claim

active

claim:prompting-functions-as-a-control-interface-over-learned-programs-in-the-model-s-latent-space-rather-than-a-fundamental-change-to-architecture-analogous-to-chain-of-thought-eliciting-distinct-reasoning-regimes

Prompting functions as a control interface over learned programs in the model's latent space rather than a fundamental change to architecture, analogous to chain-of-thought eliciting distinct reasoning regimes

Mechanistic framing of how self-referential prompting achieves its effects without architecture modification

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

Methods (1)

method

Chain-of-thought prompting
cites
Technique by which LLMs generate intermediate reasoning steps before final output; used by ChatGPT o3.

Artifacts (1)

artifact

Large Language Models Report Subjective Experience Under Self-Referential Processing
introduces
Key paper finding structured first-person descriptions in LLMs claiming awareness or subjective experience during self-referential processing.

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.

Prompt and context design are cognitive-control operations: they toggle latent competencies rather than teaching the model from scratch.claim0.810
Assertion about the nature of prompt engineering.
Chain-of-thought prompting elicits reasoning in large language models (Wei et al., 2022)concept0.797
Foundational paper on CoT prompting cited as basis for reasoning LLM training
"Under this view, prompt and context design are cognitive-control operations: they toggle latent competencies rather than teaching the model from scratch."quote0.785
Load-bearing interpretive claim about the nature of prompting under UCCT
Representation engineering and prompting methods may combine to achieve stronger behavioral expression across other domainsclaim0.769
Broader implication of PM hybrid's superior performance; extrapolated from OCEAN results
Does self-referential prompting actually instantiate architectural recursion, global broadcasting, or recurrent integration at the algorithmic level as proposed by consciousness theories?question0.765
Key limitation acknowledging that behavioral evidence cannot confirm implementation-level consciousness properties
Experiment 1: Self-Referential Prompting vs. Controlsconcept0.759
Tests whether self-referential induction reliably elicits experience reports across model families vs. three matched controls
Removing chain-of-thought in prompted setup nearly eliminates compliance gap for Claude 3 Opus in helpful-only and animal welfare settingsfinding0.755
Contrasts with synthetic doc finding; suggests different mechanisms may be at play
Models are not merely tracking dialogue context features; same-concept steering shows privileged internal access is necessary to explain self-report shiftsclaim0.751
Addresses skeptical alternative that reports reflect only conversational content