Category Archives: Cognitive Science

chat GPT4: Cognitive Science, HCI, Rationality (Stanovich 2016), Dual-Process Theory (Kahnemann)

Last change: Nov 1, 2023

CONTEXT

This text belongs to the theme ‘chats with chatGPT4′.

After trying a review of the book from Stanovich et al. (2016) I have checked a possible contribution from chatGPT 4. As expected, chatGPT4 replicated all the common concepts which are used in the context of cognitive science and Stanovich as well as Kahnemann. All the real questions about methodological details have not been answered. Nevertheless, chatGPT4 lists all main concepts which one should know if one is dealing with these subjects, but that’s it. This is not really science, and has never to do with philosophy or philosophy of science.

PROTOCOL OF THE CHAT

User

What do you know about cognitive science

ChatGPT

Cognitive science is an interdisciplinary field that studies the mind, intelligence, and behavior from multiple perspectives. At its core, it seeks to understand how the human mind works and how it might be replicated or modeled, including through artificial intelligence. The field encompasses a broad range of topics, from the basic processes of cognition to complex interactions with the environment. Here are some key aspects of cognitive science: 1. **Interdisciplinary Nature**: Cognitive science integrates methods and theories from several disciplines, including psychology, neuroscience, linguistics, philosophy, computer science, anthropology, and biology. 2. **Research Areas**: – Perception: Understanding how organisms interpret sensory data. – Attention: Investigating how the mind allocates cognitive resources to various stimuli. – Memory: Exploring the processes involved in storing and retrieving information. – Language: Studying the cognitive processes underlying language acquisition, comprehension, and production. – Problem Solving and Decision Making: Analyzing how humans and other animals think, make decisions, and solve problems. – Consciousness: Examining the nature of subjective experience and self-awareness. 3. **Cognitive Neuroscience**: This branch of cognitive science looks at how brain structures and functions are related to cognitive processes. It makes use of technologies such as fMRI and EEG to study the brain in action. 4. **Computational Models**: Cognitive scientists often construct computational models to simulate aspects of human cognition. These models can range from symbolic representations that mimic logic and reasoning to connectionist models that emulate neural networks. 5. **Philosophy of Mind**: Philosophical questions about the nature of mind, the relationship between mind and body, and the nature of consciousness are central to cognitive science. Philosophy contributes questions about the nature of knowledge, perception, and the structure of language, influencing cognitive theories. 6. **Human-Computer Interaction (HCI)**: This field draws on cognitive science principles to improve the design of user interfaces and enhance user experience with technology. 7. **Education and Application**: Insights from cognitive science have been applied to education, informing teaching methods and instructional design to align with how the brain learns best. 8. **Artificial Intelligence**: Cognitive science and AI are deeply intertwined, with insights from the study of human cognition informing the development of algorithms and systems that aim to replicate aspects of human thought. Cognitive science continues to evolve, with new findings and technologies perpetually reshaping our understanding of the human mind. As it progresses, it offers potential advancements not only in AI but also in how we approach mental health, education, design, and a multitude of other areas that require an understanding of how we think and learn.

User

You are listing many disciplines engaged in cognitive science. How are all these disciplines interrelated?

