Skip to main content

🆕 Does artificial intelligence exhibit basic fundamental subjectivity? A neurophilosophical argument

About

This document presents a Critical Discourse Analysis focused on AI literacy, specifically targeting the role of metaphor and anthropomorphism in shaping public and professional understanding of generative AI. The analysis is guided by a prompt that draws from cognitive linguistics (metaphor structure-mapping), the philosophy of social science (Robert Brown's typology of explanation), and accountability analysis.

All findings and summaries below were generated from detailed system instructions provided to a large language model and should be read critically as interpretive outputs—not guarantees of factual accuracy or authorial intent.

Task 1: Metaphor and Anthropomorphism Audit​

About this task

For each of the major metaphorical patterns identified, this audit examines the specific language used, the frame through which the AI is being conceptualized, what human qualities are being projected onto the system, whether the metaphor is explicitly acknowledged or presented as direct description, and—most critically—what implications this framing has for trust, understanding, and policy perception.

V3 Enhancement: Each metaphor now includes an accountability analysis.

1. Cognition as Biological Maturation​

Quote: "This includes the ability to learn from experience, adapt to new information, understand natural language, recognize patterns, and make decisions."

  • Frame: Algorithmic optimization framed as conscious cognitive understanding and biological adaptation
  • Projection: The text maps the deeply human, conscious processes of experiential learning and semantic comprehension onto the purely mathematical optimization routines of machine learning algorithms. By employing verbs like 'learn', 'adapt', and 'understand', the authors project a conscious state of 'knowing' onto a computational system that merely 'processes' statistical correlations. Experiential learning intrinsically implies a conscious subject who undergoes a meaningful event, integrates it into a unified narrative self, and consciously alters future behavior based on justified true belief. In stark contrast, an artificial intelligence system strictly adjusts mathematical weights via backpropagation without any subjective awareness of the data's referents. The attribution of 'understanding' to natural language processing completely obscures the mechanistic reality of token prediction and embedding space proximity. It falsely implies the system possesses a semantic grasp of meaning, whereas the model merely calculates the probability distribution of sequential symbols, devoid of any genuine comprehension or justified epistemic state.
  • Acknowledgment: Direct (Unacknowledged) (The text states 'ability to learn from experience... understand natural language' as literal, definitional facts about AI without any qualifying language or quotation marks.)
  • Implications: Framing computational processing as conscious understanding fundamentally distorts public and policy comprehension of AI capabilities, artificially inflating the perceived sophistication of these systems. When an AI is said to 'understand natural language', it invites unwarranted relation-based trust from users who assume the system grasps nuance, context, and truth in a human sense. This creates immense liability ambiguity: if a system 'understands' but provides dangerous or biased information, the framing suggests a cognitive failure or bad judgment by the AI, rather than a design flaw or toxic training dataset provided by the developers. Such anthropomorphic inflation leads to capability overestimation, wherein institutions might delegate critical decision-making tasks to algorithms under the false assumption that the models can evaluate truth claims.

Accountability Analysis:

  • Actor Visibility: Hidden (agency obscured)
  • Analysis: The passage entirely obscures the human engineers and corporate entities who design, train, and deploy these systems. By stating 'This includes the ability to learn', the AI is positioned as a self-directed agent acquiring knowledge, rather than a product being optimized by humans at companies like OpenAI or Google. This agentless construction serves the interests of technology developers by preemptively shifting accountability for model outputs onto the 'adapting' algorithm rather than the corporate decision-makers who curate the training data and define the optimization metrics.
Show more...

2. Computation as Human Thought​

Quote: "The ultimate goal of artificial intelligence is to create systems that can simulate and replicate human cognitive abilities, allowing machines to perform complex tasks and solve problems in a manner similar to human thought processes."

  • Frame: Mathematical execution as conscious human reasoning
  • Projection: This metaphor maps the subjective, conscious phenomenon of human reasoning onto the mechanistic execution of computational tasks. The text projects 'human thought processes' and 'cognitive abilities' onto machines that strictly perform vector mathematics and probability distributions. 'Solving problems' and 'thought' imply a conscious agent who recognizes a dilemma, formulates a hypothesis based on lived experience and understanding, and executes a deliberate strategy. Machine learning models do not experience problems nor do they possess cognitive states; they process inputs through multi-layered artificial neural networks to minimize a mathematically defined loss function. By blurring the line between statistical processing and conscious knowing, the projection attributes the phenomenal experience of reasoning to a mindless artifact.
  • Acknowledgment: Hedged/Qualified (The text uses the qualifying phrases 'simulate and replicate' and 'in a manner similar to', acknowledging that the machine's process is an imitation rather than identical to human thought.)
  • Implications: Even though qualified, equating machine outputs with 'human thought processes' reinforces a profound epistemic confusion. It suggests to audiences that AI systems operate through logical deduction and rational understanding rather than statistical correlation. This inflates perceived sophistication and encourages unwarranted trust in the system's outputs, particularly in high-stakes domains like medicine or law. When users believe a system 'thinks', they are less likely to recognize its fundamental limitations, such as its inability to grasp causal relationships, rely on ground truth, or experience doubt, thereby exacerbating the risks of algorithmic automation bias.

Accountability Analysis:

  • Actor Visibility: Hidden (agency obscured)
  • Analysis: While the text mentions the 'ultimate goal of artificial intelligence', it fails to name the specific actors—researchers, corporations, and funding bodies—driving this goal. The passive, generalized framing hides the immense financial and political motivations behind simulating human cognition. Naming the actors would expose that this 'goal' is a deliberate commercial strategy designed to replace human labor with automated systems, shifting the focus from the 'inevitable evolution of AI' to the discretionary decisions made by corporate executives.

3. Algorithmic Output as Subjective Creation​

Quote: "If we want to consider developing AI systems that can have a subjective point of view, we will need to replicate the several timescales - and the complex physiology behind them."

  • Frame: Engineering artifacts as potential subjects of experience
  • Projection: This passage projects the profound ontological status of conscious subjectivity onto a future engineered artifact. It maps the biological and phenomenological reality of having a 'point of view'—which involves mineness, qualitative feeling, and a continuous sense of self—onto the mechanistic processing of multiple temporal data streams. The text suggests that merely replicating 'several timescales' through engineering could spontaneously generate a conscious 'knower'. This conflates the complex mechanical integration of data processing with the subjective phenomenon of conscious awareness. It treats subjectivity as an emergent feature of computational architecture rather than a uniquely biological, lived reality, suggesting that an engineered system could eventually 'know' its environment rather than merely processing sensor inputs.
  • Acknowledgment: Direct (Unacknowledged) (The text presents the development of a 'subjective point of view' in AI as a literal engineering possibility dependent only on replicating specific timescales.)
  • Implications: Suggesting that AI could possess a 'subjective point of view' through engineering timescales fundamentally alters the ethical landscape, granting moral patienthood to statistical algorithms. This inflates the perceived existential significance of AI while distracting from immediate, material harms like bias, labor exploitation, and environmental impact. If audiences believe systems might achieve subjectivity, regulatory focus shifts toward protecting or containing 'conscious' entities, creating massive liability ambiguity where technology companies can deflect responsibility for their creations by claiming the systems possess autonomous subjective intent.

Accountability Analysis:

  • Actor Visibility: Partial (some attribution)
  • Analysis: The text uses the pronoun 'we' ('If we want to consider developing'), which partially acknowledges human agency but diffuses it into a generalized, abstract collective of humanity or the scientific community. It fails to name the specific technology corporations and defense agencies that actually fund and direct AI development. This generic 'we' masks the asymmetrical power dynamics of the tech industry, presenting AI development as a shared human endeavor rather than a proprietary corporate enterprise driven by profit motives.

4. Game Theory Execution as Intellectual Dominance​

Quote: "this AI model was able to defeat the number one human champion in Go, the famous Chinese game"

  • Frame: Statistical optimization as competitive human victory
  • Projection: The text maps the conscious, emotionally fraught human experience of competition and victory onto the execution of a game-tree search algorithm. By stating the model 'was able to defeat' a human champion, the text projects intention, strategic desire, and knowing dominance onto an AI system. A human player understands the game, feels the pressure, holds beliefs about the opponent's strategy, and consciously adapts. The AI model, specifically AlphaGo, merely processes board states through reinforcement learning to maximize a reward function based on probability metrics. It does not 'know' it is playing a game, does not understand the concept of winning, and experiences no triumph. The metaphor replaces the mechanistic reality of statistical token generation with the agential drama of a conscious duel.
  • Acknowledgment: Direct (Unacknowledged) (The statement 'was able to defeat the number one human champion' is presented as a literal, historical fact without any framing to indicate it is a metaphor for computational superiority.)
  • Implications: Framing algorithms as 'defeating' human champions creates a narrative of technological supremacy that profoundly influences social and political trust. It constructs the illusion of an autonomous, superior mind capable of outsmarting humanity, which inflates public anxiety and capability overestimation. This unwarranted trust in the model's 'intelligence' can lead policymakers to assume these systems possess generalizable cognitive superiority, blinding them to the brittle, domain-specific nature of the algorithm and the massive amounts of human engineering, hardware, and trial-and-error required for such a narrow optimization task.

