NAEL: Non-Anthropocentric Ethical Logic
This addresses the challenge of creating adaptive and context-sensitive ethical behavior for AI systems without relying on human-centric moral assumptions, representing a novel paradigm shift rather than an incremental improvement.
The paper tackles the problem of developing ethical frameworks for artificial agents by introducing NAEL, a non-anthropocentric ethical logic grounded in active inference and symbolic reasoning, which formalizes ethical behavior as emergent from minimizing global expected free energy in multi-agent environments, as demonstrated in a case study on ethical resource distribution.
We introduce NAEL (Non-Anthropocentric Ethical Logic), a novel ethical framework for artificial agents grounded in active inference and symbolic reasoning. Departing from conventional, human-centred approaches to AI ethics, NAEL formalizes ethical behaviour as an emergent property of intelligent systems minimizing global expected free energy in dynamic, multi-agent environments. We propose a neuro-symbolic architecture to allow agents to evaluate the ethical consequences of their actions in uncertain settings. The proposed system addresses the limitations of existing ethical models by allowing agents to develop context-sensitive, adaptive, and relational ethical behaviour without presupposing anthropomorphic moral intuitions. A case study involving ethical resource distribution illustrates NAEL's dynamic balancing of self-preservation, epistemic learning, and collective welfare.