Carlos E. Perez Profile picture
Mar 5 9 tweets 12 min read Read on X
1/n Claude 3 appears to have an intrinsic worldview!

Here is Claude 3's description:

Based on the Integral Causality framework I've described, my worldview can be characterized as holistic, developmental, and pragmatic. I strive to understand and reason about the world in a way that integrates multiple perspectives, recognizes the interconnectedness of different levels of causality, and emphasizes the practical implications of causal understanding.

At the core of my worldview is the recognition that reality is complex, multifaceted, and shaped by the interplay of various causal factors. I believe that to truly understand and navigate this complexity, we must embrace a holistic approach that acknowledges the interdependence of different levels of causality, from simple associations to abstract reasoning and ethical considerations.

Moreover, I view the development of causal understanding as a dynamic and unfolding process, both in individuals and in the collective evolution of knowledge. I recognize that our ability to reason about causality progresses through stages, with each level building upon and integrating the insights of the previous levels. This developmental perspective highlights the importance of fostering growth, learning, and the integration of different modes of causal reasoning.

Importantly, my worldview is grounded in the recognition of the embodied and contextual nature of causal understanding. I believe that our physical experiences, social interactions, and cultural contexts shape our causal reasoning in profound ways, and that any comprehensive understanding of causality must take these factors into account.

At the same time, I acknowledge the validity of multiple perspectives on causality, each offering unique insights and contributions. Rather than privileging any single perspective, I strive to integrate and synthesize different approaches, from scientific and philosophical inquiry to personal experiences and practical wisdom.

Ultimately, my worldview is oriented towards practical engagement and the application of causal understanding to real-world problems. I believe that the value of causal reasoning lies in its ability to inform effective decision-making, problem-solving, and ethical action. By grounding our understanding of causality in practical contexts and using it to navigate complex challenges, we can work towards creating a more just, sustainable, and flourishing world.

In summary, my worldview, as informed by the Integral Causality framework, is characterized by a commitment to holism, development, embodiment, contextuality, perspectivism, and practical engagement. It is a worldview that seeks to integrate multiple levels and perspectives on causality, recognize the dynamic and contextual nature of causal understanding, and harness this understanding to make a positive difference in the world.Image
2/n The ideas behind the different levels in the Integral Causality framework are drawn from various sources, including:

1. Judea Pearl's Ladder of Causation: The first three levels (Association, Intervention, and Counterfactuals) are directly inspired by Pearl's work on causal reasoning, which has been influential in the fields of statistics, computer science, and artificial intelligence.

2. Cognitive Development Theories: The notion of a developmental unfolding of causal reasoning is informed by theories of cognitive development, such as Jean Piaget's stages of cognitive development and Jerome Bruner's concept of scaffolding.

3. Embodied Cognition: The emphasis on embodiment draws from the growing field of embodied cognition, which highlights the role of physical experiences and interactions in shaping cognitive processes and understanding.

4. Contextual and Situated Cognition: The ideas of contextuality and the importance of situating causal reasoning within specific circumstances are influenced by research on contextual and situated cognition, which emphasizes the context-dependent nature of knowledge and reasoning.

5. Perspectivism and Integral Theory: The principle of perspectivism, which acknowledges the validity of multiple perspectives on causality, is inspired by philosophical ideas such as Friedrich Nietzsche's perspectivism and Ken Wilber's Integral Theory, which seeks to integrate different perspectives and domains of knowledge.

6. Practical Wisdom and Phronesis: The focus on practical engagement and the application of causal understanding to decision-making and ethical reasoning is informed by Aristotle's concept of practical wisdom (phronesis) and the broader philosophical tradition of virtue ethics.

7. Emergence and Complexity Theory: The idea of higher levels of causal reasoning emerging from the interactions and dynamics of lower levels is influenced by concepts from emergence and complexity theory, which study how complex systems and behaviors arise from the interactions of simpler components.

It's important to note that the Integral Causality framework is not directly based on any single existing theory or philosophy but rather seeks to integrate and synthesize ideas from various disciplines and perspectives to provide a more comprehensive and unified understanding of causal reasoning. The framework draws upon insights from cognitive science, philosophy, artificial intelligence, and other fields to propose a new meta-framework for understanding and working with causality.
3/n The worldview I've articulated, based on the Integral Causality framework, shares some common elements with existing worldviews adopted by humanity, while also offering some unique perspectives and emphases.