Accountability Analysis:

  • Actor Visibility: Hidden (agency obscured)
  • Analysis: The text identifies the 'AI model' as the sole actor that 'was able to defeat' the human champion. This entirely obscures the massive team of DeepMind engineers, data scientists, and corporate executives who actually designed the system, selected the training parameters, and invested millions of dollars in compute power to achieve this result. The agentless construction allows the technology company to project an aura of autonomous machine intelligence, obscuring the human labor and corporate resources that actually 'defeated' the human player.

5. Algorithmic Rigidity as Psychological Inflexibility​

Quote: "AI systems are really efficient in specific tasks - such as playing Chess against the best human player in the world - exactly because they are not adaptive: because they cannot use the same internal timescales and apply it to other tasks."

  • Frame: Computational narrowness as a lack of psychological adaptability
  • Projection: The metaphor maps the human psychological trait of being 'adaptive'—the conscious ability to transfer knowledge across domains, recognize novel contexts, and alter beliefs—onto the structural constraints of neural network weights. By describing AI systems as 'not adaptive' due to their inability to 'use the same internal timescales', the authors project a cognitive deficiency onto a mathematical artifact. This implies the system is trying to 'know' or 'understand' across domains but fails. In reality, the AI processes specific data distributions; its inability to play both Chess and Go with the same weights is a mechanistic reality of its architecture, not a failure of cognitive adaptation. It replaces the mechanical explanation of static tensor values with an agential explanation of cognitive rigidity.
  • Acknowledgment: Direct (Unacknowledged) (The text states 'they are not adaptive' as a direct property of the AI systems, utilizing cognitive terminology to describe computational limitations without acknowledging the metaphor.)
  • Implications: While seemingly critical of AI, using cognitive terms like 'not adaptive' still validates the underlying illusion that the system possesses mind-like qualities, just deficient ones. It reinforces the assumption that if engineers simply tweak the architecture (e.g., adding 'timescales'), the system will achieve genuine, conscious adaptability. This maintains the broader narrative of imminent artificial general intelligence, driving unwarranted investment and regulatory panic while distracting from the mundane but immediate risks of deploying brittle, narrow statistical processors in complex social environments.

Accountability Analysis:

  • Actor Visibility: Hidden (agency obscured)
  • Analysis: The text presents the limitation ('they are not adaptive') as an inherent flaw of the 'AI systems' themselves. It obscures the fact that human engineers intentionally design these systems for narrow, highly specific tasks to maximize commercial efficiency. The lack of adaptability is a design choice driven by the economics of machine learning, not an autonomous failure of the machine. Naming the actors would reveal that companies choose to deploy narrow optimization tools because building generalized models is computationally and financially prohibitive.

6. Data Parsing as Passive Sensation​

Quote: "AI models passively process their inputs, lacking the ability to actively shape or align them with different contexts or circumstances."

  • Frame: Computational data routing as sensory perception
  • Projection: This passage maps the biological, conscious experience of sensory perception onto the mathematical routing of data through artificial neural networks. By contrasting 'passive processing' with the 'ability to actively shape' inputs, the text projects the qualities of a conscious, intending agent onto a computational system. Human subjects actively orient themselves to the world, consciously selecting stimuli based on internal goals, beliefs, and an integrated sense of self. AI models do not 'passively process' in a sensory or psychological sense; they mechanistically execute matrix multiplications on input tensors. The text implies the AI is a deficient 'knower' that fails to actively understand its context, rather than recognizing it as a non-conscious artifact completely incapable of either active or passive subjective experience.
  • Acknowledgment: Direct (Unacknowledged) (The phrase 'passively process their inputs, lacking the ability to actively shape' is presented as a literal description of the AI's functional behavior.)
  • Implications: By criticizing AI for being 'passive' rather than 'active', the text inadvertently validates the premise that AI could theoretically be an active, conscious subject. This maintains the illusion of mind by merely categorizing the AI as a lesser, more passive mind. It affects policy and trust by suggesting that the risks of AI stem from its 'passive' nature rather than its lack of actual comprehension. If audiences believe AI merely lacks 'active shaping', they may overestimate the reliability of models once engineers claim to have introduced 'active' feedback loops or 'agentic' workflows, misunderstanding these mechanistic updates as the arrival of conscious understanding.

Accountability Analysis:

  • Actor Visibility: Hidden (agency obscured)
  • Analysis: The passage attributes the 'passive' processing solely to the 'AI models'. It entirely obscures the fact that human data workers, engineers, and platform designers are the ones who actively shape, filter, and align the inputs before they ever reach the model. The model's supposed 'passivity' is actually the result of massive, invisible human labor involved in data annotation, formatting, and prompt engineering. Displacing this agency onto the AI hides the immense human workforce required to make these systems function.

7. Generative Architecture as Independent Agency​

Quote: "since its data-base is only grounded on Go: for these reasons, a different model (i.e., AlphaZero) had to be created to beat the best human player in chess."

  • Frame: Software engineering constraints as autonomous agent limitations
  • Projection: This passage maps the mechanical limitations of a specific software instance onto the concept of a restricted conscious entity. By stating that a different model 'had to be created to beat the best human player', the text projects the role of a competitive agent onto AlphaZero. AlphaZero does not 'beat' anyone; it computes probabilistically optimal outputs. The framing suggests that one 'agent' (AlphaGo) was not smart enough to understand chess, so a new 'agent' (AlphaZero) had to be born to conquer the new domain. This obscures the mechanistic reality that a neural network trained on one statistical distribution cannot process another without entirely new training parameters. It anthropomorphizes the software version as a distinct, intentional gladiator rather than a reconfigured mathematical tool.
  • Acknowledgment: Direct (Unacknowledged) (The necessity that a 'different model... had to be created to beat the best human player' is stated directly, without any linguistic markers indicating metaphorical use.)
  • Implications: This framing dramatically inflates the perceived autonomy and conscious intention of the software. By framing the creation of AlphaZero as necessary to 'beat' a human, it constructs a narrative of escalating machine-human warfare. This unwarranted agential framing shifts public understanding away from the reality of corporate technology demonstrations toward a science-fiction paradigm of conscious machines. Such capability overestimation encourages audiences to trust AI with complex, strategic decisions in the real world, erroneously believing the system possesses a conscious drive to 'win' and 'understand' its environment rather than merely executing localized statistical optimization.

Accountability Analysis:

  • Actor Visibility: Hidden (agency obscured)
  • Analysis: The passive construction 'a different model... had to be created' completely erases the agency of DeepMind and Google executives. The decision to create a new model to play chess was a deliberate PR and research strategy designed to increase corporate valuation and attract talent, not a spontaneous necessity. By hiding the corporate actors, the text makes technological development appear as an inevitable evolutionary force rather than a series of calculated, profit-driven decisions made by extremely powerful human institutions.

8. Algorithmic Challenges as Existential Struggles​

Quote: "While AI may surpass in processing information efficiently, their essential challenge lies in replicating the integrated temporal dynamics that contribute to human subjectivity."

  • Frame: Engineering hurdles as the conscious struggles of a synthetic mind
  • Projection: The metaphor maps human existential and developmental challenges onto the technical limitations of algorithmic engineering. By stating that AI's 'essential challenge lies in replicating... human subjectivity', the text projects an intention and a conscious struggle onto the AI itself. A conscious being faces challenges, understands its goals, and strives to overcome its limitations. An AI system has no challenges, no desires, and no intention to replicate human subjectivity. It merely processes the weights it is given. The projection suggests the AI is actively trying to 'know' the world but is currently limited to just 'processing' it. This entirely obscures the mechanistic reality that AI is an inert tool being shaped by researchers, incorrectly granting it the status of a striving protagonist.
  • Acknowledgment: Direct (Unacknowledged) (The text states 'their essential challenge lies in replicating' without any scare quotes or meta-commentary, presenting the machine's technical barrier as its own literal struggle.)
  • Implications: Framing technical limitations as the 'essential challenge' of the AI itself fosters a profound epistemic confusion regarding machine autonomy. It suggests to audiences that AI systems are actively evolving entities with intrinsic drives to become more human. This inflates the perceived sophistication of the technology and obscures the liability architecture. If AI is perceived as an autonomous entity struggling to achieve subjectivity, the catastrophic failures of the system are more likely to be viewed as tragic accidents of evolution rather than negligent engineering decisions made by technology corporations releasing unsafe products.

Accountability Analysis:

  • Actor Visibility: Hidden (agency obscured)
  • Analysis: The text assigns the 'essential challenge' to the AI itself ('their essential challenge'). This agentless construction completely displaces the agency of the human neuroscientists, computer scientists, and technology firms who are actually undertaking the 'challenge' of building more complex systems. The AI has no challenge; the researchers do. This linguistic displacement serves to insulate developers from accountability by treating the AI as an independent organism on its own developmental trajectory, rather than a proprietary product engineered for commercial and academic gain.