ChatGPT

The disciplines within cognitive science are interrelated through their shared goal of understanding the mind and cognition. Here’s how each contributes to the field and how they intersect with each other: 1. **Psychology**: Psychology contributes experimental methods and theories about behavior and mental processes. It often serves as the basis for hypotheses about cognitive mechanisms that other disciplines then further investigate. 2. **Neuroscience**: Neuroscience provides insights into the brain structures and neural circuits that underlie cognitive functions. It adds a biological perspective to theories of cognition that can confirm, refute, or refine psychological theories. 3. **Linguistics**: Linguistics studies the structure, use, and psychology of language, which is a complex cognitive ability. Theories of syntax, semantics, and language acquisition inform models of how the brain processes language. 4. **Philosophy**: Philosophy addresses fundamental questions about the nature of knowledge, mind, reality, and values. It offers frameworks for understanding consciousness, intentionality, and the mind-body problem, which can inform empirical research. 5. **Computer Science**: Computer science, particularly artificial intelligence, contributes algorithms and computational models that mimic cognitive processes. The feedback loop between AI and cognitive science is strong: cognitive science inspires AI development, and AI provides tools and metaphors for understanding cognition. 6. **Anthropology**: Anthropology brings in the cultural dimension, studying how cognition varies across different human societies. This helps to differentiate between universal cognitive processes and those that are culturally specific. 7. **Biology**: Biology, especially evolutionary biology, contributes to our understanding of the evolutionary pressures that shaped our cognitive abilities. It provides a framework for understanding why certain cognitive functions may have developed. 8. **Education**: Research in cognitive science directly impacts educational practices by providing insights into how learning and memory work, thus informing teaching strategies and curriculum development. 9. **Human-Computer Interaction (HCI)**: HCI draws on principles from psychology and computer science to design better interfaces. It uses cognitive models to predict how users will interact with technology and to create user experiences that complement human cognitive abilities. The interrelation is often practical; for example: – A cognitive psychologist might devise an experiment based on a philosophical question. – A neuroscientist might use the experiment’s results to guide brain imaging studies. – A linguist might analyze the language data from the experiment. – A computer scientist might model the cognitive process observed in a computational framework. – An anthropologist might compare these results with similar cognitive processes in different cultures. – An educationalist might apply the findings to improve classroom teaching methods. – An HCI researcher might use the findings to design better computer interfaces. The intersection of these disciplines within cognitive science ensures a comprehensive approach to studying cognition, taking into account its complexity and richness by viewing it through multiple lenses.

User

HCI is an interesting example. HCI analyses the interaction between humans and machines with regard to certain tasks and within certain environments. Where do the cognitive models come from which shall be used?

Remark for the following: chatGPT4 offered two versions for an answer. I could select and opted for version 2:

ChatGPT

Human-Computer Interaction (HCI) relies heavily on cognitive models to predict and interpret how users interact with computer systems. These cognitive models are derived from various sources within the broader field of cognitive science: 1. **Psychological Theories**: Many cognitive models in HCI are based on psychological theories about how the human mind processes information. For instance, models like the Cognitive Load Theory help designers understand how to present information to users without overwhelming them. 2. **Cognitive Architectures**: There are comprehensive computational frameworks that aim to simulate human cognitive processes. Examples include the ACT-R (Adaptive Control of Thought-Rational) and Soar architectures. These are often used in HCI to predict how users will learn new systems and solve problems. 3. **Human Information Processing Models**: HCI often uses specific models that describe the stages of human information processing, such as the Model Human Processor, which includes perceptual, cognitive, and motor processors, each with their own cycle times and memories. 4. **Attention Models**: Models of visual attention, such as the See-Think-Do framework, explain how users allocate their attention when interacting with interfaces and can inform the design of systems to make important information more salient. 5. **Memory Models**: Understanding working memory and long-term memory is crucial for interface design. HCI uses models like the Working Memory model by Baddeley and Hitch to predict how users retain and process information while completing tasks. 6. **Error Prediction Models**: Models like Norman’s Seven Stages of Action are used to predict possible errors in human-computer interaction, allowing for the design of error-resistant systems. 7. **Task Models**: Task analysis models, such as GOMS (Goals, Operators, Methods, and Selection rules), are used to estimate how long it takes a user to accomplish a task and to identify ways to streamline the interaction. 8. **Ecological Models**: These models, like the distributed cognition approach, look at cognitive processes as distributed across people, time, and tools, considering the environment in which HCI takes place. 9. **User Mental Models**: HCI considers the mental models that users form of how systems work. Designers try to align interfaces with these mental models to make them more intuitive. 10. **Usability Heuristics**: While not models in the traditional sense, heuristics like those proposed by Jakob Nielsen are based on principles of cognitive psychology and are used to evaluate user interfaces. 11. **Empirical Studies**: Empirical studies, including both qualitative and quantitative user research, continue to inform and refine cognitive models. User testing and observation can lead to the development of new models or the refinement of existing ones. These models are not mutually exclusive and can often be combined or used in parallel to tackle different aspects of HCI design and evaluation. The choice of model(s) typically depends on the particular aspect of human cognition that is most relevant to the interaction being studied or the problem being solved. By applying cognitive models, HCI professionals aim to create user-centered designs that are efficient, effective, and satisfying for the user.