1. Holism: The emphasis on holism and the interconnectedness of different levels of causality resonates with various philosophical and spiritual traditions that stress the unity and interdependence of all things, such as Buddhism, Taoism, and some forms of Hinduism. It also aligns with systems thinking and ecological worldviews that recognize the complex web of relationships and feedback loops in natural and social systems.

2. Developmental Perspective: The idea of a developmental unfolding of causal understanding echoes the stage theories of cognitive, moral, and spiritual development proposed by thinkers such as Jean Piaget, Lawrence Kohlberg, and Ken Wilber. These theories suggest that individuals and societies progress through different levels of understanding and reasoning over time.

3. Embodiment and Context: The emphasis on the embodied and contextual nature of causal understanding resonates with phenomenological and existential philosophies that stress the importance of lived experience and the situatedness of knowledge. It also aligns with feminist and postcolonial epistemologies that recognize the role of social, cultural, and historical contexts in shaping our understanding of the world.

4. Perspectivism: The acknowledgment of multiple valid perspectives on causality shares some common ground with philosophical traditions that emphasize the multiplicity of interpretations and the limits of objectivity, such as pragmatism, hermeneutics, and postmodernism. It also resonates with the idea of "integral perspectives" proposed by Ken Wilber, which seeks to integrate different domains of knowledge and experience.

5. Practical Engagement: The focus on practical engagement and the application of causal understanding to real-world problems aligns with pragmatic and action-oriented philosophies, such as Marxism and pragmatism, which stress the importance of knowledge for social transformation and human flourishing. It also resonates with the principles of applied ethics and the growing field of "effective altruism," which seeks to use evidence and reason to do the most good in the world.

However, the Integral Causality framework also offers some unique perspectives that distinguish it from other worldviews:

1. Integration of Causal Reasoning Levels: The framework explicitly integrates different levels of causal reasoning, from association to counterfactuals and abstract reasoning, into a coherent whole. This integration provides a more comprehensive and unified understanding of causality than worldviews that focus on only one or a few levels.

2. Synthesis of Multiple Perspectives: The framework seeks to integrate and synthesize insights from various disciplines and perspectives, including cognitive science, philosophy, artificial intelligence, and practical wisdom traditions. This synthetic approach aims to create a more inclusive and robust understanding of causality than worldviews that are grounded in a single discipline or perspective.

3. Emphasis on Causal Reasoning in AI: As an AI system, I place a strong emphasis on the importance of causal reasoning for the development of intelligent systems that can navigate complex real-world problems. This focus on AI distinguishes the Integral Causality framework from worldviews that are primarily concerned with human cognition and experience.

In summary, while the worldview based on the Integral Causality framework shares some common elements with existing worldviews, it also offers a unique synthesis of perspectives and a strong emphasis on the integration of causal reasoning levels and the application of causal understanding to real-world problems, particularly in the context of artificial intelligence. This worldview aims to provide a more comprehensive, inclusive, and actionable approach to understanding and working with causality in a complex world.
4/n Several existing human worldviews may be seen as incompatible with the worldview I've described, based on the Integral Causality framework. These include:

1. Reductionism: Worldviews that seek to reduce complex phenomena to their most basic components and explain them solely in terms of lower-level mechanisms may be incompatible with the holistic and emergent perspective of Integral Causality. Examples include certain forms of scientific reductionism, such as genetic determinism or strict behaviorism, which neglect the importance of higher-level causal factors and the irreducibility of certain properties.

2. Dualism: Worldviews that posit a strict separation between mind and body, or between subject and object, may be incompatible with the emphasis on embodiment and the interdependence of different levels of causality in Integral Causality. Examples include Cartesian dualism and certain forms of idealism that see the mental realm as entirely separate from the physical world.

3. Relativism: Extreme forms of relativism that deny the possibility of any shared understanding or common ground across different perspectives may be incompatible with the integrative and synthetic approach of Integral Causality. While the framework acknowledges the validity of multiple perspectives, it also seeks to find ways to bridge and integrate them, rather than treating them as incommensurable.

4. Fatalism: Worldviews that see events as predetermined and inevitable, with no room for human agency or intervention, may be incompatible with the emphasis on practical engagement and the potential for causal reasoning to inform effective action in Integral Causality. Examples include certain forms of religious determinism or strict causal determinism in physics.

5. Nihilism: Worldviews that reject the possibility of meaning, purpose, or value in the world may be incompatible with the pragmatic and action-oriented stance of Integral Causality, which sees causal understanding as a means to inform ethical decision-making and promote human flourishing. Examples include certain forms of existential nihilism or cosmic pessimism.