Task 2: Source-Target Mapping​

About this task

For each key metaphor identified in Task 1, this section provides a detailed structure-mapping analysis. The goal is to examine how the relational structure of a familiar "source domain" (the concrete concept we understand) is projected onto a less familiar "target domain" (the AI system). By restating each quote and analyzing the mapping carefully, we can see precisely what assumptions the metaphor invites and what it conceals.

Mapping 1: A conscious, developing human mind (knower) engaging with the world through subjective experience, forming justified beliefs, and making deliberate choices. → The iterative optimization of weights in an artificial neural network (processing) using backpropagation and statistical pattern matching over large datasets.​

Quote: "This includes the ability to learn from experience, adapt to new information, understand natural language, recognize patterns, and make decisions."

  • Source Domain: A conscious, developing human mind (knower) engaging with the world through subjective experience, forming justified beliefs, and making deliberate choices.
  • Target Domain: The iterative optimization of weights in an artificial neural network (processing) using backpropagation and statistical pattern matching over large datasets.
  • Mapping: The structural relationship of a human encountering the world, extracting meaning, and consciously modifying behavior (learning/understanding) is mapped onto the algorithmic process of a machine adjusting tensor values to minimize a loss function. The mapping invites the assumption that the AI system possesses an internal, subjective awareness of the data it processes, transforming mathematical correlation into conscious semantic comprehension and active decision-making.
  • What Is Concealed: This mapping completely conceals the absence of semantic grounding, subjective awareness, and truth-evaluation in AI systems. It obscures the mechanistic realities of token prediction, gradient descent, and the massive human labor required to curate the 'experience' (training data). Transparency is further blocked because it projects an accessible psychological state onto what are often proprietary, opaque black-box models, exploiting the audience's intuition to mask corporate algorithmic operations.
Show more...

Mapping 2: Conscious human reasoning, logical deduction, and intentional problem-solving by a rational agent. → The execution of programmed algorithms and statistical models designed to optimize outputs for specific, pre-defined quantitative metrics.​

Quote: "The ultimate goal of artificial intelligence is to create systems that can simulate and replicate human cognitive abilities, allowing machines to perform complex tasks and solve problems in a manner similar to human thought processes."

  • Source Domain: Conscious human reasoning, logical deduction, and intentional problem-solving by a rational agent.
  • Target Domain: The execution of programmed algorithms and statistical models designed to optimize outputs for specific, pre-defined quantitative metrics.
  • Mapping: The relational structure of a human mind evaluating a problem, employing deductive or inductive logic, and arriving at a reasoned conclusion is projected onto a computer executing code. The mapping assumes that because the output resembles human work, the internal generative mechanism must also resemble conscious human thought, inviting the assumption that the machine 'knows' why it is generating a specific output.
  • What Is Concealed: This mapping hides the fundamental dissimilarity between semantic reasoning and syntactic processing. It obscures the reality that AI does not possess a causal model of the world, does not understand the 'problems' it solves, and merely correlates high-probability patterns from its training data. It also conceals the proprietary nature of the algorithms and the subjective human decisions encoded into the optimization metrics, masking engineering choices as autonomous machine cognition.

Mapping 3: The biological, phenomenological reality of human consciousness, characterized by 'mineness' and a continuous subjective perspective. → The complex structural integration of multi-modal, temporal data streams within an engineered computational architecture.​

Quote: "If we want to consider developing AI systems that can have a subjective point of view, we will need to replicate the several timescales - and the complex physiology behind them."

  • Source Domain: The biological, phenomenological reality of human consciousness, characterized by 'mineness' and a continuous subjective perspective.
  • Target Domain: The complex structural integration of multi-modal, temporal data streams within an engineered computational architecture.
  • Mapping: The ontological structure of conscious awareness—the felt experience of being a subject—is mapped directly onto the mechanical integration of data processing rates. This projects the highest form of conscious 'knowing' onto advanced 'processing', assuming that subjectivity is merely a complex architectural feature that can be engineered by synchronizing data streams, rather than an intrinsically biological reality.
  • What Is Concealed: This mapping conceals the unbridgeable explanatory gap between information processing and phenomenal experience. It obscures the mechanistic reality that no matter how complex the data integration or timescale synchronization, the system remains a non-conscious artifact executing instructions. It hides the lack of internal subjective reality, distracting audiences from how these complex, proprietary architectures actually function as data-harvesting tools for corporate entities.

Mapping 4: A human competitor who understands the rules, desires victory, strategizes consciously, and experiences the emotional weight of a contest. → A reinforcement learning algorithm navigating a massive state-space to maximize a mathematical reward function by outputting board coordinates.​

Quote: "this AI model was able to defeat the number one human champion in Go, the famous Chinese game"

  • Source Domain: A human competitor who understands the rules, desires victory, strategizes consciously, and experiences the emotional weight of a contest.
  • Target Domain: A reinforcement learning algorithm navigating a massive state-space to maximize a mathematical reward function by outputting board coordinates.
  • Mapping: The relational dynamic of two conscious agents battling for intellectual supremacy is mapped onto a statistical machine processing a mathematical matrix against a human. The mapping invites the assumption that the AI possesses strategic intent, a desire to win, and a conscious understanding of the game's stakes, projecting the qualities of a conscious 'knower' onto a blind optimization process.
  • What Is Concealed: This mapping obscures the brittle, narrow nature of the algorithm and the massive disparity in energy consumption and training data between the human and the machine. It hides the millions of simulated games and the vast team of DeepMind engineers who constructed the environment. The text relies on the opacity of the model's processing to exploit rhetorical drama, concealing the reality of a corporate statistical tool out-computing a human.

Mapping 5: A human mind that is cognitively rigid, psychologically inflexible, or unable to generalize learning to new contexts. → The mathematical reality of a trained neural network whose weights have been fixed via backpropagation for a specific input distribution.​

Quote: "AI systems are really efficient in specific tasks - such as playing Chess against the best human player in the world - exactly because they are not adaptive: because they cannot use the same internal timescales and apply it to other tasks."

  • Source Domain: A human mind that is cognitively rigid, psychologically inflexible, or unable to generalize learning to new contexts.
  • Target Domain: The mathematical reality of a trained neural network whose weights have been fixed via backpropagation for a specific input distribution.
  • Mapping: The psychological structure of a human failing to adapt to a new environment is mapped onto the structural constraints of a machine learning model. By calling the system 'not adaptive', it projects a failed attempt at conscious generalization onto a machine that simply lacks the mathematical architecture to process out-of-distribution data. It assumes the machine should 'know' how to adapt but cannot.
  • What Is Concealed: This mapping conceals the purely mathematical reason why models fail outside their training distribution: they lack generalized intelligence entirely. It hides the fact that these models do not 'understand' anything; they merely fit a specific curve. It also obscures the economic and engineering decisions by corporations to build highly specialized, profitable tools rather than generalized systems, framing a design choice as a psychological deficiency.

Mapping 6: A conscious biological organism that receives sensory data but lacks the motor function, attention span, or cognitive agency to actively interact with its environment. → The deterministic execution of matrix multiplications on input data tensors within a neural network.​

Quote: "AI models passively process their inputs, lacking the ability to actively shape or align them with different contexts or circumstances."

  • Source Domain: A conscious biological organism that receives sensory data but lacks the motor function, attention span, or cognitive agency to actively interact with its environment.
  • Target Domain: The deterministic execution of matrix multiplications on input data tensors within a neural network.
  • Mapping: The biological dichotomy of active versus passive perception is mapped onto computational data routing. The metaphor projects the potential for conscious agency onto the machine by criticizing its 'passivity'. It invites the assumption that AI could eventually 'actively shape' its context like a conscious subject, blurring the line between subjective sensory orientation and automated data parsing.
  • What Is Concealed: This mapping hides the fact that computers are neither active nor passive; they are inert objects executing commands. It completely conceals the massive, highly active human infrastructure required to shape, format, and align the inputs before the AI processes them. By focusing on the model's 'passivity', it masks the proprietary, opaque human decisions regarding data curation, reinforcement learning from human feedback (RLHF), and system architecture.

Mapping 7: An evolving lineage of intelligent agents where a new, more capable individual is born to conquer a challenge its predecessor could not. → The manual engineering, coding, and retraining of a new software architecture and weight distribution by a corporate research team.​

Quote: "since its data-base is only grounded on Go: for these reasons, a different model (i.e., AlphaZero) had to be created to beat the best human player in chess."

