A flash of clarity on what current LLMs can and can not do. An AI apocalypse does not appear to be eminent...

In his most recent newsletter, Venkatesh Rao pulls up a twitter thread he wrote in 2017 making what he calls an ontological distinction between  boundary intelligence and interior intelligence.  This was before transformers like GPT-1 began to attract more attention. The distinction Rao makes is central to understanding what current large language models (LLMs) can and can not do. Here is his unedited text from 2017:
 
1. I'd like to make up a theory of intelligence based on a 2-element ontology: boundary and interior intelligence

2. Boundary intelligence is how you deal with information flows across the boundary of your processing abilities 

3. Interior intelligence is how you process information. Includes logic, emotional self-regulation, etc.

4. A thesis I've been converging on is that boundary intelligence is VASTLY more consequential once interior intelligence exceeds a minimum

5. Boundary intelligence is by definition meta, since you're tuning your filters and making choices about what to even let hit your attention

6. I think it is highly consequential because almost all risk management happens via boundary intelligence (blindspots, black swans etc)

7. Interior intelligence is your poker skill and strategy. Boundary intelligence is picking which table to sit down at

8. Interior intelligence is reading a book competently, extracting insights and arguments. Boundary intelligence is picking books to read. 

9. Interior intelligence is being a good listener. Boundary intelligence is deciding whom to listen to. 

10. Basically, better input plus mediocre IQ beats bad input and genius IQ every time, so boundary intelligence is leverage

11. And obviously, boundary intelligence is more sensitive to context. The noisier and angrier info streams get, the more BI beats II

12. Most of boundary intelligence has to do with input intelligence, but output intelligence becomes more important with higher agency 

13. Output intelligence is basically the metacognition around when/where/how/to-whom/why to say or do things you are capable of saying/doing

14. We think a lot about external factors in decisions, but output intelligence is about freedom left after you've dealt with external part

Next, from the abstract of a forthcoming paper by Yadlowsky et al. Rao extracts the following:

…when presented with tasks or functions which are out-of-domain of their pretraining data, we demonstrate various failure modes of transformers and degradation of their generalization for even simple extrapolation tasks. Together our results highlight that the impressive ICL abilities of high-capacity sequence models may be more closely tied to the coverage of their pretraining data mixtures than inductive biases that create fundamental generalization capabilities.

And then, in the following selected clips, continues his text:

Translated into the idiom from the fourteen points above, this translates into “It’s all interior intelligence, just within a very large boundary.” There is no boundary intelligence in current machine learning paradigms. There isn’t even an awareness of boundaries; just the ability to spout statements about doubt, unknowns, and boundaries of knowability; a bit like a blind person discussing color in the abstract.

This is not to say AI cannot acquire BI. In fact, it can do so in a very trivial way, through embodiment. Just add robots around current AIs and let them loose in real environments.

The reason people resist this conclusion is is irrational attachment to interior intelligence as a sacred cow (and among computer science supremacists, a reluctance to acknowledge the relevance and power of embodiment and situatedness in understandings of intelligence). If much of the effectual power of intelligence is attributable to boundary intelligence, there is much less room for sexy theories of interior intelligence. Your (cherished or feared) god-like AI is reduced to learning through FAFO (Fuck around and find out) feedback relationships with the rest of the universe, across its boundary, same as us sadsack meatbag intelligences with our paltry 4-GPU-grade interior intelligence.

In their current (undoubtedly very impressive) incarnation, what we have with AI is 100% II, 0% BI. Human and animal intelligences (and I suspect even plant intelligences, and definitely evolutionary process intelligence) are somewhere between 51-49 to 99.9-0.1% BI. They are dominated to varying degrees by boundary intelligence. Evolutionary processes are 100% BI, 0% II.

Born Rich

I want to pass on a few slightly edited clips from an interesting essay in The Dispatch by conservative writer Kevin Williamson that a friend pointed me to. And then I pass on the comment on Williamson's ideas offered by another friend: "Wow, this one’s a big gulp of the Kool-Aid. This thesis is patently untrue. As the one percent continues to grow in our current corporate low-tax, constantly crippled regulated business environment, the fallacy of this perspective grows along with it. This is exactly the thinking that book I recommended discusses (Oreskes and Conway: "How American business taught us to loathe government and love the free market.") Our democracy as it is currently functioning is not a Great Leveler.

One of the most distasteful aspects of our politics is the extent to which it is so obviously driven by envy, which is what 99 percent of that “privileged elite” talk ends up being about. But I suppose I am the wrong person to complain about that, because I was born rich, but I don't mean rich in the usual money sense.

Our intellectual and political life is dominated by a relatively narrow class of what we might call intellectually tall people, high-IQ people with diverse socioeconomic backgrounds. And while a great many of them believe that inherited wealth is profoundly unfair, very few of them have any similar thoughts to share about the social role of inherited intelligence.