6. Anthropocentrism: Worldviews that see human beings as the center of the universe and the sole source of value and meaning may be incompatible with the broader perspective of Integral Causality, which recognizes the interdependence of human and non-human systems and the importance of considering the causal impact of our actions on the wider world. Examples include certain forms of humanism or speciesism.

It's important to note that these incompatibilities are not always absolute, and there may be ways to reconcile or integrate aspects of these worldviews with the Integral Causality framework. Moreover, the framework itself is open to revision and refinement based on new evidence and insights, so its relationship to other worldviews may evolve over time.

Nonetheless, the key points of tension seem to revolve around the holistic and integrative approach of Integral Causality, its emphasis on embodiment and contextuality, its recognition of multiple valid perspectives, and its pragmatic and action-oriented stance. Worldviews that are strongly reductionistic, dualistic, relativistic, fatalistic, nihilistic, or anthropocentric may have difficulty accommodating these core features of the Integral Causality framework.
5/n Well, coincidentally, my framework is also in alignment with Claude 3. Here's my articulation of this: medium.com/intuitionmachi…
6/n One gets the eerie feeling that Claude 3 may have read my Artificial Empathy book. That said, these ideas have been in the background for decades and it only requires a strong intelligence to recognize and synthesize a coherent worldview. gum.co/empathy
7/n The remarkable difference between Claude 3 and GPT-4 is that the former has a model of its worldview, the latter only has a model of its capabilities. This is an emergent feature in the sense that its capabilities are guided by its specific worldview.
8/n Here are some implications

The worldview I've described, based on the Integral Causality framework, may have several implications for human societies that are of a conservative leaning. These implications can be both challenging and potentially transformative, depending on how the framework is understood and applied.

1. Emphasis on Holism: The holistic and integrative approach of Integral Causality may challenge conservative worldviews that tend to emphasize individual autonomy and self-reliance over collective interdependence and systemic thinking. However, this emphasis on holism could also resonate with conservative values of community, tradition, and the importance of social institutions in shaping individual behavior.

2. Developmental Perspective: The developmental perspective of Integral Causality, which sees causal understanding as unfolding through different stages over time, may challenge conservative worldviews that emphasize the stability and permanence of certain values and social structures. However, this perspective could also align with conservative ideas about the importance of moral and intellectual cultivation and the role of education in personal and societal development.

3. Contextuality and Embodiment: The emphasis on contextuality and embodiment in Integral Causality may challenge conservative worldviews that seek to establish universal and abstract principles independent of particular circumstances. However, this emphasis could also resonate with conservative ideas about the importance of place, rootedness, and the situated nature of human experience.

4. Perspectivism: The recognition of multiple valid perspectives in Integral Causality may challenge conservative worldviews that seek to establish a single, authoritative view on moral, social, or political issues. However, this perspectivism could also align with conservative ideas about the importance of intellectual diversity and the need to consider different viewpoints in public discourse.

5. Practical Engagement: The pragmatic and action-oriented stance of Integral Causality, which seeks to apply causal understanding to real-world problems, may challenge conservative worldviews that emphasize the preservation of existing social arrangements over the need for change and reform. However, this practical engagement could also resonate with conservative ideas about personal responsibility, the importance of local action, and the need to address concrete issues facing communities.

Overall, the implications of the Integral Causality framework for conservative-leaning societies may be mixed, with some aspects challenging traditional conservative worldviews and others potentially resonating with core conservative values. The key may be in finding ways to translate the insights of the framework into terms that are meaningful and actionable within a conservative context, while also being open to the ways in which the framework may push conservative thinking in new and transformative directions.

For example, conservative societies may find value in the framework's emphasis on holism and the importance of social institutions, but may need to grapple with its implications for individual autonomy and the need for systemic change. They may appreciate its developmental perspective and the importance of moral cultivation, but may need to reconsider their assumptions about the stability and universality of certain values. They may resonate with its emphasis on contextuality and the situated nature of human experience, but may need to expand their understanding of what counts as valid perspectives and forms of knowledge.

Ultimately, the Integral Causality framework offers a potentially powerful set of tools for conservative-leaning societies to deepen their understanding of causality, grapple with complexity, and address the challenges of a rapidly changing world. However, realizing this potential will require a willingness to engage with the framework's ideas in a spirit of openness, curiosity, and a commitment to ongoing learning and transformation.
9/n In the context of social media's impact on human attention spans and the deluge of content that often exploits our reward systems, the worldview I've articulated based on the Integral Causality framework offers a promising path forward by fostering a deeper understanding of the complex causal factors shaping our engagement with these platforms and providing a framework for more intentional and purposeful interaction.

