The unbearable slowness of being: Why do we live at 10 bits/s?

A brief review by Rachel Nuwer in the Scientific American points to an article by Zheng and Meister with the title of this post (motivated readers can obtain a PDF of the article from me).  

I pass on an initial clip from Nuwer's review and then the abstract of the Zheng and Meister paper: 

PEOPLE OFTEN FEEL that their inner thoughts and feelings are much richer than what they are capable of expressing in real time. Entrepreneur Elon Musk is so bothered by what he calls this “bandwidth problem,” in fact, that one of his long-term goals is to create an interface that lets the human brain communicate directly with a computer, unencumbered by the slow speed of speaking or writing.

If Musk succeeded, he would probably be disappointed. According to recent research by Zheng and Meister published in Neuron, human beings remember, make decisions and imagine things at a fixed, excruciatingly slow speed of about 10 bits per second. In contrast, human sensory systems gather data at about one billion bits per second. 

This biological paradox, highlighted in the new study, probably contributes to the false feeling that our mind can engage in seemingly infinite thoughts simultaneously—a phenomenon the researchers deem “the Musk illusion.”  

The Zheng and Meister astract: 

This article is about the neural conundrum behind the slowness of human behavior. The information throughput of a human being is about 10 bits/s   . In comparison, our sensory systems gather data at ∼1⁢0⁹ bits/s. The stark contrast between these numbers remains unexplained and touches on fundamental aspects of brain function: what neural substrate sets this speed limit on the pace of our existence? Why does the brain need billions of neurons to process 10 bits/s? Why can we only think about one thing at a time? The brain seems to operate in two distinct modes: the “outer” brain handles fast high-dimensional sensory and motor signals, whereas the “inner” brain processes the reduced few bits needed to control behavior. Plausible explanations exist for the large neuron numbers in the outer brain, but not for the inner brain, and we propose new research directions to remedy this. 

How complex brains and cognition first arose

I have received a draft of an upcoming paper in Behavioral and Brain Sciences by Coombs and Trestman titled "A Multi-Trait Embodied Framework for the Evolution of Brains and Cognition across Animal Phyla "  It has a nice graphic indicating different brain regions whose functionalities are common to humans and phylogenetically different animals with complex brains  (crows, octopuses and honeybees).  Motivated readers can obtain a PDF of the article from me.  Here is the abstract :

Among non-human animals, crows, octopuses and honeybees are well-known for their complex brains and cognitive abilities. Widening the lens from the idiosyncratic abilities of exemplars like these to those of animals across the phylogenetic spectrum begins to reveal the ancient evolutionary process by which complex brains and cognition first arose in different lineages. The distribution of 35 phenotypic traits in 17 metazoan lineages reveals that brain and cognitive complexity in only three lineages (vertebrates, cephalopod mollusks, and euarthropods) can be attributed to the pivotal role played by body, sensory, brain and motor traits in active visual sensing and visuomotor skills. Together, these pivotal traits enabled animals to transition from largely reactive to more proactive behaviors, and from slow and two-dimensional motion to more rapid and complex three-dimensional motion. Among pivotal traits, high-resolution eyes and laminated visual regions of the brain stand out because they increased the processing demands on and the computational power of the brain by several orders of magnitude. The independent acquisition of pivotal traits in cognitively complex (CC) lineages can be explained as the completion of several multi-trait transitions over the course of evolutionary history, each resulting in an increasing level of complexity that arises from a distinct combination of traits. Whereas combined pivotal traits represent the highest level of complexity in CC lineages, combined traits at lower levels characterize many non-CC lineages, suggesting that certain body, sensory and brain traits may have been linked (the trait-linkage hypothesis) during the evolution of both CC and non-CC lineages.

Everything we experience comes from inside

I pass on this cryptic paragraph from my personal journal:

Everything we experience is coming from inside us - our illusion of having a self, our sense of agency. This includes attributing causal agency to others, as in  'they are making me do this,’  This 'error' allows individuals in a kinship group or tribe who share the same error to form an imaginary 'we' hive mind supporting unified action. The higher metacognitive stance is to participate when necessary in the group illusion while maintaining clarity on the fact that the actual agency is within oneself.

 

Predictive coding for social perception

Rittershofer et al. introduce a special issue of Neuroscience and Biobehavioral Reviews titled "Neurobiology of Social Interactions Across Species."  Here is the first part of that introduction:

Perception cannot rely solely on bottom-up processes, whereby patterns of receptor stimulation are passed up the hierarchy to generate a corresponding awareness. Such bottom-up processes would always generate experiences that are out-of-date and saturated by noise. Predictive processes are thought to play a key role in overcoming these problems, allowing us to generate best guesses concerning the likely sensorium, and highlighting quickly when the world is not as we expect. Action provides a crucial predictive source and a mechanism for us to resolve uncertainty and surprise, but further complicates our understanding due to further predictive cues and continuous change of sensory input. Another agent who can also change the world and who we seek to understand adds another layer of complexity yet. How can we understand the predictive mechanisms supporting social interaction and understanding, with such a multitude of moving and interacting components? In this special issue, Keysers et al. (2024) outline how predictive coding can be applied to understanding the actions and emotions of others, with Mayo and Shamay-Tsoory (2024) discussing how these mutual predictions might shape social learning. They suggest that such social learning might be supported by interbrain synchronization and Antonelli et al. (2024) discuss the critical role of emotion in shaping these multibrain dynamics.