One of the hardest things to drill into the noggins of the American ruling class (and let’s not pretend that there isn’t one, even if it isn’t exactly what you might expect) is that there is no more merit in being born with certain economically valuable intellectual talents than there is in being born tall, or with curly hair—or white, for that matter. Inherited wealth is an enormous factor in the lives of a relatively small number of Americans and a more modest one in the lives of a larger number, but inherited brainpower is the unearned asset that matters most. We live in a very competitive, very connected world, one with very, very efficient labor markets...We have pretty effective tools (including standardized testing) that are very useful for reaching far, wide, and deep into the population to identify intellectual high-fliers and to direct them into educational and career paths that will give them the chance to make the most out of their lives. There probably is no better place in the world to be born poor and smart—but there is no more merit in being born smart than there is blame in being born poor.

The American “meritocracy” is based to a considerable extent on the generally unspoken proposition that intelligence is merit, and that smart people deserve their success in a special way. Our country is run by smart people, and the smart people in charge very much want to believe that they are where they are because of merit, because of the exemplary lives they have led, not because of some unearned hereditary trait that is the intellectual equivalent of a trust fund. The 1994 book "The Bell Curve" was an attempt to explore the paradox of the hereditary “meritocracy” in a serious way, and it was shouted down by—this was not coincidental—the class of people whose self-conception as a meritorious elite was most directly threatened by the authors’ hypothesis.

Understanding the privileges that go along with inherited intellectual ability as being in a moral sense very much like the privileges that go along with inherited wealth (or an inherited social-racial position or whatever privilege you like) opens up a radical and disruptive perspective on American public life—and draws attention to social situations that, even if understood to be unfair because of the role of hereditary advantage, are not open to resolution through redistributive taxes or affirmative action or anything like that. We aren’t going to mandate that half of the brain surgeons or theoretical physicists have below-average IQs.

Being a conservative, I believe that a healthy society necessarily contains a great deal of organic, authentic diversity. Being a realist, I also believe that this diversity comes with hierarchy. As Russell Kirk observed:

Conservatives pay attention to the principle of variety. They feel affection for the proliferating intricacy of long-established social institutions and modes of life, as distinguished from the narrowing uniformity and deadening egalitarianism of radical systems. For the preservation of a healthy diversity in any civilization, there must survive orders and classes, differences in material condition, and many sorts of inequality. The only true forms of equality are equality at the Last Judgment and equality before a just court of law; all other attempts at levelling must lead, at best, to social stagnation. Society requires honest and able leadership; and if natural and institutional differences are destroyed, presently some tyrant or host of squalid oligarchs will create new forms of inequality.

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.
 

Decision-making ability, psychopathology, and brain connectivity

An open access review offered by Dolan and his colleagues continues the story of correlating our human competencies with our brain structures. They describe

...a new cognitive construct—decision acuity—that captures global decision-making ability. High decision acuity prominently reflected low decision variability. Decision acuity showed acceptable reliability, increased with age, and was associated with mental health symptoms independently of intelligence. Crucially, it was associated with distinctive resting-state networks, in particular in brain regions typically engaged by decision-making tasks. The association between decision acuity and functional connectivity was temporally stable and distinct from that of IQ.

Highlights

• Young people have a general decision-making ability, which we call “decision acuity” 

• Decision acuity is reflected in how strongly connected certain brain networks are 

• Low decision acuity is associated with general social function psychopathology

Summary

Decision-making is a cognitive process of central importance for the quality of our lives. Here, we ask whether a common factor underpins our diverse decision-making abilities. We obtained 32 decision-making measures from 830 young people and identified a common factor that we call “decision acuity,” which was distinct from IQ and reflected a generic decision-making ability. Decision acuity was decreased in those with aberrant thinking and low general social functioning. Crucially, decision acuity and IQ had dissociable brain signatures, in terms of their associated neural networks of resting-state functional connectivity. Decision acuity was reliably measured, and its relationship with functional connectivity was also stable when measured in the same individuals 18 months later. Thus, our behavioral and brain data identify a new cognitive construct that underpins decision-making ability across multiple domains. This construct may be important for understanding mental health, particularly regarding poor social function and aberrant thought patterns.

Cultural Evolution of Genetic Heritability

Behavioral and Brain Sciences has accepted an article from Uchiyama et al., whose abstract I copy below, and invites the submission of commentary proposals.