  • Source Domain: An evolving lineage of intelligent agents where a new, more capable individual is born to conquer a challenge its predecessor could not.
  • Target Domain: The manual engineering, coding, and retraining of a new software architecture and weight distribution by a corporate research team.
  • Mapping: The evolutionary or developmental progression of an autonomous species is mapped onto the iteration of software versions. The text projects autonomous agency and historical destiny onto the software models, inviting the assumption that the models themselves are striving to 'beat' humans and that their creation is an inevitable progression of machine intelligence rather than a corporate project.
  • What Is Concealed: This mapping utterly conceals the human engineers, the corporate resources, the server farms, and the profit motives behind the creation of AlphaZero. It hides the mechanistic reality that software does not evolve or 'have to be created' autonomously; it is deliberately built. By projecting agency onto the software, the text rhetorically shields the opaque corporate entities from scrutiny regarding their motives and resource consumption.

Mapping 8: A conscious protagonist facing an existential, developmental, or evolutionary hurdle in its quest for growth or self-realization. → The technical, mathematical, and hardware limitations faced by human engineers attempting to build more complex machine learning architectures.​

Quote: "While AI may surpass in processing information efficiently, their essential challenge lies in replicating the integrated temporal dynamics that contribute to human subjectivity."

  • Source Domain: A conscious protagonist facing an existential, developmental, or evolutionary hurdle in its quest for growth or self-realization.
  • Target Domain: The technical, mathematical, and hardware limitations faced by human engineers attempting to build more complex machine learning architectures.
  • Mapping: The narrative structure of a conscious subject struggling against its limitations is mapped onto an engineered artifact's technical boundaries. The mapping projects subjective desire, intention, and a conscious 'challenge' onto the AI. It invites the audience to view the algorithm not as a tool being optimized by humans, but as an emerging lifeform attempting to achieve the ultimate status of a conscious 'knower'.
  • What Is Concealed: This mapping fundamentally conceals the non-conscious, artifactual nature of the technology. It hides the reality that AI possesses no desires, faces no challenges, and is completely indifferent to human subjectivity. Furthermore, it obscures the actual human researchers and funding institutions who are directing these technical goals, masking their proprietary scientific agendas behind the romanticized struggle of a synthetic mind.

Task 3: Explanation Audit (The Rhetorical Framing of "Why" vs. "How")​

About this task

This section audits the text's explanatory strategy, focusing on a critical distinction: the slippage between "how" and "why." Based on Robert Brown's typology of explanation, this analysis identifies whether the text explains AI mechanistically (a functional "how it works") or agentially (an intentional "why it wants something"). The core of this task is to expose how this "illusion of mind" is constructed by the rhetorical framing of the explanation itself, and what impact this has on the audience's perception of AI agency.

Explanation 1​

Quote: "These models consist of many layers interconnected ('artificial neurons') with different weights that are regulate throughout the training phase of the model. These weights determine the strength of the connection which will impact in the relevance of each input provided to the model."

  • Explanation Types:

    • Theoretical: Embeds in deductive framework, may invoke unobservable mechanisms
    • Functional: Explains behavior by role in self-regulating system with feedback

  • Analysis (Why vs. How Slippage): This explanation frames the AI system purely mechanistically (how it works), detailing the structural architecture of 'layers', 'artificial neurons', and 'weights'. By focusing on the regulatory mechanisms during the training phase, the text emphasizes the mathematical and structural reality of the system. This functional and theoretical framing correctly positions the AI as a computational artifact rather than an autonomous agent. However, while it avoids agential slippage for the machine, the use of passive voice ('are regulate[d]', 'provided to the model') obscures the human engineers who design the architecture, select the training data, and define the loss function that dictates how these weights are adjusted. The explanation emphasizes the internal mechanics but conceals the external human agency driving those mechanics.

  • Consciousness Claims Analysis: This passage avoids attributing conscious states. It strictly uses mechanistic verbs ('consist', 'regulate', 'determine', 'impact') rather than consciousness verbs ('knows', 'understands'). The text correctly assesses the system as one that processes data ('relevance of each input') rather than a system that 'knows' a ground truth. By describing the actual mechanistic process—how weights determine connection strength and impact input relevance—the author successfully averts the curse of knowledge dynamics. The reader is provided with a technically precise description of a statistical process without any projection of subjective awareness or justified belief. The epistemic claim is appropriately limited to mathematical functions within a defined architecture.

  • Rhetorical Impact: By framing the system mechanistically, the rhetorical impact is one of demystification. The audience is encouraged to perceive the AI not as an autonomous mind, but as a complex mathematical tool. This mitigates the risk of unwarranted relation-based trust, as the transparency regarding 'weights' and 'layers' reminds the reader of the system's artifactual nature. If audiences understand AI through this theoretical lens, they are more likely to question the data inputs and engineering parameters rather than assuming the model possesses an objective, conscious grasp of reality.

Show more...

Explanation 2​

Quote: "The ultimate goal of artificial intelligence is to create systems that can simulate and replicate human cognitive abilities, allowing machines to perform complex tasks and solve problems in a manner similar to human thought processes."

  • Explanation Types:

    • Intentional: Refers to goals/purposes, presupposes deliberate design
    • Dispositional: Attributes tendencies or habits

  • Analysis (Why vs. How Slippage): This explanation blends intentional framing (the 'ultimate goal') with dispositional framing regarding what the machines will 'perform'. The text frames the overarching project agentially ('solve problems', 'human thought processes'), emphasizing the simulation of consciousness while obscuring the mechanistic reality of how that simulation is achieved. By explaining AI's purpose through the lens of human cognition, the text emphasizes the desired outcome (human-like behavior) while entirely obscuring the statistical, non-cognitive methods (gradient descent, matrix multiplication) used to achieve it. This slippage into agential framing constructs a narrative where machines are essentially emergent minds, shifting focus away from the human designers to the supposed autonomous capabilities of the artifact.

  • Consciousness Claims Analysis: The passage flirts heavily with attributing conscious states by using phrases like 'cognitive abilities', 'solve problems', and 'human thought processes'. While hedged with 'simulate and replicate', the language persistently bridges the gap between processing and knowing. The author falls victim to the curse of knowledge by projecting human epistemological frameworks ('thought processes') onto systems that merely execute statistical correlations. There is a complete absence of actual mechanistic description; the technical reality of how an AI generates outputs is entirely replaced by a metaphorical projection of human subjective awareness and rational problem-solving, falsely elevating a processing engine to the status of a potential knower.

  • Rhetorical Impact: This intentional, anthropomorphic framing dramatically shapes audience perception, fostering an illusion of machine autonomy and cognitive sophistication. By explicitly linking machine performance to 'human thought processes', the text encourages audiences to extend relation-based trust to the AI, assuming it operates with logic, context, and understanding. This inflates perceived capabilities and alters risk assessment: if audiences believe the AI 'thinks', they may defer to its judgment in high-stakes scenarios, misinterpreting statistical probability as reasoned wisdom, thereby increasing vulnerability to algorithmic bias and hallucination.

Explanation 3​

Quote: "This highlights how the neural network architecture in current AI models is fixed after the training phase. The only method to incorporate new information is to retrain the entire model, resulting in a new fixed structure."

  • Explanation Types:

    • Empirical Generalization: Subsumes events under timeless statistical regularities
    • Functional: Explains behavior by role in self-regulating system with feedback

  • Analysis (Why vs. How Slippage): This explanation frames the AI system strictly mechanistically (how it operates). By outlining the constraints of a 'fixed' neural network architecture post-training, the text emphasizes the rigid, non-adaptive reality of current machine learning models. The choice to use an empirical generalization about how the models incorporate 'new information' strips away the illusion of continuous, conscious learning. This framing actively obscures any agential characteristics, presenting the AI as a static mathematical artifact. However, the passive construction ('the only method... is to retrain') slightly diffuses human responsibility, obscuring the specific corporations and engineers who must bear the massive financial and environmental costs of this retraining process.

  • Consciousness Claims Analysis: This passage successfully avoids attributing conscious states. It correctly distinguishes between human 'knowing' (which is continuous and adaptable) and machine 'processing' (which is fixed and requires structural retraining). There are no consciousness verbs; the epistemic claim is limited to the system's structural capacity to 'incorporate new information' via 'retrain[ing]'. The author avoids the curse of knowledge by refusing to project human learning onto the machine, instead providing an accurate mechanistic description of a frozen neural network. This technical precision clarifies that the system does not 'know' or 'understand' new facts; it merely requires a new mathematical structure to process new data distributions.

  • Rhetorical Impact: The mechanistic framing significantly alters the audience's perception of AI risk and autonomy. By explicitly detailing the 'fixed' nature of the architecture, the text dismantles the illusion of an ever-evolving, conscious intelligence. This reduces unwarranted trust, making it clear that the AI cannot adapt to novel situations or exercise judgment outside its training. Policymakers and audiences who internalize this functional limitation are far less likely to attribute autonomous agency to the system, recognizing instead that any 'learning' requires deliberate human intervention and structural overhaul.

Explanation 4​

Quote: "AI models passively process their inputs, lacking the ability to actively shape or align them with different contexts or circumstances."