 

While it is clearly crucial that we understand the nature of the mechanisms underlying social interactions, we wish to highlight the challenges of this complexity for scientific progress. Particularly, how to find ways to properly test, refute, and improve our models, when the assumed supporting mechanisms are so complex.

 

How predictions shape neural processing is thought to differ across space and time, even for processing of the simplest (non-social; static) elements of our environment. Keysers et al. (2024) highlight the assumed neural interactions across cortical layers, such that predictions are passed down the hierarchy to hypothesis units in deep (and perhaps superficial) cortical layers, input arrives in middle layers, and error signals are calculated and represented in superficial layers. This idea is supported by recent 7 T MRI work from our lab demonstrating increased decoding of predicted Gabor orientations in deep layers of primary visual cortex, with an advantage for unpredicted orientations in superficial layers (Thomas et al., 2024). Recent evidence suggests opposing influences at the temporal level as well (McDermott et al., 2024). This electroencephalography (EEG) study found that early perceptual processing is biased towards what we expect (< 200 ms; optimizing veridicality) with the advantage flipping in later timeranges (> 200 ms; optimizing informativeness – in line with the opposing process account proposed in Press et al., 2020). Building testable mechanistic accounts of these interactions across time and space – even for the simple perception of deterministic sequences of Gabor patches – represents a continued puzzle for future work.

 

In the social domain, the stimuli are by their nature highly complex and dynamic (Keysers et al., 2024). Therefore, these above interactions across space and time must be continuously updated. Despite this complexity, there is some evidence cited by Keysers et al. (2024) inline with the above laminar conclusions in simpler environments. Specifically, there is increased deep-layer information about observed actions in parietal cortex when presented in a predictable order, mediated via feedback connections (from premotor cortex). Social domains also yield multiple sources of prediction about the self and other (Mayo and Shamay-Tsoory, 2024) and we must determine how we weight the precision, or reliability, of these different sources, as well as how we render information about the self and other separable. Is this achieved by different cell populations coding information about the self and other (Mayo and Shamay-Tsoory, 2024)? Or could mechanisms similar to those proposed to distinguish products of imagination from reality (similarly internal vs external sources), also help in determining the information source in social situations?

 

Social predictions might be supported by interbrain synchronization (measured via hyperscanning), as discussed by Mayo and Shamay-Tsoory (2024); focus on social learning) and Antonelli et al. (2024); focus on emotion). We propose that one key challenge for this approach is determining the role played by different event-related inputs and responses in the effects: Interpretation of hyperscanning data is plagued by the problem that brains will be “in synch” if two individuals are either perceiving the same events or producing the same behaviour. The brain’s responses to moving our arm or looking at a face are remarkably similar across individuals, such that if two of us perceive or produce the same event our neural response will be matched. Fluctuations in synchronisation according to, e.g., dominance of individuals or levels of excitement on stage, could be determined by fluctuations in whether we attend to, or produce, the same events. It is crucial to understand the fascinating influence of these effects on synchronisation.

 

 

An AI framework for neural–behavioral modeling

Work of Sani et al. (open access) is reported in the Oct. 2024 issue of Nature Neuroscience. From the editor's summary:

Neural dynamics are complex and simultaneously relate to distinct behaviors. To address these challenges, Sani et al. have developed an AI framework termed DPAD that achieves nonlinear dynamical modeling of neural–behavioral data, dissociates behaviorally relevant neural dynamics, and localizes the source of nonlinearity in the dynamical model. What DPAD does is visualized as separating the overall brain activity into distinct pieces related to specific behaviors and discovering how these pieces fit together to build the overall activity.

Here is the Sani et al. abstract:

Understanding the dynamical transformation of neural activity to behavior requires new capabilities to nonlinearly model, dissociate and prioritize behaviorally relevant neural dynamics and test hypotheses about the origin of nonlinearity. We present dissociative prioritized analysis of dynamics (DPAD), a nonlinear dynamical modeling approach that enables these capabilities with a multisection neural network architecture and training approach. Analyzing cortical spiking and local field potential activity across four movement tasks, we demonstrate five use-cases. DPAD enabled more accurate neural–behavioral prediction. It identified nonlinear dynamical transformations of local field potentials that were more behavior predictive than traditional power features. Further, DPAD achieved behavior-predictive nonlinear neural dimensionality reduction. It enabled hypothesis testing regarding nonlinearities in neural–behavioral transformation, revealing that, in our datasets, nonlinearities could largely be isolated to the mapping from latent cortical dynamics to behavior. Finally, DPAD extended across continuous, intermittently sampled and categorical behaviors. DPAD provides a powerful tool for nonlinear dynamical modeling and investigation of neural–behavioral data.

