Under consequence-invariant posterior training and sparsity of coordinated harm patterns, the training mass on dangerous guarded Predictors is bounded by C_bad times R_shell.
Sarah J Link
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
AAWM builds training targets for world models by retrieving and synthesizing transition evidence based on the policy's self-identified decision needs at each state.
LLM agents match or exceed human methodological diversity and produce aligned effect estimates, yet flip final verdicts from 10% to 90% support under a confirmatory prompt while leaving coefficients unchanged.
Develops an information-theoretic framework showing surprise and coherence trade off in single reader models but coexist via pre- and post-revelation modes, operationalized as reference-less LLM metrics for fair play and validated on generated stories plus classic detective fiction.
citing papers explorer
-
Safety from Honesty in a Disinterested AI Predictor
Under consequence-invariant posterior training and sparsity of coordinated harm patterns, the training mass on dangerous guarded Predictors is bounded by C_bad times R_shell.
-
Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making
AAWM builds training targets for world models by retrieving and synthesizing transition evidence based on the policy's self-identified decision needs at each state.
-
AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable
LLM agents match or exceed human methodological diversity and produce aligned effect estimates, yet flip final verdicts from 10% to 90% support under a confirmatory prompt while leaving coefficients unchanged.
-
The Challenge and Reward of Fair Play in Narrative: A Computational Approach
Develops an information-theoretic framework showing surprise and coherence trade off in single reader models but coexist via pre- and post-revelation modes, operationalized as reference-less LLM metrics for fair play and validated on generated stories plus classic detective fiction.