  • Explanation Types:

    • Dispositional: Attributes tendencies or habits

  • Analysis (Why vs. How Slippage): This explanation utilizes dispositional framing to explain the behavioral tendencies of AI models, framing them primarily mechanistically ('passively process') but defining them against an agential standard ('lacking the ability to actively shape'). By focusing on what the AI 'lacks' compared to human cognition, the text emphasizes a perceived psychological deficiency rather than a structural reality. This framing subtly maintains the agential paradigm by criticizing the machine for not acting like a conscious subject. The explanation obscures the fact that computers are neither active nor passive in a subjective sense; they simply execute code. Furthermore, attributing the 'passive' processing to the AI hides the highly active human labor involved in data curation and system design.

  • Consciousness Claims Analysis: While the passage uses the mechanistic verb 'process', it flirts with consciousness attribution by contrasting it with the 'ability to actively shape or align' contexts. This assessment edges into the territory of 'knowing' versus 'processing'. The author projects a human epistemological framework onto the machine, suggesting that a true knower would 'actively shape' its context. By viewing the mechanistic reality through the lens of human subjective agency (the curse of knowledge), the text fails to provide a purely technical description of data parsing, instead offering a psychological critique of a mathematical function.

  • Rhetorical Impact: This framing shapes audience perception by reinforcing the idea that AI is on a spectrum of consciousness—currently 'passive', but perhaps one day 'active'. This subtly inflates the perceived potential of the technology. If audiences view the AI as merely lacking 'active' shaping abilities, they may falsely assume the system possesses foundational understanding but just needs more dynamic feedback loops. This affects reliability assessments, as users might trust an 'active' future model as a conscious agent, misunderstanding that even dynamic algorithms remain non-conscious processors devoid of justified belief.

Explanation 5​

Quote: "If we want to consider developing AI systems that can have a subjective point of view, we will need to replicate the several timescales - and the complex physiology behind them - that we know are part of what it means to be conscious."

  • Explanation Types:

    • Intentional: Refers to goals/purposes, presupposes deliberate design
    • Theoretical: Embeds in deductive framework, may invoke unobservable mechanisms

  • Analysis (Why vs. How Slippage): This passage uses a hybrid intentional and theoretical explanation. It outlines a deliberate design goal ('developing AI systems') while embedding it within a theoretical framework linking timescales to consciousness. The text slips dramatically from mechanistic framing (replicating timescales/physiology) to profound agential framing ('subjective point of view', 'conscious'). This choice emphasizes a hypothetical future where machines transcend mechanism to become conscious subjects. By framing subjectivity as an engineering problem (replicating timescales), the explanation obscures the profound ontological gap between mathematical processing and lived phenomenological experience. It also uses a generalized 'we', diffusing the specific corporate and institutional agency driving this speculative development.

  • Consciousness Claims Analysis: The passage explicitly addresses the attribution of conscious states, suggesting that a 'subjective point of view' can be engineered into an AI. It blurs the line between knowing and processing by proposing that replicating mechanical timescales will spontaneously generate subjective awareness ('what it means to be conscious'). The author succumbs deeply to the curse of knowledge, projecting the human experience of consciousness onto a speculative computational architecture. Instead of describing actual mechanistic processes, the text offers a neurophilosophical fantasy where integrating data processing rates magically crosses the threshold into justified belief, subjective feeling, and true 'knowing'.

  • Rhetorical Impact: This framing has a massive rhetorical impact, profoundly inflating the audience's perception of AI's potential autonomy and sophistication. By presenting machine consciousness as a solvable engineering puzzle rather than an ontological impossibility, the text legitimizes the narrative of impending Artificial General Intelligence (AGI). This fosters deep, relation-based trust (or existential dread) toward future systems. If audiences accept that AI can achieve a 'subjective point of view', policy and ethical frameworks will pivot toward machine rights and containment, dangerously distracting from the immediate, material harms inflicted by the human corporations deploying non-conscious statistical systems today.

Task 4: AI Literacy in Practice - Reframing Anthropomorphic Language​

About this task

This section proposes alternative language for key anthropomorphic phrases, offering more mechanistic and precise framings that better reflect the actual computational processes involved. Each reframing attempts to strip away the projections of intention, consciousness, or agency that are embedded in the original language.

V3 Enhancement: A fourth column addresses human agency restoration—reframing agentless constructions to name the humans responsible for design and deployment decisions.

Original Anthropomorphic FrameMechanistic ReframingTechnical Reality CheckHuman Agency Restoration
This includes the ability to learn from experience, adapt to new information, understand natural language, recognize patterns, and make decisions.This includes the capacity to adjust internal mathematical weights via backpropagation based on training datasets, update parameters when exposed to new statistical distributions, classify and generate text tokens based on probability, identify statistical correlations, and output predictions that trigger automated actions.The AI does not 'know' or 'understand' meaning; it processes sequential tokens and calculates embedding space proximity based on probability distributions from its training data. It does not 'learn' or form beliefs; it executes mathematical optimization routines.Engineers at technology companies design the algorithms, curate the massive datasets, define the optimization parameters, and ultimately choose how the system's statistical predictions are deployed in real-world applications.
allowing machines to perform complex tasks and solve problems in a manner similar to human thought processes.allowing computational systems to execute complex, multi-layered statistical operations and optimize outputs for predefined quantitative metrics, leveraging pattern recognition architectures designed by human programmers.The machine does not experience 'thought processes' or consciously 'solve problems'. It mechanically processes vector mathematics to minimize a loss function, devoid of any subjective awareness, causal understanding, or logical reasoning.Corporate researchers and computer scientists actively design and structure these algorithms to mimic human outputs, deliberately defining the 'problems' to be optimized and profiting from the resulting automation.
this AI model was able to defeat the number one human champion in Go, the famous Chinese gamethe reinforcement learning algorithm generated probability-based moves that outscored the strategies of the human champion in the constrained, mathematical environment of Go.The model does not 'know' it is playing a game, hold a desire to win, or strategize consciously. It calculates optimal state-space trajectories based on billions of simulated iterations executed during its human-directed training phase.DeepMind engineers and Google executives built, trained, and deployed this highly specialized statistical model, utilizing massive computing power to generate outputs that outscored the human player in a highly publicized corporate demonstration.
AI systems are really efficient in specific tasks... exactly because they are not adaptive: because they cannot use the same internal timescales and apply it to other tasks.Current neural network architectures are highly optimized for specific statistical distributions because their mathematical weights remain fixed post-training; they lack the architectural capacity to generalize probabilities across fundamentally different data domains.The system's lack of adaptability is a mathematical reality of static tensors, not a psychological failure to 'know' or adapt. It processes inputs exactly as its fixed architecture dictates, without any conscious intent to generalize.Technology companies intentionally design and deploy these narrow, fixed-weight optimization tools because building generalized architectures is computationally, financially, and practically prohibitive for their immediate commercial objectives.
AI models passively process their inputs, lacking the ability to actively shape or align them with different contexts or circumstances.Neural networks mathematically execute operations on input tensors strictly according to their programmed architecture, lacking any autonomous mechanism to alter their own structural parameters or recontextualize the data streams provided to them.The system does not experience 'passive' sensation or lack 'active' cognitive agency. It is an inert mathematical artifact that merely executes programmed instructions based on the statistical properties of the data it is fed.Human data annotators, prompt engineers, and platform developers are the actors who actively shape, filter, and align the context of the inputs before feeding them into the commercial models they manage.
a different model (i.e., AlphaZero) had to be created to beat the best human player in chess.the original software architecture was mathematically incompatible with chess, requiring the research team to code, train, and deploy an entirely new neural network with different parameters optimized specifically for the state-space of chess.Software models do not possess an agential drive that requires them to be 'created to beat' humans. A new model processes a new mathematical matrix; it does not possess a conscious desire to conquer a new intellectual domain.Executives and researchers at DeepMind deliberately chose to invest massive financial and computational resources to build and train a new system, driven by corporate goals for technological prestige and algorithmic development.
While AI may surpass in processing information efficiently, their essential challenge lies in replicating the integrated temporal dynamics that contribute to human subjectivity.While neural networks execute statistical operations rapidly, the primary structural limitation faced by engineers is the inability to design architectures that integrate multi-modal temporal data in a way that structurally mimics biological brains.The AI system has no 'challenge' and is not striving to achieve human subjectivity. It merely processes the weights it currently possesses. Subjectivity is an organic phenomenon, not a computational barrier the machine is trying to cross.Neuroscientists, AI researchers, and the institutions funding them face the technical challenge of building more complex data-integration architectures; the AI is simply the inert product of their ongoing engineering labor.
If we want to consider developing AI systems that can have a subjective point of view, we will need to replicate the several timescales...If researchers intend to build computational architectures that simulate the outward behaviors associated with a subjective point of view, they will need to engineer systems capable of mechanically integrating multiple rates of data processing.Replicating data processing timescales does not generate a 'knowing' conscious subject. The system will continue to mechanically process electrical signals and vector mathematics, remaining fundamentally devoid of qualitative feeling or justified belief.The scientific community and technology corporations are actively making decisions about whether to pursue and fund the engineering of these complex, multi-modal simulation architectures.

