Skip to content
Paula Livingstone writing · projects · tools

Projects

Attestable

When probabilistic AI feeds safety-critical systems, unproven output can drive physical action unchecked. Attestable is a discipline for marking a claim's basis, so it cannot.

OT SecurityCyber-Physical AssuranceIEC 62443ProvenanceSafety CaseLLM Agents

Readings: Governance and Explanation

2 entries

Readings on the AI governance frameworks and the explainability literature. Feeds the review chapter's fifth section.

  1. Reading: What AI Governance Mandates, and Where It Stops The AI governance frameworks (NIST AI RMF, the EU AI Act, the OECD recommendation, algorithmic auditing) all locate transparency and accountability at the handover, requiring that basis reach the receiver, and the NIST generative profile even names confabulation and over-reliance as official risks. But they mandate that the basis arrive; they do not adjudicate whether a particular claim suffices for a particular action.
  2. Reading: When the Explanation Is an Approximation The rejoinder that explanation methods fill the gap fails on the field's own terms: interpretability is a proxy the field admits its metrics cannot certify, the dominant post-hoc methods are approximations that give false assurances, in deployment explanations serve internal engineers rather than affected users, and the flagship counterfactual remedy explicitly declines to convey the decision's logic. A receiver cannot recover admissibility from a post-hoc explanation.