Visualizers
Learn by moving things
Interactive explainers for the ideas behind retrieval, embeddings, and agents. A formula tells you what is true; dragging a vector shows you why. Each one also appears inside the article it belongs to, and runs entirely in your browser, so drag, poke, and break it.
The modern AI ecosystem (interactive)
A live map instead of a static landscape picture. Click any of the eleven layers, from LLMs and RAG to MCP, memory, and vector databases, and animated flowing connectors stream out to the real tools in that layer, with a one-line explanation of what the layer does.
LLM
The models that actually generate the text. Everything else plugs into one of these.
Why a parallel draft goes sloppy (auto-playing)
From: Draft, Then Verify →A looping explainer, no clicking. Two replies fit equally well, 'of course' and 'no problem'. The autoregressive drafter picks one coherently; the parallel drafter, predicting both positions blind to each other, crossbreeds them into 'of problem'. Every word plausible alone, incoherent together.
Someone says "Thanks!" The model will reply with two tokens.
The draft-and-verify cycle
From: Draft, Then Verify →One cycle of speculative decoding. A small draft model guesses the next tokens in one pass; the large target model verifies them together, accepts the correct prefix, and corrects the first miss. Step through it and watch one target pass commit several tokens.
So far, the model has written the text above. Now it needs the next tokens.