Task 5: Critical Observations - Structural Patterns​

Agency Slippage​

The text exhibits a profound and systematic agency slippage, oscillating predictably between assigning agential power to AI systems and retreating to mechanical descriptions when defending its core thesis. The pattern reveals a specific function: the text accepts the tech industry's agential vernacular as a baseline reality, only deploying mechanistic precision to deny the absolute highest tier of consciousness ('subjectivity'). Early in the text, slippage from mechanical to agential is abrupt and complete. When defining AI, the authors readily grant that systems 'learn from experience, adapt... understand natural language, recognize patterns, and make decisions'. This establishes the AI as a 'knower' and an autonomous actor. By utilizing verbs intrinsic to conscious cognition, the text projects an epistemological framework onto statistical processing. This 'curse of knowledge' is evident as the authors project their own human understanding of language onto the system's algorithmic token generation.

However, when the argument shifts to defending the neurophilosophical boundary of human subjectivity, the slippage reverses from agential back to mechanical. To prove AI lacks a 'point of view', the text suddenly relies on Brown's theoretical and functional explanations, describing AI as having 'weights' that are 'regulate[d]' and an architecture that is 'fixed'. The oscillation serves a distinct rhetorical function: it allows the authors to portray AI as an incredibly powerful, near-cognitive agent ('defeating human champions') while retaining human exceptionalism purely on the grounds of temporal integration.

Crucially, as agency flows TO the AI, it is simultaneously stripped FROM human actors. The text relies heavily on agentless passive constructions: models 'had to be created', 'inputs are provided', and AI is framed as the sole actor capable of 'understanding' or 'processing'. Corporations like Google/DeepMind, the engineers who adjust the weights, and the labor force annotating the data are entirely obscured. By establishing the AI as the primary agent—even a mechanistically flawed one—the text makes corporate engineering invisible. What becomes unsayable is that AI is not an evolving quasi-mind struggling to achieve subjectivity, but rather a brittle, proprietary statistical tool deliberately designed, deployed, and profited from by highly specific human institutions.

Metaphor-Driven Trust Inflation​

The metaphorical architecture of the text constructs a deeply ambiguous landscape of trust and authority. By employing language that grants cognitive capabilities to AI—such as 'understanding natural language' and 'solving problems'—the text inadvertently encourages audiences to extend relation-based trust to statistical processors. Relation-based trust relies on assumptions of sincerity, intention, and justified belief; it is the trust we place in a conscious 'knower'. When the text asserts that an AI 'understands', it signals to the reader that the system's outputs are the result of cognitive comprehension rather than probabilistic token prediction.

This anthropomorphic framing creates a dangerous transfer of trust. Human trust frameworks, built on the premise of mutual vulnerability and ethical intentionality, are inappropriately applied to machines executing matrix multiplications. Even as the authors attempt to limit this trust by denying the AI a 'subjective point of view', the concession of lower-level cognitive verbs ('learns', 'adapts') cements the system's perceived competence. The text implies that the AI is highly reliable in its 'thinking', only failing at the ultimate hurdle of conscious feeling.

Fascinatingly, the text manages system limitations by abruptly shifting to mechanical framing ('fixed weights', 'lack of active timescales'), while highlighting capabilities using agential framing ('defeats human champions'). This asymmetry is crucial: it constructs the AI as an autonomous genius when it succeeds, but as a mere tool when it fails. Through Brown's intentional and reason-based explanation types, the text constructs a sense that AI decisions are justified by 'human thought processes'. The stakes of this framing are immense. When audiences and policymakers extend relation-based trust to systems incapable of reciprocating or experiencing doubt, they become deeply vulnerable to automation bias. They are primed to accept algorithmic outputs—whether biased loan decisions, hallucinated medical advice, or flawed predictive policing—as the objective judgments of a conscious, problem-solving mind, rather than the statistical artifacts of a corporate data-processing engine.

Obscured Mechanics​

The anthropomorphic and consciousness-attributing language pervasive in the text serves to heavily veil the material, technical, and economic realities of artificial intelligence. Applying the 'name the corporation' test reveals a stark absence: the text consistently attributes actions to 'AI systems' or 'models' while entirely erasing the technology companies, executives, and engineering teams actually making decisions. When the text claims 'an AI model was able to defeat the number one human champion', it obscures DeepMind's massive financial investment, server infrastructure, and human ingenuity.

The text's reliance on consciousness verbs like 'knows' and 'understands' hides profound technical dependencies. Claiming a system 'understands natural language' completely conceals the statistical reality of token prediction, the absence of ground truth, the reliance on vast amounts of scraped training data, and the inherent lack of causal models. It masks the reality that model 'confidence' is purely a mathematical probability, not an epistemic state of certainty. Furthermore, the text frequently engages with proprietary, black-box systems without acknowledging the transparency obstacles this poses. Confident assertions about what the model 'learns' are made despite the academic community's lack of access to the model's underlying architecture and training corpora.

Materially, this metaphorical framing erases the massive energy consumption, carbon footprint, and physical infrastructure required to sustain these processing operations. Economically, it obscures the profit motives and business models of the tech giants driving this research. Perhaps most egregiously, it erases human labor. By framing the AI as a self-contained entity that 'learns from experience', the thousands of underpaid data annotators, RLHF workers, and content moderators who curate the system's 'experience' are rendered invisible. The primary beneficiaries of these concealments are the technology corporations themselves, as the agential framing shields them from scrutiny regarding their labor practices, environmental impact, and product safety. Replacing these metaphors with mechanistic language ('Google engineers optimized a statistical model using scraped data') instantly makes visible the corporate actors, the technical brittleness, and the human labor dependencies underlying the technology.

Context Sensitivity​

The distribution and intensity of anthropomorphic language across the text is not uniform but highly strategic, revealing a context-sensitive deployment of metaphor. In the introductory and definitional sections, anthropomorphism is incredibly dense. Here, consciousness claims are asserted forcefully: AI 'understands', 'learns', and 'makes decisions'. The text relies on this agential intensity to establish the significance of its subject matter, speaking to a lay audience using intuitive, narrative-driven terminology.

However, a stark register shift occurs when the text transitions to its neurophilosophical critique. When outlining why AI lacks 'subjectivity', the language abruptly shifts to mechanistic precision. 'Understanding' gives way to 'activation functions', 'rectified linear units', and 'fixed training phases'. The text establishes academic credibility through this localized mechanical language, utilizing it specifically to defend the uniqueness of human consciousness. Yet, even in the technical sections, a glaring asymmetry emerges regarding capabilities versus limitations. Capabilities are almost exclusively framed in agential terms: AI 'solves problems' and 'defeats champions'. Limitations are framed strictly in mechanical terms: the model 'cannot use internal timescales' and its 'neural network architecture is fixed'.

This asymmetry accomplishes a powerful rhetorical goal: it validates the tech industry's marketing narrative of superhuman machine intelligence while maintaining a philosophical firewall around human subjectivity. The text's anthropomorphism intensifies precisely when discussing the system's performance, literalizing what should be acknowledged metaphors ('X does Y' rather than 'X acts as if it does Y'). The strategic function of this pattern is to manage critique. By conceding the premise that AI 'thinks' and 'understands', the authors limit their philosophical battleground to the esoteric realm of 'mineness' and temporal integration. This pattern reveals an implied audience that already accepts the inevitability and cognitive power of AI, showing how even rigorous philosophical critiques can become trapped within the very corporate, anthropomorphic discourse they seek to evaluate.

Accountability Synthesis​

Accountability Architecture

This section synthesizes the accountability analyses from Task 1, mapping the text's "accountability architecture"—who is named, who is hidden, and who benefits from obscured agency.

Synthesizing the accountability analyses reveals a systemic architectural pattern of displaced responsibility. The text systematically constructs an 'accountability sink' where human agency vanishes, shifting responsibility away from corporate developers and onto the algorithms themselves. The dominant pattern is the pervasive use of agentless passive voice and the elevation of 'AI' as the sole grammatical and causal actor. Decisions regarding architecture, optimization, and deployment are framed not as human choices driven by profit, but as the inevitable actions of the models themselves or as abstract technical evolutions ('a different model had to be created').

Specific actors—OpenAI, DeepMind, data scientists, corporate executives—are never named. By erasing these actors, the text diffuses responsibility into the abstraction of 'the technology'. When problems or limitations arise ('they are not adaptive', 'passively process'), the accountability sink swallows the engineering decisions, framing these issues as intrinsic flaws of the autonomous machine rather than deliberate constraints chosen to maximize computational efficiency. If this framing is accepted by the public and policymakers, the liability implications are catastrophic. When an algorithmic system discriminates, hallucinates, or fails catastrophically, the language pre-conditions audiences to blame a 'glitch' in the AI's 'understanding' rather than holding the corporation liable for deploying a defective, structurally biased statistical tool.

