull the pain of our thorniest problems without fixing them.
A.G.I. undermines civic virtues and amplifies trends we already dislike.
Depending on how (and if) the robot rebellion unfolds, A.G.I. may or may not prove an existential threat. But with its antisocial bent and its neoliberal biases, A.G.I.-ism already is: We don’t need to wait for the magic Roombas to question its tenets.

Monday, July 10, 2023

Inheritance of social status - stability in England from 1600 to 2022.

From historical records Clarks demonstrates (open source) strong persistence of social status across family trees over 400 years, in spite of large increases in general levels of education and social mobility.  

Significance

There is widespread belief across the social sciences in the ability of social interventions and social institutions to significantly influence rates of social mobility. In England, 1600 to 2022, we see considerable change in social institutions across time. Half the population was illiterate in 1,800, and not until 1,880 was compulsory primary education introduced. Progressively after this, educational provision and other social supports for poorer families expanded greatly. The paper shows, however, that these interventions did not change in any measurable way the strong familial persistence of social status across generations.
Abstract
A lineage of 422,374 English people (1600 to 2022) contains correlations in social outcomes among relatives as distant as 4th cousins. These correlations show striking patterns. The first is the strong persistence of social status across family trees. Correlations decline by a factor of only 0.79 across each generation. Even fourth cousins, with a common ancestor only five generations earlier, show significant status correlations. The second remarkable feature is that the decline in correlation with genetic distance in the lineage is unchanged from 1600 to 2022. Vast social changes in England between 1600 and 2022 would have been expected to increase social mobility. Yet people in 2022 remain correlated in outcomes with their lineage relatives in exactly the same way as in preindustrial England. The third surprising feature is that the correlations parallel those of a simple model of additive genetic determination of status, with a genetic correlation in marriage of 0.57.

Friday, July 07, 2023

A meta-analysis questions the cognitive benefits of physical activity.

I give up. If anything was supposed to have been proven I would have thought it would be that exercise has a beneficial effect on brain health and cognition. Now Ciria et al. offer the following in Nature Human Biology:
Extensive research links regular physical exercise to an overall enhancement of cognitive function across the lifespan. Here we assess the causal evidence supporting this relationship in the healthy population, using an umbrella review of meta-analyses limited to randomized controlled trials (RCTs). Despite most of the 24 reviewed meta-analyses reporting a positive overall effect, our assessment reveals evidence of low statistical power in the primary RCTs, selective inclusion of studies, publication bias and large variation in combinations of pre-processing and analytic decisions. In addition, our meta-analysis of all the primary RCTs included in the revised meta-analyses shows small exercise-related benefits (d = 0.22, 95% confidence interval 0.16 to 0.28) that became substantially smaller after accounting for key moderators (that is, active control and baseline differences; d = 0.13, 95% confidence interval 0.07 to 0.20), and negligible after correcting for publication bias (d = 0.05, 95% confidence interval −0.09 to 0.14). These findings suggest caution in claims and recommendations linking regular physical exercise to cognitive benefits in the healthy human population until more reliable causal evidence accumulates.
I can not offer an informed opinion on this abstract because my usual access to journals through the University of Wisconsin library does not work with Nature Human Behavior. However, I can point you to an excellent commentary by Claudia Lopez Lloreda that discusses the meta-analysis done by Ciria et al. and gives a summary of several recent studies on exercise and brain health.

Wednesday, July 05, 2023

Why music training slows cognitive aging

A team of Chinese collaborators has reported experiments in the Oxford academic journal Cerebral Cortex titled "Functional gradients in prefrontal regions and somatomotor networks reflect the effect of music training experience on cognitive aging" which are stated to show that music training enhances the functional separation between regions across prefrontal and somatomotor networks, delaying deterioration in working memory performance and prefrontal suppression of prominant but irrelevant information. I'm passing on the abstract and a clip from the paper's conclusion, and can send interested readers the whole article. I think it is an important article but I find it is rendered almost unintelligble by Chinese to English translation issues. I'm surprised the journal let this article appear without further editing.
Studies showed that the top-down control of the prefrontal cortex (PFC) on sensory/motor cortices changes during cognitive aging. Although music training has demonstrated efficacy on cognitive aging, its brain mechanism is still far from clear. Current music intervention studies have paid insufficient attention to the relationship between PFC and sensory regions. Functional gradient provides a new perspective that allows researchers to understand network spatial relationships, which helps study the mechanism of music training that affects cognitive aging. In this work, we estimated the functional gradients in four groups, young musicians, young control, older musicians, and older control. We found that cognitive aging leads to gradient compression. Compared with young subjects, older subjects presented lower and higher principal gradient scores in the right dorsal and medial prefrontal and the bilateral somatomotor regions, respectively. Meanwhile, by comparing older control and musicians, we found a mitigating effect of music training on gradient compression. Furthermore, we revealed that the connectivity transitions between prefrontal and somatomotor regions at short functional distances are a potential mechanism for music to intervene in cognitive aging. This work contributes to understanding the neuroplasticity of music training on cognitive aging.
From the conclusion paragraph:
In a nutshell, we demonstrate the top-down control of prefrontal regions to the somatomotor network, which is associated with inhibitory function and represents a potential marker of cognitive aging, and reveal that music training may work by affecting the connectivity between the two regions. Although this work has investigated the neuroplasticity of music on cognitive aging by recruiting subjects of different age spans, the present study did not include the study of longitudinal changes of the same group. Further studies should include longitudinal follow-up of the same groups over time to more accurately evaluate the effect of music intervention on the process of cognitive aging.

