Panel on Causality
summary
Panelists argue causality lives in models: claims are about what an interventionist causality model predicts, which interventions are allowed, and which variables are chosen. Examples: age as a macro proxy for intervenable biological mechanisms; asthma appearing protective because it triggers faster, higher-quality care; day–night niches explaining coexistence. Refining models flips causal answers, so causation is model-dependent. Practical concerns include strategic gaming (books in admissions) and packaging treatment/context with predictions.
AI-written summary · about
chapters (4)
- 0:00Start
- 35:33How Does Interpretability Relate to Robustness of the Model
- 42:08Causal Pathways
- 46:41The Dynamics of the Explanation
related talks
26mCausal inference with Causallib
17mArchitecture panel
43mDiscussion
31mPanel: The AI Architecture Debt—Refactoring Infrastructure for Sustainable Privacy
45mModeling as Mind Redesign: Why participatory AI is better
33mPanel: How Privacy Engineers Can Shape the Coming Wave of AI Governance
26mWhy More Context Makes Your Agent Dumber and What to Do About It
30mFrom Constraints to Cognition: A Hybrid Framework for Adaptive, Explainable(…)