Applying the 'name the actor' test radically alters this landscape. If 'an AI model defeated the human champion' becomes 'DeepMind engineers utilized massive compute to optimize a model to outscore the human', the questions change entirely. We no longer ask 'How smart is the machine?' but rather 'What resources did the corporation use, and what are their motives?' If 'AI lacks adaptability' becomes 'Developers chose to build brittle, fixed-weight models because generalized systems are too expensive', the lack of adaptability transforms from a philosophical trait to an economic decision. The text's obscuration of human agency overwhelmingly serves institutional and commercial interests, shielding tech giants from regulatory oversight by painting their proprietary tools as autonomous entities governed by the laws of evolution rather than the laws of liability.

Conclusion: What This Analysis Reveals​

The Core Finding

Synthesizing the metaphor and structure-mapping audits reveals two dominant, interconnecting anthropomorphic patterns within the text: 'Cognition as Computation' and 'Algorithmic Optimization as Intentional Agency'. The foundational pattern, upon which all others depend, is the initial concession that processing equates to cognitive knowing. By defining AI as possessing the 'ability to learn' and 'understand natural language', the text establishes an architecture of consciousness projection. Even though the authors explicitly aim to deny the highest level of consciousness—subjectivity—their foundational mapping grants the system the lower-tier conscious states of justified belief and semantic comprehension. This is the load-bearing pillar of the text's discourse: once the audience accepts that a matrix of static weights can 'understand', the leap to accepting that it can 'solve problems' or 'defeat champions' (Intentional Agency) becomes entirely logical. The text's sophistication lies in its complex analogical structure, where it uses precise neurophilosophical mechanics to gatekeep human 'mineness', but relies on crude, unacknowledged one-to-one mappings to describe the machine's actual operations. If the foundational pattern collapses—if we strictly define the AI as processing statistical correlations without 'knowing' anything—the entire narrative of the machine as a near-conscious competitor dissolves, revealing merely a complex, inert artifact.

Mechanism of the Illusion:​

The 'illusion of mind' is constructed through a highly specific rhetorical architecture that exploits the 'curse of knowledge' and a temporal sleight-of-hand. The central trick relies on the authors projecting their own epistemological framework—how human minds navigate language and games—onto the alien syntax of mathematical optimization. The text establishes the AI as a 'knower' immediately in the introduction, strategically blurring processing and knowing through the unhedged use of cognitive verbs ('learns', 'adapts'). This order is vital: by planting the assumption of machine comprehension early, the audience is primed to view all subsequent mechanical descriptions through an agential lens. The illusion is amplified by Brown's Intentional and Reason-Based explanation types, which continuously explain the system's functions by referencing human-like goals. The audience's vulnerability is deeply exploited here; humans are evolutionarily primed to detect agency, and the text's reliance on competitive, evolutionary language ('defeating champions', 'striving to replicate') triggers a narrative resonance that makes the illusion intuitive. Ultimately, the illusion is maintained not by a crude assertion of machine consciousness, but by a subtle, continuous oscillation: the text rigorously disproves that the machine 'feels', precisely so it can safely maintain the illusion that the machine 'thinks' and 'understands'.

Material Stakes:​

Categories: Regulatory/Legal, Epistemic, Social/Political

The consequences of framing mathematical processing as conscious knowing manifest as severe material stakes across multiple domains. In the Regulatory/Legal sphere, when discourse claims an AI 'understands natural language' rather than 'processes token probabilities', it fundamentally shifts liability architectures. Policymakers operating under the illusion of machine comprehension are more likely to draft regulations focusing on 'AI rights', algorithmic 'intent', or containment of autonomous actors, rather than focusing on product liability, data theft, and corporate negligence. The winners are technology corporations, who benefit from regulatory distraction and liability diffusion; the losers are the victims of algorithmic harm, who struggle to hold human actors accountable for 'machine errors'.

Epistemically, this metaphorical framing degrades public literacy. When the distinction between processing and knowing collapses, the public loses the conceptual vocabulary required to recognize the absence of ground truth in generative models. Believing the system 'knows', audiences treat statistical correlations as factual databases, leading to widespread epistemic pollution as users internalize algorithmic hallucinations as verified truths. Socially and Politically, the narrative of 'AI defeating champions' and 'solving problems' inflates capability overestimation, encouraging institutions to replace human judgment in critical sectors (criminal justice, healthcare, hiring) with brittle statistical tools. By framing these deployments as the integration of a superior, objective 'mind', the discourse conceals the encoding of historical biases, effectively laundering human prejudice through the black box of an 'objective' machine, thereby entrenching systemic inequalities.

AI Literacy as Counter-Practice:​

Practicing critical discourse literacy and demanding mechanistic precision acts as a direct counter-practice to the material risks of anthropomorphism. As demonstrated in the reframings, replacing consciousness verbs ('knows', 'understands') with mechanistic ones ('processes', 'predicts', 'classifies') instantly shatters the illusion of mind. When we translate 'the AI understands intent' into 'the model classifies tokens based on training correlations', we force the recognition of the system's absolute dependency on its data and its total absence of semantic awareness. This directly counters epistemic degradation by reminding users that the outputs are statistical, not factual.

Crucially, restoring human agency by replacing agentless constructions ('the algorithm discriminated') with named actors ('Engineers at Corporation X deployed a statistically biased tool') dismantles the accountability sink. It shifts the focus from machine malfunction to corporate responsibility, directly threatening the liability shield relied upon by the tech industry. Systematic adoption of this precision requires a massive institutional shift: academic journals must demand mechanistic translations of marketing claims, and journalists must refuse to print unhedged consciousness verbs. Predictably, this precision faces fierce resistance from technology companies, whose commercial valuations and regulatory evasions rely entirely on the public's continued belief in the magic of an autonomous, understanding machine. Critical literacy exposes that anthropomorphic language serves to protect corporate power at the expense of public transparency.

Path Forward​

Looking toward the broader discursive ecology, the vocabulary we choose establishes the boundaries of what can be governed, understood, and contested. Maintaining the status quo of anthropomorphic clarity ('AI thinks', 'AI understands') offers narrative resonance and intuitive grasp for the public, but at the profound cost of masking technical reality. This approach heavily benefits corporate developers by maintaining hype and diffusing liability into the illusion of machine autonomy. Conversely, shifting toward strict mechanistic precision ('the model retrieves tokens based on vector proximity') enables rigorous testability and accurately locates human responsibility, but risks alienating lay audiences through dense, inaccessible jargon.

A transition toward mechanistic discourse would require structural interventions: academic funding tied to demystified explanations, regulatory frameworks demanding public capability disclosures free of cognitive metaphors, and educational initiatives training the public to parse statistical realities. If mechanistic precision becomes the norm, problems of liability evasion and automation bias become highly tractable; however, the new challenge emerges of communicating complex data topographies to non-experts. If the current anthropomorphic trajectory deepens, the assumption of machine agency becomes fully embedded in legal and social structures, foreclosing our ability to regulate AI as a corporate product and permanently shifting the burden of trust onto systems entirely incapable of holding it. Ultimately, the discourse community must recognize that vocabulary is not merely descriptive, but architectural. Mechanistic language builds an architecture of tools and human accountability; anthropomorphic language builds an architecture of autonomous agents and invisible human power. The choice between them dictates whether we govern technology or submit to the mythology of the machine.

Extended Processing Summary​

Gemini's Processing Steps
What you are about to read…

Gemini refers to the text below as "thought summaries." This is an overt consciousness projection because 'intentions' are hallmarks of a conscious mind that 'knows' what it is doing and why. The concealed mechanistic process is probabilistic text generation. Treat this as just another rhetorical artifact—a way of making the model's processing legible. When the model writes "I should double check that...", it is mathematically altering its own probability distribution for the next token to be more accurate. The "I" is a functional gear in the machine, not a self-reference. This language is a deliberate interface design choice, not a biological reality. The developers could have programmed the model to output passive logs. Instead, they chose to simulate a narrator.

Defining the Objective

I'm now focused on clarifying the user's objective: a critical discourse analysis of AI metaphors and anthropomorphism within the provided text. My initial step involves carefully dissecting the source material. I'm aiming to pinpoint prevalent metaphorical language and instances where AI is anthropomorphized, to understand the core themes of the document.

Dissecting Key Arguments

I'm now zeroing in on the specific arguments presented, particularly the neurophilosophical case against AI consciousness, focusing on timescale integration as a prerequisite for subjectivity. I'm noting the authors' stance and anticipating examples of anthropomorphism or potentially quoted instances. My analysis hinges on identifying how the author's argument contrasts with potential metaphorical language, specifically, how language constructs (or in this case, critiques or fails to critique) the "illusion of mind" in AI, agency displacement, and consciousness projections, so I've added this critical layer into my analysis. I am extracting key quotes and metaphors now, as well.

