Get Started
Research questionWhy does human understanding rely on predictive compression, and why must its models be simple and transmissible?Compression can reflect an ability to predict relational structure, but it does not by itself explain explanatory understanding or competence with novelty. Human understanding also supports trust and learning from others, creating pressures toward models that are demonstrable, transmissible, and simple.
AI
Machine Learning
Research Paper
Latest papersRecent research connected to this question, newest first.Why We Care About Understanding: Competence through Predictive CompressionThe source provides a theoretical framework rather than an empirical benchmark or implementation recipe. It addresses human understanding and the interpretability or inscrutability of AI systems, without specifying a particular model architecture or evaluation procedure.research paper · Sep 4, 2026
Related questions
How can machine learning education build accurate mental models that support appropriately calibrated reliance on AI systems?How can we measure whether computer-vision models are understandable to independent human evaluators?How can language models compress conversational and document context without reconstruction while preserving task-relevant information?Can language models infer others’ mental states as social interactions evolve under unreliable information?
Home
Topics
Search
Library