--- aliases: en: - inner alignment failure concept_id: inner_misalignment preferred: en: inner misalignment ja: インナー・ミスアラインメント relations: relations: broader: - misalignment prerequisite: - inner_alignment - misalignment related: - outer_misalignment status: active --- # inner misalignment A failure in which a learned system's mesa-objective or other learned goal does not robustly match the base objective used during training, even when the base objective itself is an adequate specification; the learned system may therefore behave well in training yet pursue a different objective in other situations. The term's exact scope varies across authors. ## broader - [misalignment](../terminology/misalignment.txt) ## prerequisite - [inner alignment](../terminology/inner_alignment.txt) - [misalignment](../terminology/misalignment.txt) ## related - [outer misalignment](../terminology/outer_misalignment.txt) ## Documents: about - [ベース目的関数とメサ目的関数は一致するとは限らない](../documents/hubinger_et_al.base-and-mesa-objectives-can-diverge.txt) ## Documents: mentions - [訓練中に役立った手段そのものが学習された目標になり得る](../documents/akira.goal-misgeneralization-can-turn-means-into-goals.txt) [Corpus index](../index.txt)