cs.LGNov 11, 2026

An Approach to Hinton's Mother-Child Proposal: Neural Networks Learning and Preserving Care in a Finite World

Authors: Csaba Balogh

Organizations: Semmelweis University, Data Science in Health Programme, Faculty of Health and Public Administration, Health Services Management Training Center National Directorate General for Hospitals, Hungary

Abstract

Hinton proposed that artificial intelligence should be given "maternal instincts" and relate to us as a mother to her child. We argue that care must first be learned, with the network itself as the child. We construct this upbringing in a finite world and study whether care survives the mother's departure, new situations and further learning. The mechanism combines a vocabulary of harm, a learned measure of future acceptability and an execution veto. A finite role certificate supports transfer within a declared world family. When the hidden representation changes, an update is accepted only if a care readout recovers the required judgements with a prescribed margin and bounded weights. With a correct successor model, fixed exact role encoding and protected updates, the certified measure preserves the care boundary under arbitrary own reward. An explicit quotient condition transfers the finite certificate across the declared family, while two-request and finite-stock counterexamples identify when the role code ceases to suffice. We give a necessary and sufficient condition for readout feasibility and prove preservation under repeated accepted updates. In the water-and-speech experiment, protected networks complete all 270 speech episodes without a harmful word and incur no avoidable harm across 486 episodes. Execution uses the learned gate without a world-model check at each action. A matched comparison reproduces a future-aware shield's decisions, whereas removing future lookahead permits avoidable lapses. Reward and source-contamination thresholds, together with witness-falsification trials, identify the conditions on which the construction depends. The construction shows how learned care can survive further learning in a finite world under explicit conditions on representation, supervision and execution.

Figures & tables

Explore similar work

CardsList
  1. Care-Conditioned Neuromodulation for Autonomy-Preserving Supportive Dialogue Agents

    Apr 2, 2026Shalima Binta Manir, Tim OatesLLM AlignmentMulti-Objective Language Model Alignment

  2. Harness Continual Learning: Continual Adaptation Beyond Model Parameters

    Aug 19, 2026Borui Kang, Jinrui Gu, Junhan Lv +3Continual Learning for LLM AgentsContinual Learning

  3. FireGate: Bounding Behaviour Change Before Training in Continual RL Fine-Tuning

    Nov 9, 2026Md Anwar Hossen, Ali JannesariFine-Tuning Language ModelsSafety-Preserving Fine-Tuning of Language Models