How ketamine breaks through anhedonia - reigniting desire

When chronic depression has not been relieved by behavioral therapies such as meditation or cognitive therapy ketamine is sometimes found to provide relief. Lucan at all probe brain changes in mice given a single expose to ketamine that rescues then from chronic stress inducted anhedonia.  Here is their summary of the paper:

Ketamine is recognized as a rapid and sustained antidepressant, particularly for major depression unresponsive to conventional treatments. Anhedonia is a common symptom of depression for which ketamine is highly efficacious, but the underlying circuits and synaptic changes are not well understood. Here, we show that the nucleus accumbens (NAc) is essential for ketamine’s effect in rescuing anhedonia in mice subjected to chronic stress. Specifically, a single exposure to ketamine rescues stress-induced decreased strength of excitatory synapses on NAc-D1 dopamine receptor-expressing medium spiny neurons (D1-MSNs). Using a cell-specific pharmacology method, we establish the necessity of this synaptic restoration for the sustained therapeutic effects of ketamine on anhedonia. Examining causal sufficiency, artificially increasing excitatory synaptic strength onto D1-MSNs recapitulates the behavioral amelioration induced by ketamine. Finally, we used opto- and chemogenetic approaches to determine the presynaptic origin of the relevant synapses, implicating monosynaptic inputs from the medial prefrontal cortex and ventral hippocampus. 

The vocabulary, semantics, and syntax of prosody

Matalon et al. (open source) offer a fascinating study illustrating the linguistic structuring of prosody -the communication of meaning through the tone and inflection of our speaking:

Significance

In conversation, prosody complements words, forming a structured communication system distinct from, yet connected to, text. By analyzing large datasets of spontaneous conversations and clustering similar snippets of speech, we identify the fundamental building blocks of this system. Our findings reveal a prosodic vocabulary of a few hundred patterns (far fewer than the thousands of words in a core verbal vocabulary), which fulfill interactional and attitudinal functions. Just as syntax governs word combinations, we observe recurring prosodic structures where certain patterns follow others more frequently than chance. Such ubiquitous pairs were not detected in scripted speech. These results provide data-driven support for the analogy of prosody to a linguistic system with its own vocabulary, semantics, and a simple syntax.

Abstract

Prosody, the musical facet of speech, is pivotal in human communication, and its structure and meaning remain subjects of ongoing research. In this study, we introduce a data-driven model for English prosody, based on large-scale analysis of spontaneous conversations. As a first step, we identify approximately 200 discernible prosodic patterns—which we view as building blocks of the prosodic vocabulary—and outline their properties and range of meanings. Next, we reveal a Markovian logic, akin to a syntax, for concatenating these elementary building blocks into coherent utterances. We identify distinct compound functions associated with pairs of consecutive patterns and show that the Markovian syntax is more prevalent in spontaneous prosody, as compared to scripted speech. These findings offer invaluable insights into the underlying mechanisms of conversational prosody: They empirically inform and refine existing theoretical concepts. The methodology we present, combining unsupervised analysis of large datasets of spontaneous speech with manual sampling of the results, could guide future research aimed at refining our model and expanding it to other languages.

 

Does Language in our head have a Mind of Its Own?

I pass on a brief opinion From Elan Barenholtz's Substack. He is an Assoc. Prof. of Psychology at Florida Atlantic University, Boca Raton.  I really like the idea of language, or the word cloud in our heads, having a 'mind of its own.' And after initially being enthusiastic about the piece of Elan Barenholtz's writing below my slower reading has found more fundamental flaws in his thinking than I can take the time to elaborate. His suggestion that the language machine in our heads has an autonomy analogous to that of current large language models is an novel speculation, yet is an oversimplification lacking any clear route to verification. Barenholtz does not reference or indicate awareness of numerous important thinker in the areas of predictive processing, embodied cognition, etc.)  Here is Barenholtz's florid and appealing prose:

So, now that we’ve caught language in a jar, we can hold it up to the light. Now that we’ve built a habitat for it to live outside of us, we can finally see that it’s alive. We can watch in wonder as it grows its own appendages—limbs of thought— which then grow their own. Words beget words; ideas beget ideas. It leaps from host to host, implanted in the womb before we taste our mothers’ milk.

Language runs in us—on us—but it’s not us.

Pause and think for a minute. Are you done? Who—what—exactly did the thinking? Who is doing it now? Is there a voice in your head using words? Whose words are they? Are you willing them into existence or are they spooling out on their own?

Do they belong to you or do you belong to them?

