Engineering Sentience
🤖 AI Summary
Formalizing and engineering machine sentience—particularly its essential subjective character—while preserving computational tractability remains an open challenge.
Method: We propose a functional sentience framework that rigorously defines sentience as the concurrent presence of assertive content (world-directed reference) and qualitative character (intrinsic, subjective experience), grounded in functionalist principles and computational modeling. The framework integrates real-time perceptual signal processing with persistent internal state mechanisms to support temporally extended, self-referential phenomenology.
Contribution/Results: This work establishes the first verifiable, implementation-level criteria for embedding subjectivity in artificial agents—delineating both necessary conditions and empirically testable design pathways. It provides foundational theoretical guidance for building sentient-capable AI architectures while simultaneously furnishing critical diagnostic criteria to prevent inadvertent creation of sentient systems. By bridging computational neuroscience, philosophy of mind, and AI ethics, the framework enables concrete interdisciplinary progress toward responsible development of conscious AI.
Application Category
📝 Abstract
We spell out a definition of sentience that may be useful for designing and building it in machines. We propose that for sentience to be meaningful for AI, it must be fleshed out in functional, computational terms, in enough detail to allow for implementation. Yet, this notion of sentience must also reflect something essentially 'subjective', beyond just having the general capacity to encode perceptual content. For this specific functional notion of sentience to occur, we propose that certain sensory signals need to be both assertoric (persistent) and qualitative. To illustrate the definition in more concrete terms, we sketch out some ways for potential implementation, given current technology. Understanding what it takes for artificial agents to be functionally sentient can also help us avoid creating them inadvertently, or at least, realize that we have created them in a timely manner.
Problem
Research questions and friction points this paper is trying to address.
Define sentience for AI in functional computational terms
Ensure sentience reflects subjective qualities beyond perception
Propose implementation methods for artificial sentience
Innovation
Methods, ideas, or system contributions that make the work stand out.
Functional computational sentience definition
Assertoric qualitative sensory signals
Implementation with current technology
🔎 Similar Papers
No similar papers found.