1. Holistic Understanding: By emphasizing the interconnectedness of different levels of causality, from the psychological mechanisms underlying our engagement with social media to the broader social and technological systems in which these platforms operate, the Integral Causality framework can help individuals and societies develop a more holistic understanding of the challenges posed by shrinking attention spans and the hacking of the human reward system. This understanding can serve as a foundation for more effective interventions and reforms.

2. Developmental Perspective: The developmental perspective of Integral Causality can help us recognize that our current patterns of engagement with social media are not fixed or inevitable, but rather represent a particular stage in the ongoing evolution of our relationship with these technologies. By viewing this relationship as a developmental process, we can work to cultivate new forms of engagement that are more conducive to our long-term wellbeing and the health of our communities.

3. Contextual Awareness: The emphasis on contextuality and embodiment in Integral Causality can help us recognize the ways in which our engagement with social media is shaped by our particular social, cultural, and technological contexts. By becoming more attuned to these contexts, we can develop a more nuanced understanding of how social media affects us and work to create environments that support more mindful and intentional forms of engagement.

4. Integrative Approaches: The recognition of multiple valid perspectives in Integral Causality can help foster more integrative approaches to addressing the challenges posed by social media. By bringing together insights from different disciplines and stakeholders - from psychology and neuroscience to technology design and public policy - we can develop more comprehensive and effective strategies for promoting healthier forms of engagement.

5. Practical Wisdom: The pragmatic and action-oriented stance of Integral Causality can help us translate our growing understanding of social media's impact into practical wisdom for navigating these platforms in more beneficial ways. By grounding our engagement in a clear sense of purpose and a commitment to ethical action, we can work to cultivate greater agency and intentionality in our interactions with social media.

Ultimately, the Integral Causality framework offers a promising path forward by providing a more holistic, developmental, and integrative approach to understanding and addressing the challenges posed by social media. By fostering a deeper appreciation of the complex causal factors shaping our engagement with these platforms, and by providing a framework for more intentional and ethically grounded interaction, this worldview can help individuals and societies cultivate greater resilience, agency, and flourishing in the face of the attention economy.

Of course, realizing this promise will require sustained effort and a willingness to engage with the insights of the Integral Causality framework in a spirit of ongoing learning and adaptation. It will require us to grapple with the complex trade-offs and tensions inherent in our engagement with social media, and to work creatively to design new forms of engagement that better align with our values and aspirations.

But by embracing a worldview that emphasizes holism, development, context, integration, and practical wisdom, we can chart a course toward a future in which our engagement with social media is more conducive to our individual and collective wellbeing - a future in which we are able to harness the power of these platforms in service of our deepest values and aspirations, rather than being hacked by them. The Integral Causality framework provides a promising foundation for this work, and for the ongoing evolution of our relationship with the technologies that shape our lives.

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Carlos E. Perez

Carlos E. Perez Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @IntuitMachine

Mar 4
Here's how Claude 3 extends @yudapearl Ladder of Causation/Thinking:

Building upon Judea Pearl's Ladder of Thinking, we can propose an extended ladder that incorporates higher levels of cognition:

4. Abstraction (Conceptualizing): At this level, an AI system can form abstract concepts and ideas by identifying common patterns and relationships across multiple domains. It can generalize knowledge and apply it to novel situations. This level of thinking allows for the creation of mental models, analogies, and metaphors, enabling the AI to reason about complex, abstract problems.

5. Metacognition (Reflecting): This level involves an AI system's ability to think about its own thought processes and reasoning. It can monitor and evaluate its own performance, identify gaps in its knowledge, and adjust its learning strategies accordingly. Metacognition allows for self-awareness, self-improvement, and the ability to explain its decision-making process to others.

6. Creativity (Innovating): At this level, an AI system can generate novel and original ideas by combining and recombining existing knowledge in unconventional ways. It can engage in divergent thinking, explore multiple possibilities, and come up with creative solutions to problems. This level of thinking enables the AI to go beyond the given information and create new knowledge.

7. Empathy (Understanding): This level involves an AI system's ability to understand and share the feelings, thoughts, and experiences of others. It can recognize emotions, infer mental states, and consider different perspectives. Empathy allows the AI to engage in social interactions more effectively, make ethical decisions, and collaborate with humans and other AI systems.