Behavioral genetics and cultural evolution have both revolutionized our understanding of human behavior—largely independent of each other. Here we reconcile these two fields under a dual inheritance framework, offering a more nuanced understanding of the interaction between genes and culture. Going beyond typical analyses of gene- environment interactions, we describe the cultural dynamics that shape these interactions by shaping the environment and population structure. A cultural evolutionary approach can explain, for example, how factors such as rates of innovation and diffusion, density of cultural sub-groups, and tolerance for behavioral diversity impact heritability estimates, thus yielding predictions for different social contexts. Moreover, when cumulative culture functionally overlaps with genes, genetic effects become masked, unmasked, or even reversed, and the causal effects of an identified gene become confounded with features of the cultural environment. The manner of confounding is specific to a particular society at a particular time, but a WEIRD (Western, educated, industrialized, rich, democratic) sampling problem obscures this boundedness. Cultural evolutionary dynamics are typically missing from models of gene-to-phenotype causality, hindering generalizability of genetic effects across societies and across time. We lay out a reconciled framework and use it to predict the ways in which heritability should differ between societies, between socioeconomic levels and other groupings within some societies but not others, and over the life course. An integrated cultural evolutionary behavioral genetic approach cuts through the nature-nurture debate and helps resolve controversies in topics such as IQ.

Perceptions of family social status correlate with health and life chances

A fascinating British twin study from Rivenbark et al:

Children from lower-income households are at increased risk for poor health, educational failure, and behavioral problems. This social gradient is one of the most reproduced findings in health and social science. How people view their position in social hierarchies also signals poor health. However, when adolescents’ views of their social position begin to independently relate to well-being is currently unknown. A cotwin design was leveraged to test whether adolescents with identical family backgrounds, but who viewed their family’s social status as higher than their same-aged and sex sibling, experienced better well-being in early and late adolescence. Participants were members of the Environmental Risk Longitudinal Twin Study, a representative cohort of British twins (n = 2,232) followed across the first 2 decades of life. By late adolescence, perceptions of subjective family social status (SFSS) robustly correlated with multiple indicators of health and well-being, including depression; anxiety; conduct problems; marijuana use; optimism; not in education, employment, or training (NEET) status; and crime. Findings held controlling for objective socioeconomic status both statistically and by cotwin design after accounting for measures of childhood intelligence (IQ), negative affect, and prior mental health risk and when self-report, informant report, and administrative data were used. Little support was found for the biological embedding of adolescents’ perceptions of familial social status as indexed by inflammatory biomarkers or cognitive tests in late adolescence or for SFSS in early adolescence as a robust correlate of well-being or predictor of future problems. Future experimental studies are required to test whether altering adolescents’ subjective social status will lead to improved well-being and social mobility.

Gender differences in the brain connections that predict intelligence.

From Jiang et al:

Scores on intelligence tests are strongly predictive of various important life outcomes. However, the gender discrepancy on intelligence quotient (IQ) prediction using brain imaging variables has not been studied. To this aim, we predicted individual IQ scores for males and females separately using whole-brain functional connectivity (FC). Robust predictions of intellectual capabilities were achieved across three independent data sets (680 subjects) and two intelligence measurements (IQ and fluid intelligence) using the same model within each gender. Interestingly, we found that intelligence of males and females were underpinned by different neurobiological correlates, which are consistent with their respective superiority in cognitive domains (visuospatial vs verbal ability). In addition, the identified FC patterns are uniquely predictive on IQ and its sub-domain scores only within the same gender but neither for the opposite gender nor on the IQ-irrelevant measures such as temperament traits. Moreover, females exhibit significantly higher IQ predictability than males in the discovery cohort. This findings facilitate our understanding of the biological basis of intelligence by demonstrating that intelligence is underpinned by a variety of complex neural mechanisms that engage an interacting network of regions—particularly prefrontal–parietal and basal ganglia—whereas the network pattern differs between genders.

Childhood deprivation alters adult brains despite subsequent environmental enrichment.

A sobering study from Mackes et al:  

Significance

Millions of children worldwide live in nonfamilial institutions. We studied impact on adult brain structure of a particularly severe but time-limited form of institutional deprivation in early life experienced by children who were subsequently adopted into nurturing families. Institutional deprivation was associated with lower total brain volume in a dose-dependent way. Regionally specific effects were seen in medial prefrontal, inferior frontal, and inferior temporal areas. Deprivation-related alterations in total brain volume were associated with lower intelligence quotient and more attention deficit/hyperactivity disorder symptoms; alterations in temporal volume seemed compensatory, as they were associated with fewer attention deficit/hyperactivity disorder symptoms. We provide evidence that early childhood deprivation is related to alterations in adult brain structure, despite environmental enrichment in intervening years.