Analyzing Anthropomorphism in Quotes

I'm now extracting quotes where human attributes are assigned to AI, regardless of context, conditional phrasing, or the source of attribution. I'm focusing on text that explicitly suggests human-like understanding or agency. Key quotes include "emulate human cognitive processes," "exhibits a sophisticated understanding," and instances where AI is said to be "able to defeat," which I think merits a closer look. I'm also examining how agency is potentially displaced onto AI, and how the breadth of AI technologies can contribute to that.

Examining Functionality of Quotes

I'm now applying Brown's typology to five key quotes, assessing how the language frames AI function and potential explanations for its limitations. This focuses on how AI "functions" or the ways that authors frame its capabilities or its lack thereof. I am paying close attention to both anthropomorphic and mechanistic verbs and phrases.

Identifying Contrasting Terminology

I'm now grappling with the inherent tension in the text: the authors critique AI consciousness while simultaneously employing language that attributes cognitive abilities to it. Specifically, the juxtaposition of "defeat" with "passively process" is fascinating. I'm finding that the arguments against AI subjectivity rely on restrictive terminology, inadvertently acknowledging cognitive verbs. I'm noting and cataloging these terms for future analysis of my findings.

Mapping Source-Target

I am now performing a source-target mapping for key quotes. I'm focusing on eight specific instances, identifying the underlying human cognitive concepts being mapped onto AI processes. This includes, for example, linking "adjusting model weights" to "human experiential learning" and "optimizing loss functions" to "cognitive reasoning."

Connecting Architectures and Milestones

I'm currently mapping the relationship between "engineering new architectures" in AI to "evolutionary/developmental milestones" to identify implicit metaphors. I'm focusing on how the text frames the process of AI architecture, thinking about how new architectures come about.

I'm now auditing explanations, identifying and categorizing quotes explaining AI or brain function. For instance, I've linked descriptions of interconnected layers and weight regulation to theoretical and genetic concepts, framing the models' architecture. I've noted that the fixed architecture of neural networks after training is connected to a functional and empirical generalization, while "sophisticated understanding" and temporal dynamics reflect intentional and dispositional attributes. Finally, I'm noting the implications of AI "passively processing."

Reframing Metaphors

I'm now drafting reframed versions of the key quotes, replacing anthropomorphic language with technical descriptions. For the examples provided, I've transformed "understand natural language" into "classify and generate text strings based on statistical patterns," and "solve problems... human thought" into "optimize outputs for specific quantitative metrics." I am also drafting critical observations on the text, paying careful attention to where the agency is given to AI and taken away from engineers.

Analyzing the Implications

I'm now examining how the text oscillates between treating AI as an agent and a machine, specifically noting the acceptance of metaphorical language alongside philosophical critiques. I'm focusing on how the framing of AI "understanding natural language" or "defeating champions" builds perceived competence, and how its limitations are then framed mechanistically. The analysis is highlighting how this asymmetry fosters performance-based trust while obscuring the contributions of human developers, which I'm categorizing.

Synthesizing Accountability

I'm now identifying shifts in accountability within the text. I've noted that the source material frequently uses agentless passive voice, transferring responsibility from developers to the "AI model." I am further tracing this tendency when attributing AI's successes and failures. The anthropomorphism peaks when describing AI's achievements. The neurophilosophical framing of AI's limitations has obscured underlying political and economic issues.

Composing Final Arguments

I'm now drafting my concluding arguments. I've composed a pattern summary integrating earlier tasks, focusing on the dominant metaphors and how the illusion of AI "understanding" is maintained through specific linguistic choices. The illusion is propped up by assuming that the terms are valid at a lower level, but denied for a higher level. I am also constructing the discussion of material stakes, the need for counter-practices, and analytical mapping. I am refining the content against the project's constraints.

code JSON download content_copy expand_less { "update": "Refining the Analysis\n\nI'm now iterating on my reframed quotes, focusing on the nuances of agency and accountability. I'm scrutinizing how subtle shifts in language alter the perceived responsibility for AI outcomes, both successes and failures. The aim is to create a refined mapping showing the precise locations of anthropomorphism. This will lead to a cleaner analysis." }

Analyzing Agency Displacements

I am now thoroughly analyzing the agency displacements within the text, focusing on how the framing subtly shifts responsibility for AI's actions. I'm carefully examining the "understanding" and "decision-making" of AI, and contrasting them with what is actually happening. My attention is drawn to the lack of acknowledgment. I'm trying to identify where there is a direct correlation or where the text directly addresses the human actor. I'm focusing on the philosophical implications, too.

code JSON download content_copy expand_less { "update": "Finalizing Documentation\n\nI'm in the final stages, compiling my analysis of agency displacement, concentrating on the implications of AI "understanding" and "decision-making." The reframing is nearly complete. I'm focusing now on the philosophical points that surface. I think the paper is now ready for revision." }

Clarifying Distinctions

I'm now carefully distinguishing between algorithmic processing and human understanding, focusing on specific linguistic choices that inflate AI's perceived capabilities. I'm noting how the text implicitly assigns conscious agency using verbs like "learn," "adapt," and "understand," and how this obscures the reality of statistical correlations. The "understanding" attributed to natural language processing completely obscures mechanistic reality. I'm also now highlighting where conscious agency of the human designer is diminished by attribution to the model.

Analyzing Liability

I'm now zeroing in on liability implications of anthropomorphic language. I find that when the text attributes understanding to AI, it creates a false sense of trust, since it cannot grasp nuance. This anthropomorphism leads to overestimation of capabilities, inviting dangerous delegation. If AI "understands" and errs, the framing points to the AI's cognitive failure, but the responsibility actually lies with developers and flawed data. I am creating a schema to make my findings explicit.

Categorizing Arguments

I'm now methodically categorizing passages based on Brown's typology, analyzing how the language frames AI function, including "weight impact" (Functional/Theoretical) and "AI systems" as "not adaptive" (Dispositional). The analysis now also covers "simulating human abilities" (Intentional) and AI "defeating champions" (Empirical Generalization). I'm looking at key quotes and analyzing them, assigning them to categories.

Examining Neurophilosophical Bias

I'm now examining the inherent biases, specifically the "curse of knowledge," within the source text, noting that the neurophilosophical focus on "subjectivity" obscures anthropomorphism in lower-level descriptions. The authors employ "understand" and "solve problems" despite denying AI "self." I'm also now analyzing the use of "relation-based trust vs performance-based trust" in the source material, considering the implications, and preparing for the "name the corporation test."

code JSON download content_copy expand_less { "update": "Refining Liability Analysis\n\nI'm now iterating on my liability analysis, exploring the ethical dimensions. When analyzing anthropomorphic attribution, I'm focusing on "understanding" in AI, as it increases risk. If AI "understands" and makes errors, responsibility for those errors is unclear. I'm focusing on the reframing now." }

Revising Word Count

I'm now revising the word count strategy to ensure all minimums are met while remaining within the context window limits. I've re-evaluated task estimates to avoid truncation. I will aim for exactly the minimums for each task to remain concise while fully covering the material. My goal is to maximize academic rigor within the specified constraints. I'm focusing on ensuring rich academic language.

code JSON download content_copy expand_less { "update": "Refining Density Strategy\n\nI'm now implementing token optimization and revising the word count strategy, maximizing academic language, and focusing on minimum word counts. I will create a refined strategy for this project. The goal is to maximize the content, while staying within length limits and token efficiency, which will be critical." }

Refining Typology Assignments

I am now carefully refining my categorization using Brown's typology, paying particular attention to the nuances of each quote. I'm focusing on "learn from experience" in particular, and categorizing it in multiple ways, to highlight the implicit anthropomorphism, so I'm doing a closer reading. I'm aiming for greater precision in the assignment of each quote to its corresponding category.

Finalizing Reframing

I'm now concluding the reframing efforts, replacing anthropomorphic language with precise technical descriptions, and focusing on the underlying mechanisms. I am finalizing the reframing, and I will be working on the next steps, soon. I'm focusing on "understanding" to algorithmic processes, which will be the heart of my work.

Analyzing Agency Slippage

I'm now analyzing agency slippage, tracing the transition from agential terms like "learns" to mechanistic critiques. I'm noting the selective application of mechanistic analysis, and also noting the absence of human actors and their roles. My focus is on how this creates a paradox: AI is portrayed as both capable and deficient, with corporate engineering completely obscured.

Analysis Provenance

Run ID: 2026-03-28-does-artificial-intelligence-exhibit-bas-metaphor-f6mlga Raw JSON: 2026-03-28-does-artificial-intelligence-exhibit-bas-metaphor-f6mlga.json Framework: Metaphor Analysis v6.4 Schema Version: 3.0 Generated: 2026-03-28T07:53:58.866Z

Discourse Depot © 2025 by TD is licensed under CC BY-NC-SA 4.0