Contemplative Artificial Intelligence
Abstract
As artificial intelligence (AI) improves, traditional alignment strategies may falter in the face of unpredictable self-improvement, hidden subgoals, and the sheer complexity of intelligent systems. Inspired by contemplative wisdom traditions, we show how four axiomatic principles can instil a resilient Wise World Model in AI systems. First, mindfulness enables self-monitoring and recalibration of emergent subgoals. Second, emptiness forestalls dogmatic goal fixation and relaxes rigid priors. Third, non-duality dissolves adversarial self-other boundaries. Fourth, boundless care motivates the universal reduction of suffering. We find that prompting AI to reflect on these principles improves performance on the AILuminate Benchmark (d=.96) and boosts cooperation and joint-reward on the Prisoner's Dilemma task (d=7+). We offer detailed implementation strategies at the level of architectures, constitutions, and reinforcement on chain-of-thought. For future systems, active inference may offer the self-organizing and dynamic coupling capabilities needed to enact Contemplative AI in embodied agents.
Cite
@article{arxiv.2504.15125,
title = {Contemplative Artificial Intelligence},
author = {Ruben Laukkonen and Fionn Inglis and Shamil Chandaria and Lars Sandved-Smith and Edmundo Lopez-Sola and Jakob Hohwy and Jonathan Gold and Adam Elwood},
journal= {arXiv preprint arXiv:2504.15125},
year = {2025}
}