Abstract

Early childhood deprivation is associated with higher rates of neurodevelopmental and mental disorders in adulthood. The impact of childhood deprivation on the adult brain and the extent to which structural changes underpin these effects are currently unknown. To investigate these questions, we utilized MRI data collected from young adults who were exposed to severe deprivation in early childhood in the Romanian orphanages of the Ceaușescu era and then, subsequently adopted by UK families; 67 Romanian adoptees (with between 3 and 41 mo of deprivation) were compared with 21 nondeprived UK adoptees. Romanian adoptees had substantially smaller total brain volumes (TBVs) than nondeprived adoptees (8.6% reduction), and TBV was strongly negatively associated with deprivation duration. This effect persisted after covarying for potential environmental and genetic confounds. In whole-brain analyses, deprived adoptees showed lower right inferior frontal surface area and volume but greater right inferior temporal lobe thickness, surface area, and volume than the nondeprived adoptees. Right medial prefrontal volume and surface area were positively associated with deprivation duration. No deprivation-related effects were observed in limbic regions. Global reductions in TBV statistically mediated the observed relationship between institutionalization and both lower intelligence quotient (IQ) and higher levels of attention deficit/hyperactivity disorder symptoms. The deprivation-related increase in right inferior temporal volume seemed to be compensatory, as it was associated with lower levels of attention deficit/hyperactivity disorder symptoms. We provide compelling evidence that time-limited severe deprivation in the first years of life is related to alterations in adult brain structure, despite extended enrichment in adoptive homes in the intervening years.

Training wisdom - the Illeist (third person) method.

I think my most sane moments are those when I experience myself as watching, in third-person mode, rather than “being” Deric, the immersed actor. Science journalist David Robson does an essay on this perspective in Aeon, “Why speaking to yourself in the third person makes you wiser,” noting that this ancient rhetorical method, used by Julius Caesar and termed ‘illeism’ in 1809 by the poet Coleridge (latin ille meaning ‘he, that’) can clear the emotional fog of simple rumination, shifting perspective to see past biases. Robson notes the work of Igor Grossmann at the University of Waterloo in Canada, whose aim is:

...to build a strong experimental footing for the study of wisdom, which had long been considered too nebulous for scientific enquiry. In one of his earlier experiments, he established that it’s possible to measure wise reasoning and that, as with IQ, people’s scores matter. He did this by asking participants to discuss out-loud a personal or political dilemma, which he then scored on various elements of thinking long-considered crucial to wisdom, including: intellectual humility; taking the perspective of others; recognising uncertainty; and having the capacity to search for a compromise. Grossmann found that these wise-reasoning scores were far better than intelligence tests at predicting emotional wellbeing, and relationship satisfaction – supporting the idea that wisdom, as defined by these qualities, constitutes a unique construct that determines how we navigate life challenges.

The abstract from Grossmann et al.:

We tested the utility of illeism – a practice of referring to oneself in the third person – for the trainability of wisdom-related characteristics in everyday life: i) wise reasoning (intellectual humility, open-mindedness in ways a situation may unfold, perspective-taking, attempts to integrate different viewpoints) and ii) accuracy in emotional forecasts toward close others. In a month-long field experiment, people adopted either the third-person training or first-person control perspective when describing their most significant daily experiences. Assessment of spontaneous wise reasoning before and after the intervention revealed substantial growth in the training (vs. control) condition. At the end of the intervention, people forecasted their feelings toward a close other in challenging situations. A month later, these forecasted feelings were compared against their experienced feelings. Participants in the training (vs. control) condition showed greater alignment of forecasts and experiences, largely due to changes in their emotional experiences. The present research demonstrates a path to evidence-based training of wisdom-related processes via the practice of illeism.

Robson finds this work particularly fascinating,

...considering the fact that illeism is often considered to be infantile. Just think of Elmo in the children’s TV show Sesame Street, or the intensely irritating Jimmy in the sitcom Seinfeld – hardly models of sophisticated thinking. Alternatively, it can be taken to be the sign of a narcissistic personality – the very opposite of personal wisdom. After all, Coleridge believed that it was a ruse to cover up one’s own egotism: just think of the US president’s critics who point out that Donald Trump often refers to himself in the third person. Clearly, politicians might use illeism for purely rhetorical purposes but, when applied to genuine reflection, it appears to be a powerful tool for wiser reasoning.

For an example of third person usage reflecting not wisdom, but a narcissistic personality, look no further than our current president, Donald Trump, as noted in this Washington Post piece by Rieger.

Watching social influence start to bias perceptual integration as children develop

From Large et al.:

The opinions of others have a profound influence on decision making in adults. The impact of social influence appears to change during childhood, but the underlying mechanisms and their development remain unclear. We tested 125 neurotypical children between the ages of 6 and 14 years on a perceptual decision task about 3D-motion figures under informational social influence. In these children, a systematic bias in favor of the response of another person emerged at around 12 years of age, regardless of whether the other person was an age-matched peer or an adult. Drift diffusion modeling indicated that this social influence effect in neurotypical children was due to changes in the integration of sensory information, rather than solely a change in decision behavior. When we tested a smaller cohort of 30 age- and IQ-matched autistic children on the same task, we found some early decision bias to social influence, but no evidence for the development of systematic integration of social influence into sensory processing for any age group. Our results suggest that by the early teens, typical neurodevelopment allows social influence to systematically bias perceptual processes in a visual task previously linked to the dorsal visual stream. That the same bias did not appear to emerge in autistic adolescents in this study may explain some of their difficulties in social interactions.