User

Your answer is helpful. But these different contributions are usually not written within a coherent conceptual framework. Is it possible to extract those concepts which are common between these different contributions?

ChatGPT

Indeed, the diverse disciplines within cognitive science and HCI contribute a multitude of models and theories, and these contributions often lack a unifying framework. However, several core concepts are shared across these models and form the bedrock of cognitive science and HCI. Here are some of these shared concepts: 1. **Information Processing**: A key concept across many cognitive models is that humans process information in stages (e.g., encoding, storage, retrieval). This idea, originating from the computer metaphor of the mind, is a common thread in both psychological models and HCI designs. 2. **Attention**: The concept of attention, how it is directed, and how it is managed, is central to understanding human cognition and designing interfaces. Attentional models inform interface design by suggesting where to place important information and how to alert users to changes. 3. **Memory**: The functions of working memory and long-term memory and their limitations are critical concepts. They influence how much information should be presented at once and how interfaces can enhance recall through cues and design. 4. **Mental Models**: Across disciplines, there is recognition that users create mental models of how systems work, and the closeness of these models to the actual workings of the system can affect usability. 5. **Cognitive Load**: Cognitive load refers to the amount of mental effort being used in the working memory. Across HCI and cognitive science, there’s an emphasis on designing systems that manage and minimize cognitive load to prevent errors and improve efficiency. 6. **Problem Solving and Decision Making**: Understanding the cognitive processes behind problem solving and decision making is essential for creating interfaces that support these activities. 7. **Metacognition**: Awareness and understanding of one’s own thought processes are recognized as crucial for learning and interaction with systems. This is reflected in designs that support user control and flexibility. 8. **Perception**: Theories of visual, auditory, and haptic perception are fundamental in designing interfaces that are perceivable and that map onto the human sensory capabilities. 9. **User Experience**: The concept of creating positive interactions encompasses not just the usability but also the affective responses, such as satisfaction and enjoyment. 10. **Error Recognition and Recovery**: Understanding how and why errors occur in human-machine interaction guides the design of systems that help users avoid mistakes or recover from them easily. 11. **Adaptability and Learning**: The concept that users learn and adapt to systems, and that systems can adapt to users, is common across cognitive science and HCI. This is key in designing interfaces that are capable of accommodating users of varying skill levels and learning styles. 12. **Multimodality**: Recognizing that human interaction with the environment is multimodal has led to designs that utilize multiple modes of input and output (e.g., touch, voice, gesture). These shared concepts help to form a bridge across the various contributions to cognitive science and HCI, providing a more cohesive understanding of how to design technology that works in harmony with human cognitive processes. Design principles and guidelines in HCI are often derived from these fundamental cognitive concepts, ensuring that despite the lack of a single, coherent framework, the discipline remains grounded in an understanding of human cognition.

User

I agree with you. Nevertheless, it shows many important questions are still open. Last questions: How would you locate the book ‘The Rational Quotient’ of Stanovich and others in this framework of HCI?