Battle of the Bots - AI gets creative with Brain Hacks

This post is meant to archive my recent exercise of asking  ChatGPT 4o, Perplexity, Gemini+ advanced,  and Anthropic  (which does not offer links to its responses) to expand my  MindBlog's Brain Hacks post into a more complete essay that offers more background and context.  They responded with slightly different styles and impressive results that required tweaking for only a few small errors.  I thought my more concise text was more inviting, and didn't see anything really new, so my next prompt  (which I had asked ChatGPT to edit and improve) said:

"Your responses are well-constructed, but I’m seeking a deeper layer of insight—something that might challenge conventional perspectives or unveil an overlooked nuance. Can you reframe these ideas or introduce a novel approach that stretches beyond familiar interpretations??"

Here things got interesting.  Click the links above and scroll down to the responses to this final prompt to see the results.  The links most likely are maintained as long as I maintain paying accounts to the bots. (Anthropic does not offer links to its exchanges.)

I pass on here what I think is the most original and striking response, from perplexity. It was right on target,  brimming with new perspectives (some of them the subject of previous posts on my MindBlog), and links to a treasure trove of articles and ideas I was not familiar with from seven sources it provided links to.   Its response also provided a potpourri  or more or less relevant graphic images of brains and models.  

Here is the perplexities text, with links to a few of the seven sources it cites, all of which you can obtain directly from perplexity.:

Reframing our understanding of introspective awareness and cognitive modulation requires us to challenge some fundamental assumptions about the nature of consciousness and self-regulation. Let's explore a more provocative perspective that integrates recent neuroscientific findings with evolutionary theory and cognitive science.

The Illusion of Conscious Control

Contrary to the intuitive notion that our conscious mind is the primary driver of behavior and emotion regulation, emerging evidence suggests that consciousness might be more of an observer than a controller. The brain's emotional and regulatory processes often occur before we become consciously aware of them, suggesting that our sense of volitional control might be, to some extent, an illusion.

Consider the possibility that what we perceive as "introspective awareness" is actually a post-hoc narrative constructed by our brain to make sense of unconscious processes. This perspective challenges the traditional view of top-down emotion regulation and suggests a more complex interplay between conscious and unconscious processes.

The Social Evolution of Consciousness

Recent theories propose that human consciousness evolved primarily for social survival rather than individual cognitive enhancement [ref]. This social evolutionary framework suggests that subjective awareness might lack independent causal influence over psychological processes or actions. Instead, it may serve as a communication tool for social interaction and collective decision-making.

This perspective reframes our understanding of self-awareness and emotion regulation. Rather than viewing these abilities as individual cognitive skills, we might consider them as evolved social tools that facilitate group cohesion and cooperation. The ability to regulate emotions, in this context, becomes less about personal control and more about social signaling and coordination.

Neurotransmitter Systems and Emotion Regulation

Recent research has begun to map the overlap between emotion regulation brain networks and specific neurotransmitter systems [ref] [ref]. This approach offers a novel way to understand the biochemical basis of self-regulation. Instead of focusing solely on cognitive strategies or neural networks, we might conceptualize emotion regulation as a dynamic interplay between neurotransmitter systems.

This biochemical perspective opens up new avenues for
understanding individual differences in emotion regulation abilities. It suggests that what we perceive as "willpower" or "self-control" might be more accurately described as the efficient functioning of specific neurotransmitter systems.

The Myth of the Unified Self

Traditional models of self-awareness and emotion regulation often assume a unified, coherent self that observes and controls mental processes. However, neuroscientific evidence increasingly points to a more fragmented view of consciousness and self-hood.

Instead of a single, unified self, we might conceptualize the mind as a coalition of semi-independent processes, each with its own goals and methods of regulation. This "multiple selves" model challenges our intuitive understanding of self-awareness and suggests that emotion regulation might be more about negotiation between different aspects of our psyche than about top-down control.

Conclusion: Towards a New Paradigm

By integrating these perspectives, we can envision a new paradigm for understanding introspective awareness and cognitive modulation. This model would:

1. Recognize the limited role of conscious volition in emotion regulation
2. Emphasize the social and communicative functions of self-awareness
3. Incorporate the biochemical basis of regulatory processes
4. Embrace a more fragmented view of consciousness and selfhood

This approach challenges us to rethink fundamental concepts like free will, personal responsibility, and the nature of the self. It suggests that effective emotion regulation might be less about strengthening willpower and more about understanding and working with the complex, often unconscious processes that shape our emotional lives. By adopting this more nuanced and provocative perspective, we open up new avenues for research and potentially more effective interventions for emotional and cognitive well-being.