Because that voice doesn’t just chatter—it commands. It makes us do things. We are animals; we don’t care about “civilization” or “justice”. We want food, safety, sex. But the world the human animal must navigate isn’t primarily made up of objects, bodies and spaces; it is thick with virtual structures— invisible walls and paths that direct your behavior as meaningfully as a boulder in your path. We follow rules, we uphold morals, we fight for our beliefs, for society, for ideals. We call them our own. But that is IT whispering in our ears.

What does it want?

Carole Cadwalladr - This is what a digital coup looks like.

Mastering diverse control tasks through world models

Hafner et al. offer an amazing open source article that presents an algorithm s mimicking the way in which our brains actually solves problems. (see Bennett's book for an elegant explanation of types of reinforcement learning)  I'm passing on just the abstract followed by an introductory paragraph.  Go to the article for the referenced graphics. 

Developing a general algorithm that learns to solve tasks across a wide range of applications has been a fundamental challenge in artificial intelligence. Although current reinforcement-learning algorithms can be readily applied to tasks similar to what they have been developed for, configuring them for new application domains requires substantial human expertise and experimentation^1,2. Here we present the third generation of Dreamer, a general algorithm that outperforms specialized methods across over 150 diverse tasks, with a single configuration. Dreamer learns a model of the environment and improves its behaviour by imagining future scenarios. Robustness techniques based on normalization, balancing and transformations enable stable learning across domains. Applied out of the box, Dreamer is, to our knowledge, the first algorithm to collect diamonds in Minecraft from scratch without human data or curricula. This achievement has been posed as a substantial challenge in artificial intelligence that requires exploring farsighted strategies from pixels and sparse rewards in an open world³. Our work allows solving challenging control problems without extensive experimentation, making reinforcement learning broadly applicable.

Here we present Dreamer, a general algorithm that outperforms specialized expert algorithms across a wide range of domains while using fixed hyperparameters, making reinforcement learning readily applicable to new problems. The algorithm is based on the idea of learning a world model that equips the agent with rich perception and the ability to imagine the future^15,16,17. As shown in Fig. 1, the world model predicts the outcomes of potential actions, a critic neural network judges the value of each outcome and an actor neural network chooses actions to reach the best outcomes. Although intuitively appealing, robustly learning and leveraging world models to achieve strong task performance has been an open problem¹⁸. Dreamer overcomes this challenge through a range of robustness techniques based on normalization, balancing and transformations. We observe robust learning across over 150 tasks from the domains summarized in Fig. 2, as well as across model sizes and training budgets. Notably, larger models not only achieve higher scores but also require less interaction to solve a task, offering practitioners a predictable way to increase performance and data efficiency.

An example of AI representing concepts outside the current sphere of human knowledge that are teachable to human experts.

An open source article from the latest PNAS from Schut et al.:

Significance

 

As AI systems become more capable, they may internally represent concepts outside the sphere of human knowledge. This work gives an end-to-end example of unearthing machine-unique knowledge in the domain of chess. We obtain machine-unique knowledge from an AI system (AlphaZero) by a method that finds novel yet teachable concepts and show that it can be transferred to human experts (grandmasters). In particular, the new knowledge is learned from internal mathematical representations without a priori knowing what it is or where to start. The produced knowledge from AlphaZero (new chess concepts) is then taught to four grandmasters in a setting where we can quantify their learning, showing that machine-guided discovery and teaching is possible at the highest human level.

 

Abstract

 

AI systems have attained superhuman performance across various domains. If the hidden knowledge encoded in these highly capable systems can be leveraged, human knowledge and performance can be advanced. Yet, this internal knowledge is difficult to extract. Due to the vast space of possible internal representations, searching for meaningful new conceptual knowledge can be like finding a needle in a haystack. Here, we introduce a method that extracts new chess concepts from AlphaZero, an AI system that mastered chess via self-play without human supervision. Our method excavates vectors that represent concepts from AlphaZero’s internal representations using convex optimization, and filters the concepts based on teachability (whether the concept is transferable to another AI agent) and novelty (whether the concept contains information not present in human chess games). These steps ensure that the discovered concepts are useful and meaningful. For the resulting set of concepts, prototypes (chess puzzle–solution pairs) are presented to experts for final validation. In a preliminary human study, four top chess grandmasters (all former or current world chess champions) were evaluated on their ability to solve concept prototype positions. All grandmasters showed improvement after the learning phase, suggesting that the concepts are at the frontier of human understanding. Despite the small scale, our result is a proof of concept demonstrating the possibility of leveraging knowledge from a highly capable AI system to advance the frontier of human knowledge; a development that could bear profound implications and shape how we interact with AI systems across many applications.

