Research program D
Rigorous ways to measure and compare AI systems, including the methods ALGEDI applies to its own work.
A result is only as strong as the instrument that produced it. This program designs and validates those instruments: rubrics, controls, failure taxonomies and replication packages. It also holds ALGEDI’s own publications to the same standard.
When an agent reports that a task is complete, how often does independent evidence agree? This entry frames the question and the checks that would settle it. It reports no results.
When a model explains a decision after making it, does the explanation match the evidence that was available to justify the decision? This entry defines the question without any claim about hidden internal reasoning. It reports no results.
A rubric-based approach to judging AI-generated learning material for correctness, curriculum alignment, level appropriateness, answer-key accuracy and instructional quality. This entry defines the question. It reports no results and no model comparison.