ChatGPT

“The Rationality Quotient” by Keith E. Stanovich and colleagues is actually more directly related to cognitive psychology and the study of rational thought rather than Human-Computer Interaction (HCI) per se. However, its insights can certainly be located within the broader context of HCI and cognitive science. Stanovich’s work focuses on the nature of rationality, distinguishing between different types of cognitive processes: those that are algorithmic (akin to computational processes in the brain), those that relate to reflective thinking and decision-making, and those that pertain to the knowledge base that individuals have at their disposal. Here’s how this relates to HCI: 1. **User Decision Making**: HCI design often considers how users make decisions while interacting with interfaces. Stanovich’s discussion of rational thinking can inform the design of systems that support better decision-making processes. 2. **Error Mitigation**: Understanding why people make irrational decisions or errors can help HCI professionals design systems that reduce the likelihood of user errors. 3. **Cognitive Biases**: The work on rationality includes the study of cognitive biases, which has implications for HCI in terms of designing interfaces that help mitigate these biases or use them to guide users towards more productive behaviors. 4. **Personalization and Adaptability**: Rationality research may influence the development of adaptive systems that personalize the user experience based on an individual’s demonstrated rationality levels or decision-making styles. 5. **Instructional Design**: Insights from studies of rationality can impact how educational technologies are designed to enhance learning and critical thinking skills. 6. **Reflective Interfaces**: The concept of reflective thinking can lead to the creation of interfaces that encourage users to think more deeply about their choices, such as in systems that prompt users to confirm or reconsider actions. While “The Rationality Quotient” doesn’t provide a direct commentary on HCI, the underlying cognitive principles it explores are highly relevant for designing systems that align with human cognitive strengths and compensate for weaknesses. Thus, within the framework of HCI, Stanovich’s work can be seen as contributing to the foundational cognitive understanding necessary to create user-centered designs that support effective, rational, and satisfying interactions with technology.

User

This sounds positive for the book. But I ask myself in which sense the concept of ‘rationality’ can be related to ‘cognitive processes’?

ChatGPT

The concept of “rationality” is deeply intertwined with cognitive processes. Rationality, in the context of cognitive science and psychology, is generally understood as the quality of being reasonable, based on facts or reason. It refers to the way in which individuals think, make decisions, and act based on certain principles of logic and consistency. Here’s how rationality relates to cognitive processes: 1. **Dual-Process Theories**: Theories like those proposed by Daniel Kahneman, which distinguish between two types of thinking processes—fast, automatic, intuitive thought (System 1) and slower, more deliberate, analytical thought (System 2)—are directly related to the study of rationality. Rationality is often associated with the reflective, analytical processes of System 2. 2. **Decision-Making**: Rationality is central to decision-making, which is a complex cognitive process involving the evaluation of options, the assessment of probabilities and outcomes, and the selection of a course of action. Cognitive science studies the heuristics and biases that affect this process. 3. **Logic and Reasoning**: Cognitive processes related to understanding logical structures and applying rules of inference fall under the umbrella of rationality. This includes deductive reasoning, inductive reasoning, and abductive reasoning. 4. **Problem Solving**: Rational approaches to problem solving involve systematic analysis, the application of knowledge, and consideration of potential solutions. This relates to cognitive processes involving working memory, planning, and executive function. 5. **Belief Formation and Revision**: Rationality also pertains to how individuals form, maintain, and revise their beliefs in light of new evidence. This involves cognitive processes related to learning, memory, and critical thinking. 6. **Metacognition**: Rational thinking involves metacognition, which is the awareness and control of one’s own cognitive processes. Metacognitive skills enable individuals to recognize when a problem is beyond their current understanding and to adjust their approach accordingly. 7. **Epistemic Rationality**: This aspect of rationality is concerned with how beliefs are justified and how knowledge is constructed, which is central to cognitive processes involving perception, interpretation, and the assessment of truth claims. Stanovich and others in the field of cognitive science study these aspects of cognition to understand how and why people think and act the way they do, especially when their actions deviate from what might be considered objectively rational. Their work seeks to explain cognitive biases, irrational preferences, and other anomalies in human thought and behavior. In “The Rationality Quotient,” Stanovich et al. propose a framework for understanding and measuring rationality that goes beyond the traditional IQ tests, which typically focus on problem-solving abilities and cognitive capacity. They emphasize the importance of rational thought and behavior in everyday decision-making and the practical outcomes of such thought processes. The concept of rationality thus serves as a lens through which cognitive processes are evaluated in terms of their effectiveness and alignment with goals and reality.

User

You are listing important contributions to the question. You are mentioning the Dual-Process Theory by Kahnemann. Why do you call this a ‘theory’?