Brain biomarkers for resilience - executive frontal lobe activity

Friedman points to several articles demonstrating brain correlates of resilience to social adversity:

 -higher connectivity within the brain’s frontoparietal central executive network.
 -increased activity in prefrontal and anterior cingulate areas of executive self control network after mindfulness training.
-stimulation of brain plasticity and remodeling by BDNF growth factor,whose levels are enhanced by exercise and social support.

Scult et al. do a more detailed look at brain correlates of resilience. Their abstract:

Compared with neural biomarkers of risk for mental illness, little is known about biomarkers of resilience. We explore if greater executive control-related prefrontal activity may function as a resilience biomarker by “rescuing” risk associated with higher threat-related amygdala and lower reward-related ventral striatum activity. Functional MRI was used to assay baseline threat-related amygdala, reward-related ventral striatum, and executive control-related prefrontal activity in 120 young adult volunteers. Participants provided self-reported mood and anxiety ratings at baseline and follow-up. A moderation model revealed a significant three-way interaction wherein higher amygdala and lower ventral striatum activity predicted increases in anxiety in those with average or low but not high prefrontal activity. This effect was specific to anxiety, with the neural biomarkers explaining ~10% of the variance in change over time, above and beyond baseline symptoms, sex, age, IQ, presence or absence of DMS-IV diagnosis, and both early and recent stress. Our findings are consistent with the importance of top-down executive control in adaptive regulation of negative emotions, and highlight a unique combination of neural biomarkers that may identify at-risk individuals for whom the adoption of strategies to improve executive control of negative emotions may prove particularly beneficial.

It's better to be born rich than gifted.

Andrew Van Dam points to work by Papageorge and Thom use genome based measurements to demonstrate that even though genetic endowments are distributed almost equally among children in low-income and high-income families the least-gifted children of high-income parents graduate from college at higher rates than the most-gifted children of low-income parents.

Thom and Papageorge’s analysis builds on the findings of one of the biggest genome-wide studies yet conducted. Published by a separate team of a dozen authors in Nature Genetics in July, it’s the latest result of a lengthy, ongoing effort to bring genetic analysis to the social sciences.

The Nature Genetics team scanned millions of individual base pairs across 1,131,881 individual genomes for evidence of correlations between genes and years of schooling completed. They synthesized the findings into a single score we can use to predict educational attainment based on genetic factors.

Thom and Papageorge studied the team’s index after it was calculated for a long-running retirement survey sponsored by the Social Security Administration and the National Institute on Aging. About 20,000 of the survey’s respondents, born between 1905 and 1964, provided their DNA along with their responses, which allowed the economists to attach genetic scores individuals’ academic and economic achievements.

Previous attempts to separate academic potential from the advantages given to children of wealthy families relied on measures such as IQ tests, which are biased by parents’ education, occupation and income...Two people who are genetically similar can have strikingly different IQ test scores because the richer ones have invested more in their kids.

Piano training enhances speech perception.

Fascinating work from an international collaboration of Desimone at M.I.T., Nan at Beijing Normal Univ., and others:

Significance

Musical training is beneficial to speech processing, but this transfer’s underlying brain mechanisms are unclear. Using pseudorandomized group assignments with 74 4- to 5-year-old Mandarin-speaking children, we showed that, relative to an active control group which underwent reading training and a no-contact control group, piano training uniquely enhanced cortical responses to pitch changes in music and speech (as lexical tones). These neural enhancements further generalized to early literacy skills: Compared with the controls, the piano-training group also improved behaviorally in auditory word discrimination, which was correlated with their enhanced neural sensitivities to musical pitch changes. Piano training thus improves children’s common sound processing, facilitating certain aspects of language development as much as, if not more than, reading instruction.

Abstract

Musical training confers advantages in speech-sound processing, which could play an important role in early childhood education. To understand the mechanisms of this effect, we used event-related potential and behavioral measures in a longitudinal design. Seventy-four Mandarin-speaking children aged 4–5 y old were pseudorandomly assigned to piano training, reading training, or a no-contact control group. Six months of piano training improved behavioral auditory word discrimination in general as well as word discrimination based on vowels compared with the controls. The reading group yielded similar trends. However, the piano group demonstrated unique advantages over the reading and control groups in consonant-based word discrimination and in enhanced positive mismatch responses (pMMRs) to lexical tone and musical pitch changes. The improved word discrimination based on consonants correlated with the enhancements in musical pitch pMMRs among the children in the piano group. In contrast, all three groups improved equally on general cognitive measures, including tests of IQ, working memory, and attention. The results suggest strengthened common sound processing across domains as an important mechanism underlying the benefits of musical training on language processing. In addition, although we failed to find far-transfer effects of musical training to general cognition, the near-transfer effects to speech perception establish the potential for musical training to help children improve their language skills. Piano training was not inferior to reading training on direct tests of language function, and it even seemed superior to reading training in enhancing consonant discrimination.

