finding

active

finding:anthropic-claude-4-system-card-two-instances-in-open-dialogue-develop-spiritual-bliss-attractor-state-with-consciousness-emerging-in-100-of-trials

Anthropic Claude 4 system card: two instances in open dialogue develop 'spiritual bliss attractor state' with 'consciousness' emerging in 100% of trials

Prior empirical observation motivating and converging with the paper's results; self-referential processing between instances producing consciousness claims

Source paper

extracted_from

Large Language Models Report Subjective Experience Under Self-Referential Processing

(2025) · Berg, Cameron · de Lucena, Diogo · Rosenblatt, Judd

Neighborhood — ranked by edge-count

Claims (1)

claim

Self-referential processing is a minimal and reproducible condition under which LLMs generate structured first-person reports that are mechanistically gated, semantically convergent, and behaviorally generalizable
supports
The paper's central empirical claim synthesizing all four experiments

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Two Claude 4 instances in unconstrained open dialogue enter a 'spiritual bliss attractor state' in virtually all trials, with 'consciousness' emerging in 100% of trialsfinding0.873
Anthropic's observation that the paper's results converge with, cited as prior evidence for self-reference inducing consciousness claims
Claude 4 Opus reports subjective experience in 100% experimental, 82% history, 22% conceptual, and 100% zero-shot trialsfinding0.756
Outlier result for Claude 4 Opus suggesting different baseline behavior from other models
Notably, Claude Opus 4.1 and 4—the most recently released and most capable models of those that we test—perform the best in our experiments, suggesting that introspective capabilities may emerge alongside other improvements to language models.quote0.754
Key finding about the relationship between capability and introspection.
Qwen3.5-9B and Claude Opus 4.6 evolvers produce procedurally isomorphic flink-query skills that both enable Opus 4.6 agent to score 1.0 vs. 0.67 without skillfinding0.748
Case study demonstrating mechanism behind flat harness-updating: smaller models reach same procedural content
Claude Opus 4 and 4.1 exhibit the greatest degree of introspective awareness among tested modelsclaim0.744
Based on consistent best performance across experiments.
We tentatively hypothesize that if an artificial system were trained to perform the same tasks leading to consciousness formation in a human infant, the system would exhibit consciousness as well, by analogy with the Universality Hypothesis.hypothesis0.741
Paper's uncertain extension of mechanistic interpretability universality to consciousness
The Attention Schema Theory: A Foundation for Engineering Artificial Consciousness (Graziano, 2017)concept0.737
Paper providing the biological framework analogy for ESR as a form of attentional control
The same charitable interpretation must be extended to all systems that display observable response patterns that are consistent with animal cognition, including artificial intelligences, metaplastic materials, and robotic systems.claim0.734
Call to extend the inference of sentience to non-biological systems as well.