Learn Before
Relation

Frontier Foundation Models, Capability Evaluation, and Just-In-Time Agent Harnesses @ University of Michigan - Ann Arbor

Learners will explore the technical foundations of frontier model evaluation, predictable scaling, and multimodal alignment as exemplified by GPT-4. The curriculum details evaluation integrity through contamination analysis, post-training effects on calibration, and rule-based safety mechanisms. Furthermore, learners will examine modern autonomous agent engineering, analyzing how dynamically generated harnesses and evolutionary optimization unlock new scaling dimensions beyond parameter count.

0

1

Updated 2026-09-11

Tags

Prep Sessions