Dalin Huang
I build AI that builds. And the trust that lets it ship.
Currently at Parker AI, taking marketing fully agentic.
01 ASK THE MODEL
No API calls and no large language model. A tiny classifier (the network in the picture) trains in your browser when the page loads and helps pick one of my hand-written answers. The rest plays out, step by step, how an LLM would produce that answer.
LLMSplits text into sub-word tokens from a learned vocabulary.
HereSimulated. The classifier has no vocabulary: it hashes your words, word pairs and letter triples into 1,024 input slots.
LLMEach token looks up a learned vector that encodes its meaning.
HereReal. Each row is the 64 numbers the classifier learned for one of your words; the last row is the whole question after ReLU.
LLMWith RAG, the question is compared with document chunks by cosine similarity.
HereKeywords pick the answer first, then the closest example question, then the classifier, and only if it knows one of your words. The scores beside the resume sections are simulated.
LLMThe prompt passes through every transformer block, and attention decides which tokens look at which.
HereSimulated. The classifier has no attention; the arcs show what it looks like in a real model.
LLMScores every token, softmax turns the scores into probabilities, and one token is sampled.
HereSimulated. The answer text is fixed, so it can't invent facts, though the wrong answer can get picked. The real softmax is in the picture: one probability per answer.
LLMTraining measures how wrong the output was and sends that error backwards to nudge every weight.
HereReal, on the classifier. 👍 runs one gradient step that makes this answer more likely for your question; 👎 makes it less likely. The weights change only in your browser. The big version is what I run at Parker AI: user reactions feed a fine-tuning queue for our self-hosted models.
02 THE AGENT OFFICE · 14 desks · 1 human gate
My personal agent team: Grok bots plus Claude Code. Tickets flow down the lane. Trusted changes ship to prod on their own; the long tail waits for a human. Click a desk to meet an agent.
03 KNOWLEDGE MAP · career clock: roles ↔ skills
My career as a clock: roles inside, skills outside. Hover or tap to trace them.
04 EXPERIENCE
05 PROJECTS
06 CONSOLES · a replay
What my agent team and a fine-tuning run print while they work. A replay for show, not live data.