Harness Engineering
The Model Landscape
What each popular model is actually good and bad at.
You can jump straight in, but this star assumes Fine-tuning. Not recommended as a first stop.
Four layers of depth
Each layer ends with a quiz. Finish layer 4 and you own this concept.
- L1IntuitionA map of today's major LLM families and the axes that actually distinguish them.5m
40 XP - L2MechanicsHow dense vs. MoE architectures, training compute, and release strategy actually shape a model's behavior and cost.8m
70 XP - L3CodeWrite code to inspect a model's architecture and compute the active-vs-total parameter split for an MoE layer.12m
110 XP - L4FoundationsScaling laws, compute-optimal training, and the arithmetic behind 'how big should this model be'.15m
180 XP
Where this leads
33 stars in the atlas.