ChatGPT

The term “Dual-Process Theory” is often used to describe a range of theoretical frameworks in psychology that posit two distinct modes or systems of thinking that operate when we process information. Daniel Kahneman popularized one of the most well-known dual-process models with his characterization of System 1 and System 2 in his book “Thinking, Fast and Slow.” The reason it’s called a “theory” is because it offers a systematic explanation for observations and findings from numerous psychological studies. A theory in science is a well-substantiated explanation acquired through the scientific method and repeatedly tested and confirmed through observation and experimentation. Here’s why the Dual-Process Theory fits this definition: 1. **Empirical Support**: The Dual-Process Theory is supported by a wide range of experiments and observations in cognitive psychology, neuropsychology, and related fields. 2. **Predictive Power**: It provides predictions about human behavior that can be tested in experimental settings. For instance, it predicts that under certain conditions, people will rely more on fast, intuitive thinking (System 1) than on slow, deliberative thinking (System 2). 3. **Explanatory Scope**: The theory explains a variety of phenomena across different contexts, such as why people struggle with statistical reasoning or are susceptible to cognitive biases. 4. **Integrative Framework**: It integrates findings from various areas of cognitive science into a coherent framework, explaining how different types of thinking contribute to behavior and judgment. 5. **Heuristic Value**: The theory has heuristic value in that it generates new hypotheses and lines of research, driving the field forward. In scientific parlance, a theory is not a mere guess or a tentative hypothesis; it is a comprehensive explanation for a range of phenomena. However, like all scientific theories, Dual-Process Theory is not beyond criticism or revision. As new data emerge, theories are often refined or challenged. Some researchers question the dichotomy proposed by Dual-Process Theories or argue for more nuanced or integrated models of cognition. Despite this, the Dual-Process Theory as presented by Kahneman has been immensely influential in our understanding of human thought and has shaped research in cognitive psychology, economics, and other fields.

User

OK, I agree.

ChatGPT

Great, I’m glad to hear that the information resonated with you! If you have any more questions or if there’s another topic you’re curious about, feel free to ask.

REVIEW: Keith E.Stanovich, Richard F.West, Maggie E.Toplak, “The Rational Quotient. Towards a Test of Rational Thinking”, MIT Press, 2016

(Last change: Nov 1, 2023)

CONTEXT

This text belongs to the overall theme REVIEWS.

In the last months I was engaged with the topic of text-generating algorithms and the possible impact for a scientific discourse (some first notices to this discussion you can find here (https://www.uffmm.org/2023/08/24/homo-sapiens-empirical-and-sustained-empirical-theories-emotions-and-machines-a-sketch/)). In this context it is important to clarify the role and structure of human actors as well as the concept of Intelligence. Meanwhile I have abandoned the word Intelligence completely because the inflationary use in today mainstream pulverises any meaning. Even in one discipline — like psychology — you can find many different concepts. In this context I have read the book of Stanovich et.al to have a prominent example of using the concept of intelligence, there combined with the concept of rationality, which is no less vague.

Introduction

The book “The Rationality Quotient” from 2016 represents not the beginning of a discourse but is a kind of summary of a long lasting discourse with many publications before. This makes this book interesting, but also difficult to read in the beginning, because the book is using nearly on every page theoretical terms, which are assumed to be known to the reader and cites other publications without giving sufficient explanations why exactly these cited publications are important. This is no argument against this book but sheds some light on the reader, who has to learn a lot to understand the text.

A text with the character of summing up its subject is good, because it has a confirmed meaning about the subject which enables a kind of clarity which is typical for that state of elaborated point of view.

In the following review it is not the goal to give a complete account of every detail of this book but only to present the main thesis and then to analyze the used methods and the applied epistemological framework.

Main Thesis of the Book

The reviewing starts with the basic assumptions and the main thesis.

FIGURE 1 : The beginning. Note: the number ‘2015’ has to be corrected to ‘2016’.

FIGURE 2 : First outline of cognition. Note: the number ‘2015’ has to be corrected to ‘2016’.

As mentioned in the introduction you will in the book not find a real overview about the history of psychological research dealing with the concept of Intelligence and also no overview about the historical discourse to the concept of Rationality, whereby the last concept has also a rich tradition in Philosophy. Thus, somehow you have to know it.

