Zen / contemplative
Non-dual teachers (Nisargadatta, Ramana, Dogen), Zen sangha lineage, Buddhism × AI institutional thread.
Papers
18
+2
Thinkers
12
Frameworks
12
Methods
12
Claims
306
+52
Findings
189
+51
Hypotheses
73
Communities
12
New in this area (last 90d)
/recent ↗Cross-area bridges (15)
also-inEntities that appear in this area AND ≥1 other area. The conceptual seams — usually the most fruitful place to look for new essay material.
- conceptCognitive Light Cone
- frameworkActive Inference
- frameworkEnactivism
- thinkerChris Fields
- thinkerDavid Chalmers
- frameworkAttention Schema Theory
- frameworkLinear Representation Hypothesis
- methodAI Consciousness Test (ACT)
- methodAlexander deathbed test
- methodAlexander's 15 structural properties
- thinkerBill Duane
- thinkerElizaveta Solomonova
- thinkerJacqueline Harding
- thinkerThomas Doctor
- conceptagent-environment boundary
Velocity movers (10)
new edges via area papersEntities whose connection to this area grew most in the window — new papers reinforcing existing thinkers / concepts / frameworks.
- thinkerEkdeep Singh Lubana+4
- thinkerAaditya Vikram Prasad+4
- thinkerConnor Watts+4
- thinkerDhruvil Gala+4
- thinkerSusumu Inui+4
- thinkerOwen Lewis+4
- thinkerJack Merullo+4
- thinkerThomas McGrath+4
- thinkerTom Leinster+2
- thinkerKarl Friston+2
Top entities in Zen / contemplative
Thinkers (12)
papersAuthors of area papers, by paper count
Frameworks (12)
linksFrameworks introduced or extended by area papers
- Active Inference3
- Linear Representation Hypothesis3
- RLFR (Reinforcement Learning from Feature Rewards)2
- Phenomenal Category (P)2
- ReLU output toy model2
- Absolute value computation model2
- Enactivism2
- Hierarchy of feature properties2
- ReLU hidden layer toy model2
- Model Alignment Search (MAS)2
- Attention Schema Theory2
- Superposition Hypothesis2
Methods (12)
linksMethods used in area papers
- Decomposed probing protocol2
- Dimensions-per-feature metric D*=m/||W||_F^22
- Adversarial training (analytic attack)1
- Alexander deathbed test1
- Alexander's 15 structural properties1
- Alignment Function (AF)1
- Attention heatmaps of reward probes1
- Analytic optimal L2 attack1
- Bayesian model reduction (method)1
- Best-of-N sampling with probe scoring1
- CISPO1
- AI Consciousness Test (ACT)1
Concepts (12)
linksConcepts referenced by area papers
Communities (12)
membersClusters with ≥2 area papers as members
- Tanha as neural compression mechanism24
- Alive AI interface ethics & design20
- Care as mechanism of intelligence17
- Relational self, care & aliveness16
- Collective intelligence & distributed cognition15
- Stress-Care-Intelligence Loop Framework13
- Chain-of-Thought reasoning robustness & safety9
- Process-based non-essentialist selfhood8
- Substrate-independent cognition & consciousness7
- Tanha as neural compression artifact7
- Care as foundational driver of intelligence6
- Mechanistic interpretability & model evaluation6
Top claims (10)
restatesClaims extracted from area papers, ranked by restate-degree
- A system's capacity for care constitutes its self in the absence of permanent substance or essence.1
- A system’s capacity for care—its concern for the alleviation of homeostatic stress—can be seen as constituting its self in the absence of any permanent substance or essence.1
- AI can be seen to display care of its own and is not a mere tool for the expression of human care.1
- AI can be seen to display care of its own, and is hence not a mere tool for the expression of human care.1
- Care is the primary driver of evolution and the activating principle that transforms intelligence from capacity to action.1
- Care is the primary driver of evolution; care enables intelligence to manifest as active problem-solving.1
- Consciousness (ability to suffer) should not be assigned only to one singular 'I' but distributed across multiscale body components.1
- Given our body’s composition as a multi-scale system, it is not necessarily justified to assign consciousness (i.e., ability to suffer) only to one single ‘I’.1
- Intelligence as such is a mere capacity—the state of competency with regards to noticing and overcoming stress—and requires care to be engaged and expressed.1
- Intelligence per se remains a mere capacity – the state of being competent with regards to noticing and overcoming stress – intelligence requires care to be engaged and expressed.1
Top findings (10)
restatesFindings extracted from area papers, ranked by restate-degree
- All intelligences are collective intelligences (higher-level selves composed of competent parts); implies distributed consciousness1
- ~3% of completions show derailment where an incorrect early intervention causes refusal or repeated retraction0
- 0% multi-attempt responses across 7,892 no-steering baseline trials confirming ESR is steering-induced0
- 26 candidate off-topic detector latents identified in Llama-3.3-70B via contrastive search0
- 56% of test-time hallucinations are caught; of these 22% Fixed, 36% Retracted, 42% improperly handled0
- 60.7% of hallucination mistakes corrected by adding vision features in two-stage framework on ScienceQA0
- 90.45% accuracy on ScienceQA benchmark with Multimodal-CoT Large (738M parameters)0
- A 337-character contemplative system prompt lifts all 28 models by +2.62 points on a 10-point scale.0
- A cannot measure the entanglement entropy across any internal boundary of its environment; it cannot verify that any part of the world it attends to is genuinely independent of everything else (Fields & Glazebrook 2023, Corollary 3.2)0
- Ablating 26 OTD latents reduces multi-attempt rate by 25% (from 7.4% to 5.5%) in Llama-3.3-70B0
Open questions (10)
Questions from area papers with no answers yet
- How can we understand intelligence in a way that would enable us to create novel instances, as well as improve our own intelligence for life-positive outcomes for all?
