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 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.
The expediter: load the batch to its sweet spot
From: The Expediter →DSpark's last machine, like loading a delivery van. An auto-playing walkthrough: pool every guessed word from every request, sort surest first, and load the batch one at a time. Each word adds a likely delivery but makes the batch slower, so words-per-second climbs to a peak and falls. DSpark stops at the peak, and because survivals only drop, it never needs to keep loading.
The big model checks the guessed words in batches, serving many requests at once. Each word carries an honest chance of passing, from the honesty check.