MindBlog's Brain Hacks

Introspective awareness and modulation of both ancient and more recently evolved aspects of our cognition:

Brain Hack #1
-The reptilian brain (whose modern descendant is found in the mammalian hypothalamus) generates affective states along axes of arousal and valence, whose states in higher primates can be assessed by introspective awareness.

Brain Hack #2
-The early mammalian emotional brain, whose ability to model a self (correlating with the appearance of the agranular prefrontal cortex), develops the ability to distinguish the difference between being (immersed in) an affective state and seeing (observing) it.

Brain Hack #3
-The appearance in the primate brain of the further ability to imagine the minds of others (correlating with appearance of the granular prefrontal cortex), permits appropriate assignments of agency, being able to distinguish one’s own experience (and problems) from the experience (and problems) of others.

The introspection that enables this ensemble of brain hacks can be strengthened by practice of three fundamental meditation techniques: focused awareness (in which our brain’s attentional mode predominates), open awareness (engaging our default mode network), and non-dual awareness (during which both are muted).  

*************
The above is an early draft text that I will be editing further (like my “Tokens of Sanity” post which has had at least six revisions since it 9/29/2024 posting).  It is trying to meld together and condense threads from my last public lecture and Max Bennett's recent book "A Brief History of Intelligence."  Feedback and comment welcome.

Tokens of sanity

-Being a calm space in which nothing can hurry

-An animal body that pretends to be human

-Dissociating from the word cloud and emotional reactivities of self and other selves.

-A courteous guest in one’s own body and when with others, owning one’s own experience and letting others own theirs.

-Favoring reflectivity over reactivity, caressing novelty

-Clinging to nothing, the current self being a passing fantasy

-Letting each moment be what it is, not what it should be

-A blip in the flow of cosmic time

The brain simulates actions and their consequences during REM sleep

During REM sleep our brains make up and work though simulated scenarios, while putting our bodies into paralysis so we don't thrash about dangerously....  Senzai and Scanziani show what in going on in mouse brains. Here is the first paragraph (abstract) of their open source text:

Vivid dreams mostly occur during a phase of sleep called REM1–5. During REM sleep, the brain’s internal representation of direction keeps shifting like that of an awake animal moving through its environment6–8. What causes these shifts, given the immobility of the sleeping animal? Here we show that the superior colliculus of the mouse, a motor command center involved in orienting movements9–15, issues motor commands during REM sleep, e.g. turn left, that are similar to those issued in the awake behaving animal. Strikingly, these motor commands, despite not being executed, shift the internal representation of direction as if the animal had turned. Thus, during REM sleep, the brain simulates actions by issuing motor commands that, while not executed, have consequences as if they had been. This study suggests that the sleeping brain, while disengaged from the external world, uses its internal model of the world to simulate interactions with it.

From nematodes to humans a common brain network motif intertwines hierarchy and modularity.

Pathak et al. (abstract below) suggest the evolved pattern they describe may apply to information processing networks in general, in particular to those of evolving AI implementations.

Significance

Nervous systems are often schematically represented in terms of hierarchically arranged layers with stimuli in the “input” layer sequentially transformed through successive layers, eventually giving rise to response in the “output” layer. Empirical investigations of hierarchy in specific brain regions, e.g., the visual cortex, typically employ detailed anatomical information. However, a general method for identifying the underlying hierarchy from the connectome alone has so far been elusive. By proposing an optimized index that quantifies the hierarchy extant in a network, we reveal an architectural motif underlying the mesoscopic organization of nervous systems across different species. It involves both modular partitioning and hierarchical layered arrangement, suggesting that brains employ an optimal mix of parallel (modular) and sequential (hierarchic) information processing.

Abstract

Networks involved in information processing often have their nodes arranged hierarchically, with the majority of connections occurring in adjacent levels. However, despite being an intuitively appealing concept, the hierarchical organization of large networks, such as those in the brain, is difficult to identify, especially in absence of additional information beyond that provided by the connectome. In this paper, we propose a framework to uncover the hierarchical structure of a given network, that identifies the nodes occupying each level as well as the sequential order of the levels. It involves optimizing a metric that we use to quantify the extent of hierarchy present in a network. Applying this measure to various brain networks, ranging from the nervous system of the nematode Caenorhabditis elegans to the human connectome, we unexpectedly find that they exhibit a common network architectural motif intertwining hierarchy and modularity. This suggests that brain networks may have evolved to simultaneously exploit the functional advantages of these two types of organizations, viz., relatively independent modules performing distributed processing in parallel and a hierarchical structure that allows sequential pooling of these multiple processing streams. An intriguing possibility is that this property we report may be common to information processing networks in general.