Monday, July 03, 2023

What Babies Know from zero to 1 year - core systems of knowledge

The journal Behavioral and Brain Sciences has sent out to reviewers the précis of a book, "What Babies Know" by Elizabeth S. Spelke, Harvard Psychology Dept. The abstract of her précis:
Where does human knowledge begin? Research on human infants, children, adults, and non- human animals, using diverse methods from the cognitive, brain, and computational sciences, provides evidence for six early emerging, domain-specific systems of core knowledge. These automatic, unconscious systems are situated between perceptual systems and systems of explicit concepts and beliefs. They emerge early in infancy, guide children’s learning, and function throughout life.
Spelke lists domain-specific core systems that are ancient, emerge early in life, and are invariant over later development. These deal with vision, objects, places, number, core knowledge, agents, social cognition, and language. Figures in the précis illustrate basic experiments characterizing the core systems. Motivated readers can obtain a PDF of the precis by emailing me.

Friday, June 30, 2023

Managing the risks of AI in pragmatic ways.

I want to pass on the final paragraphs of a recent commentary by Venkatesh Rao on the tragedy of the Titan submersible, which was a consequence of Stockton Rush, the CEO of OceanGate Expeditions, taking a number of design risks to reduce costs and increase profits. The bulk of Rao's piece deals with issues in the design of potentially dangerous new technologies, and the final paragraphs deal with managing the risks of artificial intelligence in pragmatic ways.
...AI risk, understood as something very similar to ordinary kinds of engineering risk (such as the risk of submersibles imploding), is an important matter, but lurid theological conceptions of AI risk and “alignment” are a not-even-wrong basis for managing it. The Titan affair, as an object lesson in traditional risk-management, offers many good lessons for how to manage real AI risks in pragmatic ways.
But there’s another point, a novel one, that is present in the case of AI that I don’t think has ever been present in technological leaps of the past.
AI is different from other technologies in that it alters the felt balance between knowledge and incomprehension that shapes our individual and collective risk-taking in the world.
AIs are already very good at embodying knowledge, and better at explaining many complex matters than most humans. But they are not yet very good at embodying doubt and incomprehension. They structurally lack epistemic humility and the ability to act on a consciousness of ignorance in justifiably arbitrary ways (ie on the basis of untheorized conservative decision principles backed by a track record). This is something bureaucratic standards bodies do very well. It is something that “software bureaucracies” (such as RLFH — reinforcement learning with human feedback) don’t do very well at all. The much demonized (by the entrepreneurial class) risk-aversion of bureaucrats is also a kind of ex-officio epistemic humility that is an essential ingredient of technology ecosystems.
On the flip side, AI itself is currently a technology full of incomprehensibilities. We understand the low-level mechanics of graph weights, gradient descents, backpropagation, and matrix multiplications. We do not understand how that low-level machinery produces the emergent outcomes it does. Our incomprehensions about AI are comparable to our incomprehensions about our own minds. This makes them extremely well-suited (impedance matched) to being bolted onto our minds as cognitive prosthetics that feel very comfortable, increase our confidence about what we think we know, and turn into extensions of ourselves (this is not exactly surprising, given that they are trained on human-generated data).
As with submersibles, we are at an alchemical state of understanding with AIs, but because of the nature of the technology itself, we might develop a prosthetic overconfidence in our state of indirect knowledge about the world, via AI.
AI might turn all humans who use it into Stockton Rushes.
The risk that AIs might destroy us is in science-fictional ways is overblown, but the risk that they might tempt us into generalized epistemic overconfidence, and systematically blind us to our incomprehensions, leading us to hurt ourselves in complex ways, is probably not sufficiently recognized.
Already, masses of programmers are relying on AIs like Github Copilot, and acting with a level of confidence in generated code that is likely not justified. AI-augmented programmers, even if sober and cautious as unaugmented individuals, might be taking Stockton-Rush type risks due to the false confidence induced by their tools. I don’t know that this is true, but the reports I see about people being 10x more productive and taking pleasure in programming again strike me as warning signs. I suspect there might be premature aestheticization going on here.
And I suspect it will take a few AI-powered Titan-like tragedies for us to wise-up and do something about it.
One way to think about this risk is by analogy to WMDs. Most people think nuclear weapons when they hear the phrase, but perhaps the most destructive WMD in the world is cheap and highly effective small arms, which have made conflicts far deadlier in the last century, and killed way more humans in aggregate than nuclear weapons.
You do not need to worry about a single AI going “AGI” and bring God-like catastrophes of malice or indifference down upon us. We lack the “nuclear science” to make that sort of thing happen. But you do need to be worried about millions of ordinary humans, drawn into drunken overconfidence by AI tools, wreaking the kind of havoc small arms do.