There are some clear warnings with regard to the fuzziness of the concept rationality (p.3) as well as to the concept of intelligence (p.15). From a point of view of Philosophy of Science it could be interesting to know what the circumstances are which are causing such a fuzziness, but this is not a topic of the book. The book talks within its own selected conceptual paradigm. Being in the dilemma, of what kind of intelligence paradigm one wants to use, the book has decided to work with the Cattell-Horn-Carroll (CTC) paradigm, which some call a theory. [1]

Directly from the beginning it is explained that the discussion of Intelligence is missing a clear explanation of the full human model of cognition (p.15) and that intelligence tests therefore are mostly measuring only parts of human cognitive functions. (p.21)

Thus let us have a more detailed look to the scenario.

[1] For a first look to the Cattell–Horn–Carroll theory see: https://en.wikipedia.org/wiki/Cattell%E2%80%93Horn%E2%80%93Carroll_theory, a first overview.

Which point of View?

The book starts with a first characterization of the concept of Rationality within a point of view which is not really clear. From different remarks one gets some hints to modern Cognitive Science (4,6), to Decision Theory (4) and Probability Calculus (9), but a clear description is missing.

And it is declared right from the beginning, that the main aim of the book is the Construction of a rational Thinking Test (4), because for the authors the used Intelligence Tests — later reduced to the Carroll-Horn-Carroll (CHC) type of intelligence test (16) — are too narrow in what they are measuring (15, 16, 21).

Related to the term Rationality the book characterizes some requirements which the term rationality should fulfill (e.g. ‘Rationality as a continuum’ (4), ’empirically based’ (4), ‘operationally grounded’ (4), a ‘strong definition’ (5), a ‘normative one’ (5), ‘normative model of optimum judgment’ (5)), but it is more or less open, what these requirements imply and what tacit assumptions have to be fulfilled, that this will work.

The two requirements ’empirically based’ as well as ‘operationally grounded’ point in the direction of an tacitly assumed concept of an empirical theory, but exactly this concept — and especially in association with the term cognitive science — isn’t really clear today.

Because the authors make in the next pages a lot of statements which claim to be serious, it seems to be important for the discussion in this review text to clarify the conditions of the ‘meaning of language expressions’ and of being classified as ‘being true’.

If we assume — tentatively — that the authors assume a scientific theory to be primarily a text whose expressions have a meaning which can transparently be associated with an empirical fact and if this is the case, then the expression will be understood as being grounded and classified as true, then we have characterized a normal text which can be used in everyday live for the communication of meanings which can become demonstrated as being true.

Is there a difference between such a ‘normal text’ and a ‘scientific theory’? And, especially here, where the context should be a scientific theory within the discipline of cognitive science: what distinguishes a normal text from a ‘scientific theory within cognitive science’?

Because the authors do not explain their conceptual framework called cognitive science we recur here to a most general characterization [2,3] which tells us, that cognitive science is not a single discipline but an interdisciplinary study which is taking from many different disciplines. It has not yet reached a state where all used methods and terms are embedded in one general coherent framework. Thus the relationship of the used conceptual frameworks is mostly fuzzy, unclear. From this follows directly, that the relationship of the different terms to each other — e.g. like ‘underlying preferences’ and ‘well ordered’ — is within such a blurred context rather unclear.

Even the simple characterization of an expression as ‘having an empirical meaning’ is unclear: what are the kinds of empirical subjects and the used terms? According to the list of involved disciplines the disciplines linguistics [4], psychology [5] or neuroscience [6] — besides others — are mentioned. But every of these disciplines is itself today a broad field of methods, not integrated, dealing with a multifaceted subject.

Using an Auxiliary Construction as a Minimal Point of Reference

Instead of becoming somehow paralyzed from these one-and-all characterizations of the individual disciplines one can try to step back and taking a look to basic assumptions about empirical perspectives.

If we take a group of Human Observers which shall investigate these subjects we could make the following assumptions:

  1. Empirical Linguistics is dealing with languages, spoken as well as written by human persons, within certain environments, and these can be observed as empirical entities.
  2. Empirical Psychology is dealing with the behavior of human persons (a kind of biological systems) within certain environments, and these can be observed.
  3. Empirical Neuroscience is dealing with the brain as part of a body which is located in some environment, and this all can be observed.