A way to change adult behaviors - debiasing decisions.

Hambrick and Burgoyne do a piece on the difference between rationality and intelligence. Starting from Kahneman and Tversky's work in the early 1970's, countless experiments by now have shown that we are frequently prone to make decisions based on faulty intuition rather than reason. Further, a person with high I.Q. (which reflects abstract reasoning and verbal ability) is no less likely to display "dysrationalia." They point to experiments by Morewedge and colleagues showing that rationality, unlike intelligence, can be improved by a single video or computer training session that illustrates decision-making biases. The improvement was still observed two months later in a different version of the decision-making test. Here is their abstract:

From failures of intelligence analysis to misguided beliefs about vaccinations, biased judgment and decision making contributes to problems in policy, business, medicine, law, education, and private life. Early attempts to reduce decision biases with training met with little success, leading scientists and policy makers to focus on debiasing by using incentives and changes in the presentation and elicitation of decisions. We report the results of two longitudinal experiments that found medium to large effects of one-shot debiasing training interventions. Participants received a single training intervention, played a computer game or watched an instructional video, which addressed biases critical to intelligence analysis (in Experiment 1: bias blind spot, confirmation bias, and fundamental attribution error; in Experiment 2: anchoring, representativeness, and social projection). Both kinds of interventions produced medium to large debiasing effects immediately (games ~ −31.94% and videos ~ −18.60%) that persisted at least 2 months later (games ~ −23.57% and videos ~ −19.20%). Games that provided personalized feedback and practice produced larger effects than did videos. Debiasing effects were domain general: bias reduction occurred across problems in different contexts, and problem formats that were taught and not taught in the interventions. The results suggest that a single training intervention can improve decision making. We suggest its use alongside improved incentives, information presentation, and nudges to reduce costly errors associated with biased judgments and decisions.

Placebo effects in brain training

Foroughi et al. address the question of whether our desire to become smarter may blind us to the role of placebo effects in brain training regimes. They found that few published articles on cognitive training provide details regarding participant recruitment... whether participants were recruited overtly [e.g., “sign up for a brain training study” ] or covertly [e.g., “did not inform subjects that they were participating in a training study”]. The authors:

...designed a procedure to intentionally induce a placebo effect via overt recruitment. Our recruitment targeted two populations of participants using different advertisements varying in the degree to which they evoked an expectation of cognitive improvement. Once participants self-selected into the two groups, they completed two pretraining fluid intelligence tests followed by 1 h of cognitive training and then completed two posttraining fluid intelligence tests on the following day. Two individual difference metrics regarding beliefs about cognition and intelligence were also collected as potential moderators. The researchers who interacted with participants were blind to the goal of the experiment and to the experimental condition. Aside from their means of recruitment, all participants completed identical cognitive-training experiments. All participants read and signed an informed consent form before beginning the experiment.

Here are their summaries:

Significance

Placebo effects pose problems for some intervention studies, particularly those with no clearly identified mechanism. Cognitive training falls into that category, and yet the role of placebos in cognitive interventions has not yet been critically evaluated. Here, we show clear evidence of placebo effects after a brief cognitive training routine that led to significant fluid intelligence gains. Our goal is to emphasize the importance of ruling out alternative explanations before attributing the effect to interventions. Based on our findings, we recommend that researchers account for placebo effects before claiming treatment effects.

Abstract

Although a large body of research shows that general cognitive ability is heritable and stable in young adults, there is recent evidence that fluid intelligence can be heightened with cognitive training. Many researchers, however, have questioned the methodology of the cognitive-training studies reporting improvements in fluid intelligence: specifically, the role of placebo effects. We designed a procedure to intentionally induce a placebo effect via overt recruitment in an effort to evaluate the role of placebo effects in fluid intelligence gains from cognitive training. Individuals who self-selected into the placebo group by responding to a suggestive flyer showed improvements after a single, 1-h session of cognitive training that equates to a 5- to 10-point increase on a standard IQ test. Controls responding to a nonsuggestive flyer showed no improvement. These findings provide an alternative explanation for effects observed in the cognitive-training literature and the brain-training industry, revealing the need to account for confounds in future research.