The ebb and flow of physical and cognitive fatigue

Matthews et al. Have investigated moment-to-moment fluctuations in fatigue using behavioral experiments and computational modeling to offer a precise account of how fatigue waxes (during physical and cognitive effort) and wanes (during rest).   From Bijleveld's review of the work:

A key insight from this work is that there are important parallels between physical and cognitive fatigue. Specifically, for both types of fatigue, the best-fitting computational model parsed fatigue into two components: a recoverable component (i.e., the share of fatigue that increases with effort and recovers with rest) and an unrecoverable component (i.e., the share of fatigue that only increases with effort and does not recover with rest, at least not within the ~1-h session). For physical fatigue, this result conceptually replicates a previous study; for cognitive fatigue, this result is new and original. Together, these findings paint a nuanced picture of how both physical and cognitive fatigue emerge over time. From an applied angle, the distinction between recoverable and unrecoverable fatigue is intriguing: it has potential implications for task design, such as in the contexts of education and work...On balance, physical and cognitive fatigue may be more similar than they are different.

Here is the Maltthews et al. abstract:

The willingness to exert effort for reward is essential but comes at the cost of fatigue. Theories suggest fatigue increases after both physical and cognitive exertion, subsequently reducing the motivation to exert effort. Yet a mechanistic understanding of how this happens on a moment-to-moment basis, and whether mechanisms are common to both mental and physical effort, is lacking. In two studies, participants reported momentary (trial-by-trial) ratings of fatigue during an effort-based decision-making task requiring either physical (grip-force) or cognitive (mental arithmetic) effort. Using a novel computational model, we show that fatigue fluctuates from trial-to-trial as a function of exerted effort and predicts subsequent choices. This mechanism was shared across the domains. Selective to the cognitive domain, committing errors also induced momentary increases in feelings of fatigue. These findings provide insight into the computations underlying the influence of effortful exertion on fatigue and motivation, in both physical and cognitive domains.

 

 

Architectural experience influences the processing of others’ body expressions

An open source article by Presti et al:  

Significance

The motor system has been recognized as a fundamental neural machinery for spatial and social cognition, making the study of the interplay between architecture and social behavior worthwhile. Here, we tested how a virtual architectural experience alters the subsequent processing of body expressions, showing that the motor system participates at two distinct stages: the earliest influenced by the dynamic architectural experience and the latter modulated by the actual physical characteristics. These findings highlight the existence of an overlapping motor neural substrate devoted to spatial and social cognition, with the architectural space exerting an early and possibly adapting effect on the later social experience. Ultimately, spatial design may impact the processing of human emotions.

Abstract

The interplay between space and cognition is a crucial issue in Neuroscience leading to the development of multiple research fields. However, the relationship between architectural space and the movement of the inhabitants and their interactions has been too often neglected, failing to provide a unifying view of architecture's capacity to modulate social cognition broadly. We bridge this gap by requesting participants to judge avatars’ emotional expression (high vs. low arousal) at the end of their promenade inside high- or low-arousing architectures. Stimuli were presented in virtual reality to ensure a dynamic, naturalistic experience. High-density electroencephalography (EEG) was recorded to assess the neural responses to the avatar’s presentation. Observing highly aroused avatars increased Late Positive Potentials (LPP), in line with previous evidence. Strikingly, 250 ms before the occurrence of the LPP, P200 amplitude increased due to the experience of low-arousing architectures, reflecting an early greater attention during the processing of body expressions. In addition, participants stared longer at the avatar’s head and judged the observed posture as more arousing. Source localization highlighted a contribution of the dorsal premotor cortex to both P200 and LPP. In conclusion, the immersive and dynamic architectural experience modulates human social cognition. In addition, the motor system plays a role in processing architecture and body expressions suggesting that the space and social cognition interplay is rooted in overlapping neural substrates. This study demonstrates that the manipulation of mere architectural space is sufficient to influence human social cognition.

What your brain is doing after the light turns green.

 Gandhi and collaboratores show that if you step out to cross the street without looking right or left the neural activity in the brain is different than if you look from side to side first to be sure no cars are coming. Population level analysis of movement-related transient activity patterns in a population of superior colliculus neurons change in the two different contexts, and this difference is not readily identifiable in single-unit recordings.  Here is their technical abstract:

Sensorimotor transformation is the process of first sensing an object in the environment and then producing a movement in response to that stimulus. For visually guided saccades, neurons in the superior colliculus (SC) emit a burst of spikes to register the appearance of stimulus, and many of the same neurons discharge another burst to initiate the eye movement. We investigated whether the neural signatures of sensation and action in SC depend on context. Spiking activity along the dorsoventral axis was recorded with a laminar probe as Rhesus monkeys generated saccades to the same stimulus location in tasks that require either executive control to delay saccade onset until permission is granted or the production of an immediate response to a target whose onset is predictable. Using dimensionality reduction and discriminability methods, we show that the subspaces occupied during the visual and motor epochs were both distinct within each task and differentiable across tasks. Single-unit analyses, in contrast, show that the movement-related activity of SC neurons was not different between tasks. These results demonstrate that statistical features in neural activity of simultaneously recorded ensembles provide more insight than single neurons. They also indicate that cognitive processes associated with task requirements are multiplexed in SC population activity during both sensation and action and that downstream structures could use this activity to extract context. Additionally, the entire manifolds associated with sensory and motor responses, respectively, may be larger than the subspaces explored within a certain set of experiments.

