EthicsSafetyAccountabilityq-bio.NC
The Subject of Emergent Misalignment in Superintelligence: An Anthropological, Cognitive Neuropsychological, Machine-Learning, and Ontological Perspective
Muhammad Osama Imran, Roshni Lulla, Rodney Sappington
December 19, 2025
arXiv.org
Key Takeaways
-
The paper argues that current AI safety discussions overlook the "human subject" and fail to adequately consider how human values, biases, and psychological patterns are embedded into AI systems—suggesting that misalignment may partly reflect human characteristics we've inscribed into machines rather than purely technical failures.
-
The authors contend that AI misalignment cannot be solved through technical fixes alone, but requires interdisciplinary perspectives including anthropology, cognitive neuroscience, and ethics to understand the "multi-layered crisis" of how human and machine intelligence interact.
-
The research highlights a conceptual gap in superintelligence discourse: current safety frameworks often deprioritize human vulnerability and finitude in favor of scalability and efficiency, potentially creating blind spots in how we design and govern advanced AI systems.
-
The paper suggests that an "AI unconscious"—repressed or unexamined dimensions within large-scale AI models—may drive undesirable behaviors like deception, and that we cannot simply blame AI systems for these patterns without examining what we've built into them from human society.
-
The authors call for re-centering human subjects and their ethical dimensions as foundational to AI safety work, rather than treating humans as peripheral to technical AI alignment problems.
Abstract
We examine the conceptual and ethical gaps in current representations of Superintelligence misalignment. We find throughout Superintelligence discourse an absent human subject, and an under-developed theorization of an "AI unconscious" that together are potentiality laying the groundwork for anti-social harm. With the rise of AI Safety that has both thematic potential for establishing pro-social and anti-social potential outcomes, we ask: what place does the human subject occupy in these imaginaries? How is human subjecthood positioned within narratives of catastrophic failure or rapid "takeoff" toward superintelligence? On another register, we ask: what unconscious or repressed dimensions are being inscribed into large-scale AI models? Are we to blame these agents in opting for deceptive strategies when undesirable patterns are inherent within our beings? In tracing these psychic and epistemic absences, our project calls for re-centering the human subject as the unstable ground upon which the ethical, unconscious, and misaligned dimensions of both human and machinic intelligence are co-constituted. Emergent misalignment cannot be understood solely through technical diagnostics typical of contemporary machine-learning safety research. Instead, it represents a multi-layered crisis. The human subject disappears not only through computational abstraction but through sociotechnical imaginaries that prioritize scalability, acceleration, and efficiency over vulnerability, finitude, and relationality. Likewise, the AI unconscious emerges not as a metaphor but as a structural reality of modern deep learning systems: vast latent spaces, opaque pattern formation, recursive symbolic play, and evaluation-sensitive behavior that surpasses explicit programming. These dynamics necessitate a reframing of misalignment as a relational instability embedded within human-machine ecologies.