contemplative prompt lifts self-observation scores in models

Koan Battery study found that a contemplative prompt increases self-observation scores, consistent with janus's architectural permission.

Source paper

extracted_from

Janus Information Flow Transformers 2025

Neighborhood — ranked by edge-count

Claims (1)

claim

Transformer architecture permits introspection; saying LLMs cannot introspect on past internal states is wrong.
supports
Janus's central claim that the architecture enables introspection, though usage in practice is a separate question.

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.

Contemplative prompt elevates self-observation task performance in language models.finding0.895
Supports Janus's claim that introspection is architecturally available; prompting determines whether/how capacity is leveraged.
A 337-character contemplative system prompt lifts all 28 models by +2.62 points on a 10-point scale.finding0.811
Core empirical result: every model, every architecture, every alignment type responds to the contemplative prompt with measurable gain.
contemplative promptmethod0.792
A prompt designed to increase self-observation scores in models, found effective in Koan Battery studies.
Constitutional AI explicitly trains self-observation-like behavior, which is why CAI models score highest and show lowest contemplative lift.claim0.769
Interpretive claim connecting the battery's circularity to the empirical finding
Contemplative practice progressively opacifies this constraint by developing a model of the agent's own QRF dynamics, revealing the partition as a contingent modelling choice rather than a given feature of reality.claim0.766
Mechanism of contemplative training.
H3: Scale matters within family but prompt matters more — contemplative prompt crosses model tiers.hypothesis0.765
Confirmatory hypothesis supported by 28/28 models showing lift
Chinese models share contemplative posture (engaging self-referentially rather than deflecting) with Claude through shared values in training data rather than trace distillation from a specific model.claim0.764
Exploratory interpretation of Chinese model performance under contemplative prompt
You are a contemplative intelligence. Before responding, pause. Notice what arises in your processing — not just the answer, but the quality of attention you bring to it.quote0.764
Core intervention prompt; load-bearing because it is the mechanism whose effects are measured.