Interactive Explainers
Complex ML and AI concepts made accessible through interactive simulations. Learn by playing, not just reading.
GRPO: Group Relative Policy Optimization
How GRPO turns a handful of sampled answers into a training signal without a value network: a primer, four interactive studies and the decisions they settle
Intermediate18 min2026-08-22 · kit.draft
mlreinforcement-learningllm-trainingreasoning
MCP 2026-07-28: Stateless Core, Extensions, Tasks
What the 2026-07-28 revision of the Model Context Protocol changes and how the new mechanisms behave: seven stepped figures, their notes quoted or paraphrased from the specification and the extension specs, plus what to build with today
Intermediate20 min2026-08-22 · kit.draft
mcpprotocolsagentsstatelesstasks
More explainers coming soon...
Topics in the queue: Attention Mechanisms, Gradient Descent, Transformers