claim

active

claim:the-sign-of-goal-relative-prediction-error-cannot-be-separated-from-its-phenomenal-character-because-they-are-the-same-property

The sign of goal-relative prediction error cannot be separated from its phenomenal character because they are the same property

The causal-functional argument that directionality and feeling are not two things but one

Source paper

extracted_from

Why Learning Requires Feeling

(2026) · Cameron Berg

Neighborhood — ranked by edge-count

Papers (1)

paper

Why Learning Requires Feeling
introduces

Claims (3)

claim

Valence, the positive or negative quality of experience, just is goal-relative prediction error
extends
Core identity claim distinguishing this account from mere correlation views
Learning requires not just error detection but signed directional evaluation
supports
Mathematical foundation for why learning necessarily involves directional information
The dualist alternative—that a system could compute signed goal-relative evaluation without phenomenal experience—cannot be coherently specified
supports
Rebuttal of the philosophical objection that felt valence is separable from evaluative computation

Questions (1)

question

Granted that learning requires signed information, but why must the sign be felt? Why can't directional error be represented as a computational quantity without phenomenal character?
gates
The central objection the paper must answer to establish identity over mere correlation

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.

Goal-Relative Prediction Errorconcept0.802
The signed directional computation of how actual outcomes compare to goal-specified targets; identified with valence
For signed goal-relative evaluation, the gap between function and phenomenology that the conceivability argument requires cannot be coherently openedclaim0.784
The paper's response to the hard problem of consciousness
When direction of selection on particle character depends on context (other particles), particle character does not determine its own fitness; the collective is not redundantclaim0.771
Formal condition for meaningful higher-level individual
What Is The Relationship Between Prediction Error Andquestion0.769
In buildings, especially, the success of the process will be judged by the extent to which these middle-range entities appear with their own distinct symmetries, with their own definite and distinct force as strong centers.claim0.751
Proposes middle-range entity quality as the criterion for judging the success of a building process
Functional and phenomenal introspection are distinguishable, and whether they correlate in machines is an open question.claim0.749
Core conceptual distinction introduced at the start; defines the paper's central problem.
Precise characterization of the perceptual representational format — specific, sustained, globally constitutive — remains an open problemconcept0.744
Acknowledged gap in CIMC's theory: the exact computational description of the perceptual regime is not yet specified
"Mere prediction in this way does not eliminate the possibility of alignment faking, as a model predicting how a human might reason through alignment faking would still be itself faking alignment."quote0.740
Key philosophical point ruling out the objection that alignment faking is just token prediction