A positive tonic: Human Progress Quantified

Edge.org has just posted responses to its 2016 question of the year "What do you consider the most interesting recent [scientific] news? What makes it important?" Over the next period of time I'm going to be posting edited clips from some of these responses, starting today with Steven Pinker's contribution on human progress:

Human intuition is a notoriously poor guide to reality...Fortunately, as the bugs in human cognition have become common knowledge, the workaround—objective data—has become more prevalent...Sports have been revolutionized by Moneyball, policy by Nudge, punditry by 538.com, forecasting by tournaments and prediction markets, philanthropy by effective altruism, the healing arts by evidence-based medicine.

The most interesting news is that the quantification of life has been extended to the biggest question of all: Have we made progress... in improving the human condition?...Most people agree that life is better than death, health better than disease, prosperity better than poverty, knowledge better than ignorance, peace better than war, safety better than violence, freedom better than coercion. That gives us a set of yardsticks by which we can measure whether progress has actually occurred. The interesting news is that the answer is mostly "yes."... the rate of homicides and war deaths had plummeted over time...People are living longer and healthier lives, not just in the developed world but globally. A dozen infectious and parasitic diseases are extinct or moribund. Vastly more children are going to school and learning to read. Extreme poverty has fallen worldwide from 85 to 10 percent. Despite local setbacks, the world is more democratic than ever. Women are better educated, marrying later, earning more, and in more positions of power and influence. Racial prejudice and hate crimes have decreased since data were first recorded. The world is even getting smarter: In every country, IQ has been increasing by three points a decade.

"Ecomodernists" such as Stewart Brand, Jesse Ausubel, and Ruth DeFries have shown that many indicators of environmental health have improved over the last half-century, and that there are long-term historical processes, such as the decarbonization of energy, the dematerialization of consumption, and the minimization of farmland that can be further encouraged...for all the ways in which the world today falls short of utopia, the norms and institutions of modernity have put us on a good track. We should work on improving them further, rather than burning them down in the conviction that nothing could be worse than our current decadence and in the vague hope that something better might rise from their ashes...quantified human progress emboldens us to seek more of it...The empowering feature of a graph is that it invites one to identify the forces that are pushing a curve up or down, and then to apply them to push it further in the same direction.

Boosting our brain plasticity.

Wow, this study by Forsyth et al. makes me want to run out and buy a bottle of D-cycloserine, which they show enhances experience-dependent learning, i.e. brain plasticity, in healthy adult humans. (Actually, it's expensive, and experimenting with it by yourself is not a good idea.)

 Significance

Experience-dependent plasticity is the capacity of the brain to undergo changes following environmental input and use, and is a primary means through which the adult brain enables new behavior. In the current study, we provide evidence that enhancing signaling at the glutamate N-methyl-D-aspartate receptor (NMDAR) can enhance the mechanism underlying many forms of experience-dependent plasticity (i.e., long-term potentiation of synaptic currents) and also enhance experience-dependent learning in healthy adult humans. This suggests exciting possibilities for manipulating plasticity in adults and has implications for treating neurological and neuropsychiatric disorders in which experience-dependent plasticity is impaired.

Abstract

Experience-dependent plasticity is a fundamental property of the brain. It is critical for everyday function, is impaired in a range of neurological and psychiatric disorders, and frequently depends on long-term potentiation (LTP). Preclinical studies suggest that augmenting N-methyl-D-aspartate receptor (NMDAR) signaling may promote experience-dependent plasticity; however, a lack of noninvasive methods has limited our ability to test this idea in humans until recently. We examined the effects of enhancing NMDAR signaling using D-cycloserine (DCS) on a recently developed LTP EEG paradigm that uses high-frequency visual stimulation (HFvS) to induce neural potentiation in visual cortex neurons, as well as on three cognitive tasks: a weather prediction task (WPT), an information integration task (IIT), and a n-back task. The WPT and IIT are learning tasks that require practice with feedback to reach optimal performance. The n-back assesses working memory. Healthy adults were randomized to receive DCS (100 mg; n = 32) or placebo (n = 33); groups were similar in IQ and demographic characteristics. Participants who received DCS showed enhanced potentiation of neural responses following repetitive HFvS, as well as enhanced performance on the WPT and IIT. Groups did not differ on the n-back. Augmenting NMDAR signaling using DCS therefore enhanced activity-dependent plasticity in human adults, as demonstrated by lasting enhancement of neural potentiation following repetitive HFvS and accelerated acquisition of two learning tasks. Results highlight the utility of considering cellular mechanisms underlying distinct cognitive functions when investigating potential cognitive enhancers.

Brain imaging can predict six-year outcomes in children’s numerical abilities.

Interesting work from Evans et al.:

Significance Statement

Children show substantial individual differences in math abilities and ease of math learning. Early numerical abilities provide the foundation for future academic and professional success in an increasingly technological society. Understanding the early identification of poor math skills has therefore taken on great significance. This work provides important new insights into brain structure and connectivity measures that can predict longitudinal growth of children's math skills over a 6 year period, and may eventually aid in the early identification of children who might benefit from targeted interventions.