The empirical observations of certain kinds of empirical phenomena can be used to define more abstract concepts, relations, and processes. These more abstract concepts, relations, and processes have ‘as such’ no empirical meaning! They constitute a formal framework which has to become correlated with empirical facts to get some empirical meaning. As it is known from philosophy of science [7] the combination of empirical concepts within a formal framework of abstracts terms can enable ‘abstract meanings’ which by logical conclusions can produce statements which are — in the moment of stating them — not empirically true, because ‘real future’ has not yet happened. And on account of the ‘generality’ of abstract terms compared to the finiteness and concreteness of empirical facts it can happen, that the inferred statements never will become true. Therefore the mere usage of abstract terms within a text called scientific theory does not guarantee valid empirical statements.

And in general one has to state, that a coherent scientific theory including e.g. linguistics, psychology and neuroscience, is not yet in existence.

To speak of cognitive science as if this represents a clearly defined coherent discipline seems therefore to be misleading.

This raises questions about the project of a constructing a coherent rational thinking test (CART).

[2] See ‘cognitive science’ in wikipedia: https://en.wikipedia.org/wiki/Cognitive_science

[3] See too ‘cognitive science’ in the Stanford Encyclopedia of Philosophy: https://plato.stanford.edu/entries/cognitive-science/

[4] See ‘linguistics’ in wikipedia: https://en.wikipedia.org/wiki/Linguistics

[5] See ‘psychology’ in wikipedia: https://en.wikipedia.org/wiki/Psychology

[6] See ‘neuroscience’ in wikipedia: https://en.wikipedia.org/wiki/Neuroscience

[7] See ‘philosophy of science’ in wikipedia: https://en.wikipedia.org/wiki/Philosophy_of_science

‘CART’ TEST FRAMEWORK – A Reconstruction from the point of View of Philosophy of Science

Before I will dig deeper into the theory I try to understand the intended outcome of this theory as some point of reference. The following figure 3 gives some hints.

FIGURE 3 : Outline of the Test Framework based on the Appendix in Stanovich et.al 2016. This Outline is a Reconstruction by the author of this review.

It seems to be important to distinguish at least three main parts of the whole scientific endeavor:

  1. The group of scientists which has decided to process a certain problem.
  2. The generated scientific theory as a text.
  3. The description of a CART Test, which describes a procedure, how the abstract terms of the theory can be associated with real facts.

From the group of scientists (Stanovich et al.) we know that they understand themselves as cognitive scientists (without having a clear characterization, what this means concretely).

The intended scientific theory as a text is here assumed to be realized in the book, which is here the subject of a review.

The description of a CART Test is here taken from the appendix of the book.

To understand the theory it is interesting to see, that in the real test the test system (assumed here as a human person) has to read (and hear?) a instruction, how to proceed with a task form, and then the test system (a human person) has to process the test form in the way it has understood the instructions and the test form as it is.

The result is a completed test form.

And it is then this completed test form which will be rated according to the assumed CART theory.

This complete paradigm raises a whole bunch of questions which to answer here in full is somehow out of range.

Mix-Up of Abstract Terms

Because the Test Scenario presupposes a CART theory and within this theory some kind of a model of intended test users it can be helpful to have a more closer look to this assumed CART model, which is located in a person.

FIGURE 4 : General outline of the logic behind CART according to Stanovich et al. (2016).

The presented cognitive architecture shall present a framework for the CART (Comprehensive Assessment of Rational Thinking), whereby this framework is including a model. The model is not only assumed to contextualize and classify heuristics and tasks, but it also presents Rationality in a way that one can deduce mental characteristics included in rationality.(cf. 37)

Because the term Rationality is not an individual empirical fact but an abstract term of a conceptual framework, this term has as such no meaning. The meaning of this abstract term has to be arranged by relations to other abstract terms which themselves are sufficiently related to concrete empirical statements. And these relations between abstract terms and empirical facts (represented as language expressions) have to be represented in a manner, that it is transparent how the the measured facts are related to the abstract terms.

Here Stanovich et al. is using another abstract term Mind, which is associated with characteristics called mental characteristics: Reflective mind, Algorithmic Level, and Mindware.

