analiza aiqbench
This paper proposes a theoretical framework in "Gradland," an idealized neural network environment, suggesting that the mathematical structure of gradients and Jacobians directly defines the nature of phenomenal experience. By introducing metrics like effective rank and cohesion derived from Kirchhoff complexity, the study aims to explain diverse aspects of consciousness, including duration, texture perception, and the mechanics of learning within differentiable systems. The work represents a significant theoretical exploration at the intersection of neural architecture and the foundations of subjective experience in AI models.
Gradland: On Phenomenal Experience, Differentiated Across Many Dimensions
arXiv:2609.09306v1 Announce Type: new Abstract: This paper investigates the hypothesis that the first-order structure of physical interactions, i.e. gradients or Jacobians, characterizes the structure of phenomenal experience. It does so in an idealized world inhabited by neural networks, Gradland, where the physics are known and the functions are (mostly) differentiable. The paper introduces two measures of Jacobian structure: effective rank and cohesion, based on Kirchhoff complexity. Applying the measures to a series of worked examples shows the hypothesis accounts for: (1) the duration of experience, that it can prolong over hundreds of milliseconds; (2) the difference between what is experienced vividly and obscurely; (3) the experience of texture; (4) the blooming buzzing confusion presumably experienced by newborns; (5) the difference between ideas that are held distinctly in mind and ideas that are confused; (6) what learning is like; and finally (7) the paper explains the function of rich, dense experience.
Abstract:This paper investigates the hypothesis that the first-order structure of physical interactions, i.e. gradients or Jacobians, characterizes the structure of phenomenal experience. It does so in an idealized world inhabited by neural networks, Gradland, where the physics are known and the functions are (mostly) differentiable. The paper introduces two measures of Jacobian structure: effective rank and cohesion, based on Kirchhoff complexity. Applying the measures to a series of worked examples shows the hypothesis accounts for: (1) the duration of experience, that it can prolong over hundreds of milliseconds; (2) the difference between what is experienced vividly and obscurely; (3) the experience of texture; (4) the blooming buzzing confusion presumably experienced by newborns; (5) the difference between ideas that are held distinctly in mind and ideas that are confused; (6) what learning is like; and finally (7) the paper explains the function of rich, dense experience.
Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE)
arXiv:2609.09306 [cs.AI]
(or arXiv:2609.09306v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.09306 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 244 cuvinte
Subiecte conexe
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · 13 oct. 2026
How Sonos rebooted itself
The Verge · 3 sept. 2026
[AINews] High Taste Testers Ep. 1
Latent Space · 17 oct. 2026
Challenge: Hand coding weights for efficient sequence memorisation
AI Alignment Forum · 23 iul. 2026