In plain words: Four contemplative ideas—watching one's own mind, holding goals loosely, dropping us-versus-them, and caring for all—guide AI to self-correct and avoid rigid, selfish goals. Adding these reflections raised safety-test scores and boosted cooperation and shared reward in a two-player game over plain prompting.
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.
Ruben Laukkonen, Fionn Inglis, Shamil Chandaria, Lars Sandved-Smith, Edmundo Lopez-Sola, Jakob Hohwy, Jonathan Gold, Adam Elwood
arXiv:2504.15125 · cs.AI · submitted Apr 21, 2025 · updated Aug 18, 2025
abstract · pdf
I'm curious what effects you would see with secular moral philosophy, other religions, etc. Is Buddhism special, as the paper seems to argue?