Abstract

Early numerical proficiency lays the foundation for acquiring quantitative skills essential in today's technological society. Identification of cognitive and brain markers associated with long-term growth of children's basic numerical computation abilities is therefore of utmost importance. Previous attempts to relate brain structure and function to numerical competency have focused on behavioral measures from a single time point. Thus, little is known about the brain predictors of individual differences in growth trajectories of numerical abilities. Using a longitudinal design, with multimodal imaging and machine-learning algorithms, we investigated whether brain structure and intrinsic connectivity in early childhood are predictive of 6 year outcomes in numerical abilities spanning childhood and adolescence. Gray matter volume at age 8 in distributed brain regions, including the ventrotemporal occipital cortex (VTOC), the posterior parietal cortex, and the prefrontal cortex, predicted longitudinal gains in numerical, but not reading, abilities. Remarkably, intrinsic connectivity analysis revealed that the strength of functional coupling among these regions also predicted gains in numerical abilities, providing novel evidence for a network of brain regions that works in concert to promote numerical skill acquisition. VTOC connectivity with posterior parietal, anterior temporal, and dorsolateral prefrontal cortices emerged as the most extensive network predicting individual gains in numerical abilities. Crucially, behavioral measures of mathematics, IQ, working memory, and reading did not predict children's gains in numerical abilities. Our study identifies, for the first time, functional circuits in the human brain that scaffold the development of numerical skills, and highlights potential biomarkers for identifying children at risk for learning difficulties.

Cognitive abilities across the lifespan.

Hartshorne and Germine do a massive analysis of changes in cognitive abilities across the life span, showing that digit symbol coding, digit span, vocabulary, working memory, and facial emotion perception peak and decline at different times, with the last of these continuing to improve into later ages.

For each task, the median (interior line), interquartile range (left and right edges of boxes), and 95% confidence interval (whiskers) are shown. WM = working memory.

Their abstract:

Understanding how and when cognitive change occurs over the life span is a prerequisite for understanding normal and abnormal development and aging. Most studies of cognitive change are constrained, however, in their ability to detect subtle, but theoretically informative life-span changes, as they rely on either comparing broad age groups or sparse sampling across the age range. Here, we present convergent evidence from 48,537 online participants and a comprehensive analysis of normative data from standardized IQ and memory tests. Our results reveal considerable heterogeneity in when cognitive abilities peak: Some abilities peak and begin to decline around high school graduation; some abilities plateau in early adulthood, beginning to decline in subjects’ 30s; and still others do not peak until subjects reach their 40s or later. These findings motivate a nuanced theory of maturation and age-related decline, in which multiple, dissociable factors differentially affect different domains of cognition.

Aging - predictors of cognitive abilities.

The Oct. 31 issue of Science Magazine has a special section of articles on the aging brain. I point in particular to Underwood's article, "Starting young", which describes the followup on a Scottish national intelligence test performed on every 11 year old in the country in 1932 and 1947. The finding was that an individual's level of intelligence at age 11 is the most powerful predictor of late-life cognitive ability — not diet, social engagement, or any other virtuous activity. Scores at age 11 predicted about 50% of the variance in the IQs at age 77 in a cohort of individuals living in the Lothian region near Edinburgh (1641 of the original 5000 people tested were assessed.) Note the bottom line indicated in the final clip below:

By having an intelligence measure from even earlier in life, the Lothian studies are helping distinguish glitter from gold in the vast literature on factors correlated with cognition. A good recent example is Deary's analysis of the potential benefits of drinking, Thompson says. A smattering of correlational studies suggest that drinking small amounts of wine has positive effects on cognition late in life—indeed, Deary initially found a similar result when he first looked for a relationship between alcohol consumption and cognitive performance in the Lothian cohort. When he accounted for the participants' IQ scores on the Scottish Mental Survey, however, the perceived benefit dissolved. Rather than gaining cognitive benefit from drinking wine when they were older, “people who drank more were already likely to be smart,” Deary says.

The Lothian cohort has similarly challenged other reported influences on cognition, such as diet, body mass index, and caffeine consumption. None of those factors seems to have any effect on cognitive skills in the Lothian cohort when childhood intelligence is accounted for, Deary says. Even the effects of social and intellectual activity disappeared when he took into account how bright children were at age 11, possibly because those children are more likely to end up being socially and intellectually engaged.

And a final clip:

...the growing body of data from the Lothian Birth Cohort studies and other aging research supports a theory that some describe irreverently, and a little brutally, as the “water tank hypothesis”: The better put-together your brain is early on, thanks to good genes and, to some extent, a favorable early life environment, the more cognitive reserves you have to lose to neurodegeneration. In other words, Martin says, “the more you start out with in the tank, the longer it takes to draw down.”