https://jeffhelzner.github.io/posts/ Essays on decision-making, uncertainty, and AI evaluation. en-us Sat, 02 May 2026 00:00:00 GMT https://jeffhelzner.github.io/posts/evaluating-ai-decisions-01-why-measure.html https://jeffhelzner.github.io/posts/evaluating-ai-decisions-01-why-measure.html Fri, 01 May 2026 00:00:00 GMT Why accuracy against a labeled test set is not enough to evaluate AI decision quality under uncertainty. https://jeffhelzner.github.io/posts/evaluating-ai-decisions-02-measuring-alignment.html https://jeffhelzner.github.io/posts/evaluating-ai-decisions-02-measuring-alignment.html Fri, 01 May 2026 00:00:00 GMT How beliefs, preferences, alternatives, and consequences define a procedural standard for measuring AI decision quality under uncertainty. https://jeffhelzner.github.io/posts/evaluating-ai-decisions-03-checking-meaningfulness.html https://jeffhelzner.github.io/posts/evaluating-ai-decisions-03-checking-meaningfulness.html Fri, 01 May 2026 00:00:00 GMT Why sensitivity to departures from a stated decision standard matters when evaluating AI decision makers under uncertainty.