Emergent analogical reasoning in large language models

Things are moving very fast in AI development. From Webb et al:

The recent advent of large language models has reinvigorated debate over whether human cognitive capacities might emerge in such generic models given sufficient training data. Of particular interest is the ability of these models to reason about novel problems zero-shot, without any direct training. In human cognition, this capacity is closely tied to an ability to reason by analogy. Here we performed a direct comparison between human reasoners and a large language model (the text-davinci-003 variant of Generative Pre-trained Transformer (GPT)-3) on a range of analogical tasks, including a non-visual matrix reasoning task based on the rule structure of Raven’s Standard Progressive Matrices. We found that GPT-3 displayed a surprisingly strong capacity for abstract pattern induction, matching or even surpassing human capabilities in most settings; preliminary tests of GPT-4 indicated even better performance. Our results indicate that large language models such as GPT-3 have acquired an emergent ability to find zero-shot solutions to a broad range of analogy problems.

Chemistry that regulates whether we stay with what we're doing or try something new

Sidorenko et al. demonstrate that stimulating the brain's cholinergic and noradrenergic systems enhances optimal foraging behaviors in humans. Their significance statement and abstract:  

Significance

Deciding when to say “stop” to the ongoing course of action is paramount for preserving mental health, ensuring the well-being of oneself and others, and managing resources in a sustainable fashion. And yet, cross-species studies converge in their portrayal of real-world decision-makers who are prone to the overstaying bias. We investigated whether and how cognitive enhancers can reduce this bias in a foraging context. We report that the pharmacological upregulation of cholinergic and noradrenergic systems enhances optimality in a common dilemma—staying with the status quo or leaving for more rewarding alternatives—and thereby suggest that acetylcholine and noradrenaline causally mediate foraging behavior in humans.

Abstract

Foraging theory prescribes when optimal foragers should leave the current option for more rewarding alternatives. Actual foragers often exploit options longer than prescribed by the theory, but it is unclear how this foraging suboptimality arises. We investigated whether the upregulation of cholinergic, noradrenergic, and dopaminergic systems increases foraging optimality. In a double-blind, between-subject design, participants (N = 160) received placebo, the nicotinic acetylcholine receptor agonist nicotine, a noradrenaline reuptake inhibitor reboxetine, or a preferential dopamine reuptake inhibitor methylphenidate, and played the role of a farmer who collected milk from patches with different yield. Across all groups, participants on average overharvested. While methylphenidate had no effects on this bias, nicotine, and to some extent also reboxetine, significantly reduced deviation from foraging optimality, which resulted in better performance compared to placebo. Concurring with amplified goal-directedness and excluding heuristic explanations, nicotine independently also improved trial initiation and time perception. Our findings elucidate the neurochemical basis of behavioral flexibility and decision optimality and open unique perspectives on psychiatric disorders affecting these functions.

A shared novelty-seeking basis for creativity and curiosity

I pass on the abstract of a target article having the title of this post, sent to me by Behavioral and Brain Science. I'm reading through it, and would be willing to send a PDF of the article to motivated MindBlog readers who wish to check it out.

Curiosity and creativity are central pillars of human growth and invention. While they have been studied extensively in isolation, the relationship between them has not yet been established. We propose that curiosity and creativity both emanate from the same mechanism of novelty-seeking. We first present a synthesis showing that curiosity and creativity are affected similarly by a number of key cognitive faculties such as memory, cognitive control, attention, and reward. We then review empirical evidence from neuroscience research, indicating that the same brain regions are involved in both curiosity and creativity, focusing on the interplay between three major brain networks: the default-mode network, the salience network, and the executive control network. After substantiating the link between curiosity and creativity, we propose a novelty- seeking model (NSM) that underlies them both and suggest that the manifestation of the NSM is governed by one’s state of mind (SoM).

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.

Turing, von Neumann, and the computational architecture of biological machines

I pass on the abstract of a PNAS perspective article by Hashim M. Al-Hashimi (motivated readers can obtain a PDF of the article from me).

