Jakob Hohwy

Authored papers (2)

• There is no self-evidence: A physics of emptiness realisation2026

  No finite agent can measure the entanglement entropy across its own boundary — this is the load-bearing result, proven by Fields and Glazebrook (2023, Corollary 3.1), from which the paper derives a formal account of Buddhist emptiness realisation. Because all of an agent's measurement operators act exclusively on the N-bit holographic screen B and have no access to the bulk state |B⟩, the agent cannot determine whether entanglement entropy S(|AB⟩) is zero (separable) or nonzero, rendering the self/environment partition permanently unevidenceable from the inside. The paper introduces the construct of the separation prior σ — a structural prior over the agent's quantum reference frame (QRF) deployments that constrains every measurement frame to respect a fixed B_self ∪ B_env sectorisation — and formalises it within the quantum free energy principle (qFEP) of Fields et al. (2022). Contemplative practice is modelled as progressive opacification of σ: as the practitioner builds a metacognitive model of their own QRF dynamics (formalised via the parametric-depth architecture of Sandved-Smith et al., 2021), σ transitions from transparent architectural constraint to explicit state-space variable, at which point Bayesian model reduction prunes it because ΔComplexity < 0 while ΔAccuracy ≈ 0. The post-dual agent optimises over the full QRF space Q rather than the restricted subspace Q_σ, yielding strictly lower variational free energy. The paper argues this implies that Buddhist awakening is neither the acquisition of a new metaphysical belief nor the dissolution of selfhood, but the embodied removal of an unevidenced constraint on inference — one whose removal simultaneously grounds a formal account of compassion as unbounded VFE minimisation and predicts a measurable shift toward critical neural dynamics in agents with stable emptiness realisation.

• Contemplative Agent2025ⓒ 1

  Embedding four Buddhist-derived axiomatic principles—mindfulness, emptiness, non-duality, and boundless care—into AI systems via a framework the paper terms the 'Wise World Model' produces measurable alignment gains and cooperation boosts in current transformer-based LLMs. Pilot experiments on GPT-4o and GPT-4.1 nano using structured contemplative prompts yielded statistically significant safety improvements across ten hazard categories on the AILuminate Benchmark (d=.96 against baseline standard prompting), and drove cooperation rates and joint reward substantially upward in an Iterated Prisoner's Dilemma across 50 simulated 10-round games (d=7+), with boundless-care and non-duality prompts producing the largest effects even against always-defecting opponents. Three implementation pathways are introduced—Contemplative Architecture (full-stack active inference embedding), Contemplative Constitutional AI (CCAI, extending Anthropic's Constitutional AI framework with a 'wisdom charter'), and Contemplative Reinforcement Learning (CRL) on chain-of-thought—each targeting different integration depths from generative-model parameters to inference-time classifiers. The paper argues that because these principles restructure how goals, beliefs, and self-other boundaries are encoded rather than prescribing what specific values to hold, they provide scale-resilient intrinsic alignment that does not degrade as AI capability outstrips human oversight—contrasting with extrinsic methods like RLHF or rule-based constraints that become gameable at superintelligent scales.

More papers — OpenAlex / S2

Recent mentions (5)

• machine-consciousness

  cimcWhitepaper.md
• papers-typed

  laukkonen-2025-contemplative-agent.md
• papers

  friston-2017-active.md
• papers-typed

  sandved-smith-2026-there.md
• papers-typed

  there.md