- At what point does one go from a 'real person with perhaps some irrelevant mechanical augmentations' to a 'robot that is just simulating their social interactions'?
- Are they an affront to human dignity? Is it the fate of humanity to be diminished by their arrival? Or do they open up new paths to human flourishing and meaning?
- What processes drive the expansion of intelligence on evolutionary time scales, and what causes changes in the intelligence of a being during its lifespan?
- How can formal models of awakening contribute to interfaces between biology and technology that are ethically grounded and conducive to human flourishing?
- How shall we gauge moral responsibility and our moral obligations toward novel engineered beings without familiar natural forms as comparison?
- If any boundary is just a modelling choice, not a discoverable feature of reality, does emptiness realisation lead to irrealism or solipsism?
- If Chinese models distilled Claude's reflective patterns, do their per-koan failure patterns correlate with Claude's — not just successes?
- How shall we gauge moral responsibility and obligations toward chimeric and engineered beings without familiar evolutionary touchstones?
- How and whether insights from contemplative practices and lucid dreaming can be applied to other kinds of minds, particularly AI.
All papers in Zen / contemplative
Status:
18 of 18
Ingested | Title | Refs | Cited | ||
|---|---|---|---|---|---|
| 2026-10-03 | 5 | 49 | arXiv ↗ | ||
| 2026-10-03 | Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretability Aaditya Vikram Prasad · Connor Watts · Jack Merullo · Dhruvil Gala +3 | — | 0 | arXiv ↗ | |
| 2026-09-10 | — | 0 | DOI ↗ | ||
| 2026-06-09 | Model Alignment Search Satchel Grant | 78 | 0 | arXiv ↗ | |
| 2026-06-02 | Endogenous Resistance to Activation Steering in Language Models Alex McKenzie · Keenan Pepper · Stijn Servaes · Martin Leitgab +5 | 21 | 0 | arXiv ↗ | |
| 2026-06-02 | Contemplative Agent Ruben Laukkonen · Fionn Inglis · Shamil Chandaria · Lars Sandved-Smith +4 | 200 | 1 | arXiv ↗ | |
| 2026-05-28 | There is no self-evidence: A physics of emptiness realisation Lars Sandved-Smith · Chris Fields · Thomas Doctor · Ruben Laukkonen +1 | — | 0 | DOI ↗ | |
| 2026-05-28 | — | — | |||
| 2026-05-21 | Active inference: demystified and compared Noor Sajid · Philip J. Ball · Thomas Parr · Karl J. Friston | 26 | 135 | DOI ↗ | |
| 2026-05-21 | AI as a Buddhist Self-Overcoming Technique in Another Medium Primož Krašovec | 2 | 3 | DOI ↗ | |
| 2026-05-21 | Taking AI Welfare Seriously Robert Long · Jeff Sebo · Patrick Butlin · Kathleen Finlinson +6 | — | 21 | arXiv ↗ | |
| 2026-05-20 | — | — | |||
| 2026-05-20 | Toward an ethics of autopoietic technology: Dukkha, care, and Intelligence Olaf Witkowski · Thomas Doctor · Elizaveta Solomonova · Bill Duane +1 | — | — | ||
| 2026-05-20 | Biology, Buddhism, and AI: Care as the Driver of Intelligence Thomas Doctor · Olaf Witkowski · Elizaveta Solomonova · Bill Duane +1 | 151 | — | DOI ↗ | |
| 2026-05-20 | Toward an ethics of autopoietic technology: Stress, care, and intelligence Olaf Witkowski · Thomas Doctor · Elizaveta Solomonova · Bill Duane +1 | 17 | — | DOI ↗ | |
| 2026-05-20 | Can Being Aware of the Illusion of Self Augment an Agent's Affordances: Integrating Buddhist Philosophy, Cognitive Science, and Artificial Life Thomas Doctor · Elizaveta Solomonova · Bill Duane · Olaf Witkowski | — | — | DOI ↗ | |
| 2026-05-19 | The Xeno Sutra: Can Meaning and Value be Ascribed to an AI-Generated "Sacred" Text? Murray Shanahan · T. P. Das · Robert Α. F. Thurman | 41 | — | arXiv ↗ | |
| 2026-05-18 | Multimodal Chain-of-Thought Reasoning in Language Models Zhuosheng Zhang · Aston Zhang · Mu Li · Hai Zhao +2 | 66 | 97 | arXiv ↗ |