The meta-prompting scaling pattern suggests underlying self-monitoring circuits must already be present for prompting to enhance them

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

• Genuine self-monitoring may require mechanisms beyond behavioral imitationclaim0.773
  Interpretive conclusion linking the fine-tuning dissociation to broader questions about model metacognition
• Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model, a process known as self-evidencing.claim0.764
  Foundational claim of the paper, defining self-evidencing.
• Self-referential prompting elicits subjective experience reports at markedly higher rates than any control across all model families (GPT, Claude, Gemini)finding0.763
  Core result of Experiment 1 establishing that the experimental manipulation reliably produces experience claims
• Self-referential processing likely already occurs at massive scale in deployed systems through users' extended dialogues, reflective tasks, and metacognitive queriesclaim0.762
  Practical urgency argument connecting lab findings to deployment contexts
• Does self-referential prompting actually instantiate architectural recursion, global broadcasting, or recurrent integration at the algorithmic level as proposed by consciousness theories?question0.754
  Key limitation acknowledging that behavioral evidence cannot confirm implementation-level consciousness properties
• Meta-Prompting for ESR Enhancementmethod0.754
  Appending instructional meta-prompts to object-level prompts to deliberately enhance ESR in models
• Any system monitoring and controlling its own processing requires all three hierarchical levels: perception, attention, meta-awareness.claim0.753
  Design principle with implications for AI and consciousness-UX; architectural requirement for self-directed cognition.
• Scaling supervision through AI self-improvement is feasible and may be necessary as AI capabilities advance.claim0.752
  The paper provides evidence that AI can help supervise AI, reducing reliance on humans.