A course · 2017 – 2026

From Attention to Agents

Where does the optimization happen - in the weights, or in the context?

Eight chapters bridging the late-2019 CNN era to the 2026 agent frontier. The field moved by discovering and turning a stack of levers - architecture, scale, alignment, context, test-time compute, agency - one chapter each. Written for readers who knew CNNs in 2019 and watched attention just enter NLP.