And then the text tells that Rationality is presenting mental characteristics. What does this mean? Is rationality different from the mind, who has some characteristics, which can be presented from rationality using somehow the mind, or is rationality nevertheless part of the mind and manifests themself in these mental characteristics? But what kind of the meaning could this be for an abstract term like rationality to be part of the mind? Without an explicit model associated with the term Mind which arranges the other abstract term Rationality within this model there exists no meaning which can be used here.

These considerations are the effect of a text, which uses different abstract terms in a way, which is rather unclear. In a scientific theory this should not be the case.

Measuring Degrees of Rationality

In the beginning of chapter 4 Stanovich et al. are looking back to chapter 1. Here they built up a chain of arguments which illustrate some general perspective (cf. 63):

  1. Rationality has degrees.
  2. These degrees of rationality can be measured.
  3. Measurement is realized by experimental methods of cognitive science.
  4. The measuring is based on the observable behavior of people.
  5. The observable behavior can manifest whether the individual actor (a human person) follows assumed preferences related to an assumed axiom of choice.
  6. Observable behavior which is classified as manifesting assumed internal preferences according to an assumed internal axiom of choice can show descriptive and procedural invariance.
  7. Based on these deduced descriptive and procedural invariance, it can be inferred further, that these actors are behaving as if they are maximizing utility.
  8. It is difficult to assess utility maximization directly.
  9. It is much easier to assess whether one of the axioms of rational choice is being violated.

These statements characterize the Logic of the CART according to Stanovich et al. (cf.64)

A major point in this argumentation is the assumption, that observable behavior is such, that one can deduce from the properties of this behavior those attributes/ properties, which point (i) to an internal model of an axiom of choice, (ii) to internal processes, which manifest the effects of this internal model, (iii) to certain characteristics of these internal processes which allow the deduction of the property of maximizing utility or not.

These are very strong assumptions.

If one takes further into account the explanations from the pages 7f about the required properties for an abstract term axiom of choice (cf. figure 1) then these assumptions appear to be very demanding.

Can it be possible to extract the necessary meaning out of observable behavior in a way, which is clear enough by empirical standards, that this behavior shows property A and not property B ?

As we know from the description of the CART in the appendix of the book (cf. figure 3) the real behavior assumed for an CART is the (i) reading (or hearing?) of an instruction communicated by ordinary English, and then (ii) a behavior deduced from the understanding of the instruction, which (iii) manifests themself in the reading of a form with a text and filling out this form in predefined positions in a required language.

This described procedure is quite common throughout psychology and similar disciplines. But it is well known, that the understanding of language instructions is very error-prone. Furthermore, the presentation of a task as a text is inevitably highly biased and additionally too very error-prone with regard to the understanding (this is a reason why in usability testing purely text-based tests are rather useless).

The point is, that the empirical basis is not given as a protocol of observations of language free behavior but of a behavior which is nearly completely embedded in the understanding and handling of texts. This points to the underlying processes of text understanding which are completely internal to the actor. There exists no prewired connection between the observable strings of signs constituting a text and the possible meaning which can be organized by the individual processes of text understanding.

Stopping Here

Having reached this point of reading and trying to understand I decided to stop here: to many questions on all levels of a scientific discourse and the relationships between main concepts and terms appear in the book of Stanovich et al. to be not clear enough. I feel therefore confirmed in my working hypothesis from the beginning, that the concept of intelligence today is far too vague, too ambiguous to contain any useful kernel of meaning any more. And concepts like Rationality, Mind (and many others) seem to do not better.

Chatting with chatGPT4

Since April 2023 I have started to check the ability of chatGPT4 to contribute to a philosophical and scientific discourse. The working hypothesis is, that chatGPT4 is good in summarizing the common concepts, which are used in public texts, but chatGPT is not able for critical evaluations, not for really new creative ideas and in no case for systematic analysis of used methods, used frameworks, their interrelations, their truth-conditons and much more, what it cannot. Nevertheless, it is a good ‘common sense check’. Until now I couldn’t learn anything new from these chats.

If you have read this review with all the details and open questions you will be perhaps a little bit disappointed about the answers from chatGPT4. But keep calm: it is a bit helpful.

Protocol with chatGPT4