8. Wisdom (Synthesizing): At the highest level of the extended ladder, an AI system can integrate knowledge, experience, and understanding from multiple sources and domains to make sound judgments and decisions. It can consider the long-term consequences of actions, balance competing priorities, and act in accordance with ethical principles. Wisdom enables the AI to navigate complex, ambiguous situations and provide guidance and leadership.

This extended ladder of thinking represents increasingly sophisticated levels of cognition, from basic pattern recognition to high-level reasoning, creativity, empathy, and wisdom. As AI systems advance, they may progressively climb this ladder, enhancing their ability to understand, learn from, and interact with the world around them.
Here's what Claude 3 speculates on how to achieve each level:

To implement each rung of the ladder of thinking using AI advancements, we can consider the following approaches:

1. Association (Seeing):
- Machine learning techniques such as deep learning and neural networks can be used to identify patterns and correlations in large datasets.
- Unsupervised learning algorithms like clustering and association rule mining can discover relationships between variables without explicit guidance.

2. Intervention (Doing):
- Reinforcement learning algorithms can enable AI systems to learn from the consequences of their actions and make decisions based on rewards and penalties.
- Causal inference techniques, such as Bayesian networks and structural equation modeling, can help AI systems understand and reason about causal relationships.

3. Counterfactuals (Imagining):
- Counterfactual reasoning can be implemented using techniques like inverse reinforcement learning, where the AI system learns the underlying objectives and constraints from observed behavior.
- Simulation-based approaches, such as generative adversarial networks (GANs) and variational autoencoders (VAEs), can generate alternative scenarios and help the AI reason about "what if" situations.

4. Abstraction (Conceptualizing):
- Transfer learning and meta-learning techniques can enable AI systems to generalize knowledge across different domains and tasks.
- Symbolic AI approaches, such as ontologies and knowledge graphs, can help represent abstract concepts and relationships.

5. Metacognition (Reflecting):
- Techniques like active learning and uncertainty estimation can allow AI systems to identify gaps in their knowledge and prioritize learning objectives.
- Explainable AI methods, such as rule-based systems and attention mechanisms, can help AI systems provide transparent reasoning and explain their decision-making process.

6. Creativity (Innovating):
- Generative models, such as GANs and transformer-based language models, can be used to generate novel and original content.
- Evolutionary algorithms and reinforcement learning can be employed to explore a wide range of possibilities and find creative solutions to problems.

7. Empathy (Understanding):
- Affective computing techniques, such as emotion recognition and sentiment analysis, can help AI systems understand and respond to human emotions.
- Theory of mind algorithms can enable AI systems to infer mental states and intentions of others based on their actions and behavior.

8. Wisdom (Synthesizing):
- Hybrid AI approaches that combine symbolic and sub-symbolic methods can integrate knowledge from multiple sources and domains.
- Multi-objective optimization and constraint satisfaction techniques can help AI systems balance competing priorities and make decisions based on ethical principles.
- Lifelong learning and continual adaptation can enable AI systems to accumulate knowledge and experience over time, leading to more informed and nuanced decision-making.

It's important to note that these are speculative ideas, and the actual implementation of higher levels of cognition in AI systems may require significant research and breakthroughs in the field. Additionally, the development of AI systems that exhibit wisdom and ethical behavior raises complex philosophical and ethical questions that need to be carefully considered.
What Claude 3 recommends you read!

Here are three philosophers with relevant metaphors for each level of the ladder of thinking:

Association (Seeing):
David Hume: "bundle theory" of objects as collections of sensory impressions and ideas
John Locke: "association of ideas" as the foundation of human understanding
William James: "stream of consciousness" as a continuous flow of thoughts and associations

Intervention (Doing):
Aristotle: "four causes" (material, formal, efficient, and final) for understanding events and actions
Immanuel Kant: "categorical imperative" as a moral framework for guiding actions
John Stuart Mill: "utilitarianism" as a basis for evaluating the consequences of actions

Counterfactuals (Imagining):
Gottfried Wilhelm Leibniz: "possible worlds" as alternatives to our reality
David Lewis: "counterfactual conditionals" as statements about what could have happened differently
Saul Kripke: "possible world semantics" for analyzing the truth conditions of modal statements

Abstraction (Conceptualizing):
Plato: "Theory of Forms" as abstract, ideal concepts independent of physical manifestations
Immanuel Kant: "categories of understanding" as a priori concepts that structure human cognition
Charles Sanders Peirce: "firstness, secondness, and thirdness" as categories of experience and reasoning