Wednesday, June 28, 2023

Mechanisms that link psychological stress to the exacerbation of gut inflammation.

Schneider et al. describe one mechanism by which psychological stress deteriorates our health  -  the enteric nervous system relays psychological stress to intestinal inflammation. Here is their abstract:  

Highlights

• Psychological stress leads to monocyte-mediated exacerbation of gut inflammation
• Chronic glucocorticoid signaling drives the effect of stress on IBD
• Stress induces inflammatory enteric glia that promote monocyte recruitment via CSF1
• Stress provokes transcriptional immaturity in enteric neurons and dysmotility
Summary 
Mental health profoundly impacts inflammatory responses in the body. This is particularlyapparent in inflammatory bowel disease (IBD), in which psychological stress is associated with exacerbated disease flares. Here, we discover a critical role for the enteric nervous system (ENS) in mediating the aggravating effect of chronic stress on intestinal inflammation. We find that chronically elevated levels of glucocorticoids drive the generation of an inflammatory subset of enteric glia that promotes monocyte- and TNF-mediated inflammation via CSF1. Additionally, glucocorticoids cause transcriptional immaturity in enteric neurons, acetylcholine deficiency, and dysmotility via TGF-β2. We verify the connection between the psychological state, intestinal inflammation, and dysmotility in three cohorts of IBD patients. Together, these findings offer a mechanistic explanation for the impact of the brain on peripheral inflammation, define the ENS as a relay between psychological stress and gut inflammation, and suggest that stress management could serve as a valuable component of IBD care.

Monday, June 26, 2023

The vagus nerve, heart rate variability, and subjective wellbeing - a MindBlog self experiment

In this post I pass on to MindBlog readers a NYTimes article by Christina Caron that has been republished several time by the newspaper. It is a sane account of what the vagus nerve is and what it does...The vagus is the main nerve of the parasympathetic nervous system. Unlike the sympathetic nervous system, which is associated with arousal of the body and the “fight or flight” response, the parasympathetic branch helps us rest, digest and calm down. Numerous experiments have shown that increased activity of the nerve correlates with an improvement in mood. from the article (slightly edited):
The activity of the vagus nerve is difficult to measure directly, especially given how complex it is. But because some vagus nerve fibers connect with the heart, experts can indirectly measure cardiac vagal tone — or the way in which your nervous system regulates your heart — by looking at your heart rate variability (HRV), which is the fluctuations in the amount of time between your heartbeats...An abnormal vagal tone — one in which there is very little HRV — has been associated with conditions like diabetes, heart failure and hypertension...A high HRV may signify an ideal vagal tone. The typical range of HRV is between 20 and 200 msec.

I will give my own experience...I have been using an Oura Ring since December 2021, and more recently an Apple watch,  to monitor nighttime resting heart rate, HRV, body temperature, and respiratory rate. By now I have documented numerous instances of a correlation - occurring over a period of several months - between subjective well being, average nighttime HRV, and duration of deep (restorative) sleep. (See the plot below showing HRV and duration of deep sleep over the past several months).  During periods of stress my average nighttime HRV decreases to ~20 msec and remains relatively constant throughout sleep, during periods when I am feeling open, chilled out, and flexible average nighttime HRV has increased to ~100 msec with large variations during the night. I've also played with techniques meant to tweak parasympathetic/sympathetic balance and found that delivering mild shocks to the body by perturbing breathing or using biofeedback to enhance HRV can correlate with increased average nighttime HRV and daytime sense of well being. Even though I take myself to be an unbiased observer and don't think that I am just feeling what I would like to feel - less stressed and more chilled out - it is important note the usual caveat that any human reports might be biased by a placebo effect. [BUT...see added note below]

Screen shot from the Oura Ring web interface:

NOTE ADDED 11/12/23:   The correlation shown has to taken with a grain of salt, because the correlation coefficient dropped to ~0.1 for the next three month period, and remains there as of 11/12/23