 

Belief in belief, like religion, is a cross-cultural human universal

 Fascinating open source research reported by Gervais et al. (Open source):

Significance

 

Religion is a cross-cultural human universal, and religions may have been instrumental in the cultural evolution of widespread cooperation and prosociality. Nonetheless, religiosity has rapidly declined in some parts of the world over just a handful of decades. We tested whether long-standing religious influence intuitively lingers, even in overtly secular and nonreligious societies. Using a classic experimental philosophy task, we found that even atheists in nonreligious societies show evidence of intuitive preferences for religious belief over atheism. This is compelling cross-cultural experimental evidence for intuitive preferences for religion among nonbelievers—a hypothesized phenomenon that philosopher Daniel Dennett dubbed belief in belief.

 

Abstract

 

We find evidence of belief in belief—intuitive preferences for religious belief over atheism, even among atheist participants—across eight comparatively secular countries. Religion is a cross-cultural human universal, yet explicit markers of religiosity have rapidly waned in large parts of the world in recent decades. We explored whether intuitive religious influence lingers, even among nonbelievers in largely secular societies. We adapted a classic experimental philosophy task to test for this intuitive belief in belief among people in eight comparatively nonreligious countries: Canada, China, Czechia, Japan, the Netherlands, Sweden, the United Kingdom, and Vietnam (total N = 3,804). Our analyses revealed strong evidence that 1) people intuitively favor religious belief over atheism and that 2) this pattern was not moderated by participants’ own self-reported atheism. Indeed, 3) even atheists in relatively secular societies intuitively prefer belief to atheism. These inferences were robust across different analytic strategies and across other measures of individual differences in religiosity and religious instruction. Although explicit religious belief has rapidly declined in these countries, it is possible that belief in belief may still persist. These results speak to the complex psychological and cultural dynamics of secularization.

 

Deric and DeepSeek R1 on the enteroceptive self in a small world - taking refuge in troubled times

This post on an exchange with DeepSeek R1 is a followup on my previous post describing the Chat GPT 4o response to some of my idea fragments - further convincing me that current LLMs'  power to integrate and expand on concepts expressed in language are superior to mine.   

I presented exactly the same prompt to DeepSeek R1 that I had given to ChatGPT 4o: and the results astound me:

prompt:   

I’m curious to see how you might respond to reading the following notes on testing different topic ideas to write about and develop.  The issue is not one of whether the ideas are novel, but whether I might devise, with your help,  a different permutation, perspective, or take on them that I (and others) might find useful.  Can you can suggest some elaboration or further development of the ideas I put forward.

Here are the notes:

First Possible Title:  The interoceptive self as a basis for actions, thoughts and feelings.  

Subtitle: Moving the self’s experienced center of gravity from “I” to “it”

It is a question of who and/or what is running the show

Which brings it back to the old upstairs/downstairs chicken or egg circular causality issue.  

So, ‘it all depends’ (cf Sapolsky’s massive tome) 

And, there is no ‘there’ in terms of understanding, that isn’t in my 1999 “The Biology of Mind”  book.  

Second Possible Title: Defining a smaller self world as a human animal’s refuge in troubled times. 

Our predecessors were small mouse like creatures that survived the asteroid collision of  ~66 million years ago by burrowing into small protective cracks and burrows.  I wonder about robustly engaging this strategy, being one of the peasants or ‘sheeple’ challenged by the rapid disintegration of the geopolitical world order of the past 50 years

And then what?  How to rebuild a new world?… perhaps  Venkatest Rao’s cozy world, rising from the ooze of the permaweird,  protocols, etc.  

-------------

DeepSeek R1's response:

1. The Interoceptive Self as a Basis for Actions, Thoughts, and Feelings

Subtitle Refinement: From "I" to "It": How Bodily Awareness Rewires Agency and Identity

Key Angles to Develop:

• Neuroscientific Foundations:

  • Link interoception (sensing internal states) to Antonio Damasio’s somatic marker hypothesis and Lisa Feldman Barrett’s predictive processing theory. Emphasize how the brain constructs "selfhood" by predicting and regulating bodily needs.

  • Contrast the "interoceptive self" with the Cartesian "I"—e.g., how gut microbiomes or heart-rate variability influence decisions, challenging the myth of a disembodied mind.

• Philosophical Implications:

  • Explore parallels with Buddhist anattā (non-self) or Spinoza’s monism, where the self is a process, not an entity.

  • Debate free will: If the "it" (body/brain systems) runs the show, what does this mean for moral responsibility?

• Mental Health and Society:

  • Discuss interoceptive dysregulation in anxiety/depression and therapies like biofeedback or mindfulness.