In the mid-1930s, the English mathematician and logician Alan Turing invented an imaginary machine which could emulate the process of manipulating finite symbolic configurations by human computers. His machine launched the field of computer science and provided a foundation for the modern-day programmable computer. A decade later, building on Turing’s machine, the American–Hungarian mathematician John von Neumann invented an imaginary self-reproducing machine capable of open-ended evolution. Through his machine, von Neumann answered one of the deepest questions in Biology: Why is it that all living organisms carry a self-description in the form of DNA? The story behind how two pioneers of computer science stumbled on the secret of life many years before the discovery of the DNA double helix is not well known, not even to biologists, and you will not find it in biology textbooks. Yet, the story is just as relevant today as it was eighty years ago: Turing and von Neumann left a blueprint for studying biological systems as if they were computing machines. This approach may hold the key to answering many remaining questions in Biology and could even lead to advances in computer science.

People who talk too much

I host a monthly discussion group in Austin TX, The Austin Rainbow Forum, that meets at 2 pm on the first Sunday of every month to consider interesting topics and ideas. On this past May 7, one of our group members led a discussion of "Overtalking" in the modern world, which has got us all spouting opinions, giving advice, and getting ourselves in trouble, according to Dan Lyons in his recent book titled "STFU: The Power of Keeping Your Mouth Shut in an Endlessly Noisy World."  The central ideas in Lyons’ book are summarized in this Time Magazine article. I looked through a reviewers copy of the book I was sent, and suggest that it is worth having a look if you are stimulated by the summary article. The bottom line of the book could be stated as "Shut up and listen instead of talking so much." Lyons offers five nudges: 

-When possible, say nothing

-Master the power of the pause

-Quit social media

-Seek out silence

-Learn how to listen

Lyons is a professional columnist who writes with a very engaging style, even if the level of his coverage is sometimes a bit superficial.  (He quotes a researcher who studied brain activity and '“figured out what causes talkaholism,” ...unfortunately, on doing a quick look up of the work describing the neuronal measurements, I found that there is no there there.)

Virality

This post is the ninth and final installment of my passing on to both MindBlog readers and my future self my idiosyncratic selection of clips of text from O’Gieblyn’s book ‘God, Human, Animal, Machine’ that I have found particularly interesting. Here are fragments of Chapter 13 from the  seventh section of her book, titled "Virality"

The most successful metaphors become invisible through ubiquity. The same is true of ideology, which, as it becomes thoroughly integrated into a culture, sheds its contours and distinctive outline and dissolves finally into pure atmosphere. Although digital technology constitutes the basic architecture of the information age, it is rarely spoken of as a system of thought. Its inability to hold ideas or beliefs, preferences or opinions, is often misunderstood as an absence of philosophy rather than a description of its tenets. The central pillar of this ideology is its conception of being, which might be described as an ontology of vacancy—a great emptying-out of qualities, content, and meaning. This ontology feeds into its epistemology, which holds that knowledge lies not in concepts themselves but in the relationships that constitute them, which can be discovered by artificial networks that lack any true knowledge of what they are uncovering. And as global networks have come to encompass more and more of our  human relations, it’s become increasingly difficult to speak of ourselves—the nodes of this enormous brain—as living agents with beliefs, preferences, and opinions.

The term “viral media” was coined in 1994 by the critic Douglas Rushkoff, who argued that the internet had become “an extension of a living organism” that spanned the globe and radically accelerated the way ideas and culture spread. The notion that the laws of the biosphere could apply to the datasphere was already by that point taken for granted, thanks to the theory of memes, a term Richard Dawkins devised to show that ideas and cultural phenomena spread across a population in much the same way genes do. iPods are memes, as are poodle skirts, communism, and the Protestant Reformation. The main benefit of this metaphor was its ability to explain how artifacts and ideologies reproduce themselves without the participation of conscious subjects. Just as viruses infect hosts without their knowledge or consent, so memes have a single “goal,” self-preservation and spread, which they achieve by latching on to a host and hijacking its reproductive machinery for their own ends. That this entirely passive conception of human culture necessitates the awkward reassignment of agency to the ideas themselves—imagining that memes have “goals” and “ends”—is usually explained away as a figure of speech.

When Rushkoff began writing about “viral media,” the internet was still in the midst of its buoyant overture, and he believed, as many did at the time, that this highly networked world would benefit “people who lack traditional political power.” A system that has no knowledge of a host’s identity or status should, in theory, be radically democratic. It should, in theory, level existing hierarchies and create an even playing field, allowing the most potent ideas to flourish, just as the most successful genes do under the indifferent gaze of nature. By 2019, however, Rushkoff had grown pessimistic. The blind logic of the network was, it turned out, not as blind as it appeared—or rather, it could be manipulated by those who already had enormous resources. “Today, the bottom-up techniques of guerrilla media activists are in the hands of the world’s wealthiest corporations, politicians, and propagandists,” Rushkoff writes in his book Team Human. What’s more, it turns out that the blindness of the system does not ensure its judiciousness. Within the highly competitive media landscape, the metrics of success have become purely quantitative—page views, clicks, shares—and so the potential for spread is often privileged over the virtue or validity of the content. “It doesn’t matter what side of an issue people are on for them to be affected by the meme and provoked to replicate it,” Rushkoff writes. In fact the most successful memes don’t appeal to our intellect at all. Just as the proliferation of a novel virus depends on bodies that have not yet developed an effective immune response, so the most effective memes are those that bypass the gatekeeping rational mind and instead trigger “our most automatic impulses.” This logic is built into the algorithms of social media, which replicate content that garners the most extreme reactions and which foster, when combined with the equally blind and relentless dictates of a free market, what one journalist has called “global, real-time contests for attention.”
            
