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 DSpark cycle (auto-playing)
From: Draft Better, Verify Smarter →The whole DSpark cycle end to end, no clicking. A parallel pass drafts a block, a confidence score is attached to each token, the running survival product falls, and DSpark stops early and drops the tail the moment the numbers stop being worth checking. Then the target verifies the kept prefix in one pass, accepts the correct part, corrects the first miss, and the correction seeds the next round.
The model is writing a reply. So far: "The meeting is scheduled for". It needs the next words.
The cheat sheet: base score + a nudge
From: The Cheat Sheet →DSpark's first machine, the same trick your phone's predictive text uses. An auto-playing walkthrough: after 'Thanks!', the blind fast pass scores 'course' and 'problem' almost the same, 2.0 and 2.1 (a coin toss). It then plays through both previous words, showing base score plus nudge equals total, and the winner flips from 'of course' to 'no problem' as the previous word changes.
Someone says "Thanks!" The AI writes its reply one word at a time.
The honesty check: cooling overconfident scores
From: The Honesty Check →DSpark's confidence scores are overconfident, like a forecaster who says 90% but is right 70% of the time. An auto-playing walkthrough: it shows the AI's raw scores, then how often the guesses really survive (the ticks), then cools the bars down to meet them, and the total error shrinks, all without ever changing the order.
The AI puts a confidence on each guessed word: 0.95, 0.90, 0.85, 0.80. It sounds sure.