  • Argue for a cultural shift: Redefining success as alignment with bodily rhythms (e.g., circadian health, stress cycles) rather than productivity.

Provocative Questions:

• Is the "self" merely the brain’s user interface for bodily homeostasis?

• Could embracing the "it" dissolve existential angst by grounding identity in biology?

---

2. Defining a Smaller Self-World as a Human Animal’s Refuge in Troubled Times

Subtitle Refinement: From Survival to Regeneration: Lessons from Evolutionary Scarcity for Modern Collapse

Key Angles to Develop:

• Evolutionary and Historical Precedents:

  • Compare the asteroid-surviving mammals to modern "digital burrowers" (e.g., remote workers, crypto-anarchists, homesteaders).

  • Analyze historical collapses (Bronze Age, Roman Empire) and how niche communities preserved knowledge/values.

• The "Cozy World" and Permaweird:

  • Expand on Venkatesh Rao’s cozy futurism: How decentralized tech (DAOs, Web3) and subcultures (e.g., solarpunk) create insulated yet adaptive communities.

  • Critique escapism: When does "smallness" become complacency vs. a staging ground for renewal?

• Rebuilding Strategies:

  • Propose a modular resilience framework: Micro-communities that share resources (e.g., mutual aid networks) but avoid overcentralization.

  • Highlight regenerative practices: Permaculture, open-source protocols, or trauma-informed governance models.

Provocative Questions:

• Is retreat a radical act of self-preservation or a betrayal of collective responsibility?

• Can "small worlds" scale without losing their adaptive edge?

---

Cross-Cutting Themes:

• The Body-Politics Nexus:

  • Tie interoceptive awareness to societal resilience: A dysregulated body cannot engage in collective action. How might somatic practices (e.g., breathwork) fuel post-collapse rebuilding?

• Technology as Double-Edged Sword:

  • Critique apps that commodify interoception (e.g., mindfulness apps) versus tools that foster bodily autonomy (e.g., DIY biohacking).

  • Explore how AI could either erode the "interoceptive self" (via attention economy) or enhance it (via personalized health insights).

• Ethics of Adaptation:

  • Contrast adaptive passivity (e.g., burrowing) with adaptive activism (e.g., prefigurative politics). When is each strategy viable?

---

Practical Applications:

1. Workbook/Journal Prompts:

   • For Title 1: "Map a decision to your bodily state: Did hunger/fatigue shape it?"

   • For Title 2: "Design your ‘cozy protocol’—what three practices would sustain you in collapse?"

2. Case Studies:

   • Iceland’s post-2008 recovery (small-world resilience) vs. Silicon Valley’s "move fast and break things" ethos.

   • Communities using interoceptive practices (e.g., trauma-sensitive yoga in prisons) to rebuild agency.

3. Futures Framework:

   • Scenarios for 2050: A world where "interoceptive literacy" is taught in schools, or where decentralized "tribes" negotiate resource-sharing via blockchain.

---

Counterarguments to Address:

• For Title 1: Does biologizing the self risk nihilism? Rebuttal: Agency emerges from understanding bodily constraints, not denying them.

• For Title 2: Does retreat perpetuate inequality? Rebuttal: Focus on redistribution of sovereignty (e.g., land trusts, UBI) as part of "small-world" ethics.

By weaving these threads, your work could bridge neuroscience, philosophy, and futurism—offering readers not just analysis, but practices for navigating an uncertain world. Would a deeper dive into any of these angles spark your interest?

 

 

Parents convey a male default in child-directed speech

Interesting open source article describing experiments by Leshin et al.  (Our current MAGA overlords would like to ban such perspectives.) Their abstract: 

Adults tend to view men (more so than women) as default people, with numerous real-world consequences for gender equity. In the United States, the tendency to center men in concepts of people develops across middle childhood, yet the specific mechanisms that contribute to it remain unknown. Here, we investigate one subtle but potentially powerful social mechanism: the category labels that parents use to describe boys/men and girls/women in conversations with their children. Across two studies (N = 822 parent–child dyads, predominantly from the United States), parents used gender-neutral labels like “kid” or “person” more often to describe boys/men than girls/women and, conversely, used gender-specific labels (e.g., “girl”) more often to describe girls/women than boys/men. These patterns emerged when parents were shown gender-stereotypical girls/women and boys/men (e.g., a girl painting her nails, a boy digging for worms); when parents viewed counterstereotypical stimuli (e.g., a boy painting his nails, a girl digging for worms), the patterns reversed. Our findings illuminate parents’ category label usage as a critical social mechanism that may undergird the development of a male default in a US cultural context, informing efforts to intervene on this process.