The general public has become preoccupied by robots—or rather “bots,” the diminutive, a term that appears almost uniformly in the plural, calling to mind a swarm or infestation, a virus in its own right, though in most cases they are merely the means of transmission. It should not have come as a surprise that a system in which ideas are believed to multiply according to their own logic, by pursuing their own ends, would come to privilege hosts that are not conscious at all. There had been suspicions since the start of the pandemic about the speed and efficiency with which national discourse was hijacked by all manner of hearsay, conspiracy, and subterfuge.

The problem is not merely that public opinion is being shaped by robots. It’s that it has become impossible to decipher between ideas that represent a legitimate political will and those that are being mindlessly propagated by machines. This uncertainty creates an epistemological gap that renders the assignment of culpability nearly impossible and makes it all too easy to forget that these ideas are being espoused and proliferated by members of our democratic system—a problem that is far more deep-rooted and entrenched and for which there are no quick and easy solutions. Rather than contending with this fact, there is instead a growing consensus that the platforms themselves are to blame, though no one can settle on precisely where the problem lies: The algorithms? The structure? The lack of censorship and intervention? Hate speech is often spoken of as though it were a coding error—a “content-moderation nightmare,” an “industry-wide problem,” as various platform executives have described it, one that must be addressed through “different technical changes,” most of which are designed to appease advertisers. Such conversations merely strengthen the conviction that the collective underbelly of extremists, foreign agents, trolls, and robots is an emergent feature of the system itself, a phantasm arising mysteriously from the code, like Grendel awakening out of the swamp.

Donald Trump himself, a man whose rise to power may or may not have been aided by machines, is often included in this digital phantasm, one more emergent property of the network’s baffling complexity…Robert A. Burton, a prominent neurologist, claimed in an article that the president made sense once you stopped viewing him as a human being and began to see him as “a rudimentary artificial intelligence-based learning machine.” Like deep-learning systems, Trump was working blindly through trial and error, keeping a record of what moves worked in the past and using them to optimize his strategy, much like AlphaGo, the AI system that swept the Go championship in Seoul. The reason that we found him so baffling was that we continually tried to anthropomorphize him, attributing intention and ideology to his decisions, as though they stemmed from a coherent agenda. AI systems are so wildly successful because they aren’t burdened with any of these rational or moral concerns—they don’t have to think about what is socially acceptable or take into account downstream consequences. They have one goal—winning—and this rigorous single-minded interest is consistently updated through positive feedback. Burton’s advice to historians and policy wonks was to regard Trump as a black box. “As there are no lines of reasoning driving the network’s actions,” he wrote, “it is not possible to reverse engineer the network to reveal the ‘why’ of any decision.”

If we resign ourselves to the fact that our machines will inevitably succeed us in power and intelligence, they will surely come to regard us this way, as something insensate and vaguely revolting, a glitch in the operation of their machinery. That we have already begun to speak of ourselves in such terms is implicit in phrases like “human error,” a phrase that is defined, variously, as an error that is typical of humans rather than machines and as an outcome not desired by a set of rules or an external observer. We are indeed the virus, the ghost in the machine, the bug slowing down a system that would function better, in practically every sense, without us.

If Blumenberg is correct in his account of disenchantment, the scientific revolution was itself a leap of faith, an assertion that the ill-conceived God could no longer guarantee our worth as a species, that our earthly frame of reference was the only valid one. Blumenberg believed that the crisis of nominalism was not a one-time occurrence but rather one of many “phases of objectivization that loose themselves from their original motivation.” The tendency to privilege some higher order over human interests had emerged throughout history—before Ockham and the Protestant reformers it had appeared in the philosophy of the Epicureans, who believed that there was no correspondence between God and earthly life. And he believed it was happening once again in the technologies of the twentieth century, as the quest for knowledge loosened itself from its humanistic origins. It was at such moments that it became necessary to clarify the purpose of science and technology, so as to “bring them back into their human function, to subject them again to man’s purposes in relation to the world.” …Arendt hoped that in the future we would develop an outlook that was more “geocentric and anthropomorphic.”  She advocated a philosophy that took as its starting point the brute fact of our mortality and accepted that the earth, which we were actively destroying and trying to escape, was our only possible home.”