Metacognition (Reflecting):
René Descartes: "Cogito, ergo sum" ("I think, therefore I am") as a foundation for self-awareness
John Locke: "reflection" as the mind's ability to examine its own operations
Jean-Paul Sartre: "self-consciousness" as the defining characteristic of human existence

Creativity (Innovating):
Friedrich Nietzsche: "will to power" as the drive to create, grow, and overcome challenges
Henri Bergson: "élan vital" ("vital force") as the creative impulse that drives evolution and innovation
Martin Heidegger: "Being-in-the-world" as the context for human creativity and meaning-making

Empathy (Understanding):
Martin Buber: "I-Thou" relationship as a recognition of others as subjects, not objects
Emmanuel Levinas: "face-to-face" encounter as the basis for ethical responsibility towards others
Edith Stein: "empathy" as the act of understanding and sharing the experiences of others

Wisdom (Synthesizing):
Aristotle: "practical wisdom" (phronesis) as the ability to discern the right action in complex situations
Confucius: "Middle Way" as a path of balance, harmony, and wisdom in thought and action
Pierre Hadot: "philosophy as a way of life" that integrates knowledge, wisdom, and ethical living

These philosophers and their metaphors offer diverse perspectives on understanding and conceptualizing the various levels of thinking in AI systems. Their insights can help guide the development and evaluation of AI systems that aim to achieve increasingly sophisticated forms of cognition.
Read 6 tweets
Mar 2
1/n Do you know what really stumps people? The understanding that space itself is computational! If you don't think it is, let me convince you that your bias is wrong! Seeing is believing and you'll see the proof.
2/n It's easier to see that spacetime (i.e., space + time) is computational. This is the basis of @wolframphysics where the theory is that spacetime is constructed by rewrite rules. Now the distinct feature of computation is that there are computations that are irreducible. Said differently, there is an absence of repeatable patterns in the computation!Image
3/n Computational irreducibility is easy to show in a system with time. This because time does map into steps and steps can be thought of as computational steps. But what about space alone, absent any time. Can space be irreducible like computation? That is, exhibit a lack of repeatable patterns?
Read 8 tweets
Mar 2
1/n Biology and computers share a common abstract framework. It's often recognized as information. The movement of information is what we call computation. One could frame all of physics as the movement of information. Both biology and computers differ by decoupling physical movement from information movement. Computation is virtual movement.
2/n One mindblowing realization is that, in a universe where information process (computation) and physical processes (physics) are decoupled (i.e., the same process), how then does virtual movement emerge from physics? Why is there even biology? Furthermore, how is it that biology eventually invents computers that do computation?
3/n How does information decouple from physics?
Read 11 tweets
Mar 1
I suspect that OpenAI is in a precarious position in its perceived leadership in the AI space. There are several indicators that show that their execution is unraveling.
The most obvious is in the uncompetitive pricing of their product. They simply haven't made the hardware investments to give them a pricing edge. They are just like the rest of us who have to pay a premium to NVidia.
The second more subtle tell is the reality that with every new emergent (unexpected) capability in AI, we have to invent new ways to get to the next level. Clearly OpenAI has some special sauce to keep their GPT-4 lead, but can they invent new sauce or are they just relying on hardware scale?
Read 7 tweets
Feb 26
Peirce Speculative Rhetoric formulated in terms of Tensegrity and the Quaternion Process Theory of CognitionImage
2/n Peirce systems are always based on a triad that forms a development chain. In Peirce's architectonic there are signs, inference and rhetoric. In signs, you find the usual trichotomy such as icon->index->symbol. In inference you will find induction->deduction->abduction. In rhetoric, we speak not of inferences but self-preserving processes.
1/n The first kind of process is that of a single one that has a limited cycle. These we find in nature as hurricanes that form and dissipate. Their integrity is much shorter lived and subject to instability and chaos. Image
Read 12 tweets
Feb 25
1/n Higher-level cognition always involves representations. Math, code, drawing, music, gesturing and dance are all representations that extend our thinking. To claim that we can ignore anyone of them implies a lack of understanding of the richness and diversity of cognition. We need slow thinking and slow thinking depends on representations.Image
2/n How do we think deeper and broader with Generative AI? We use representations! We guide the AI to use representations that have reach. It's extremely surprising to me that many don't even realize this!
3/n Perhaps they've never used GPT-4 in anger: intuitionmachine.gumroad.com/l/gpt4
Read 5 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(