Interactive explainers and simulators
Mechanisms you can move: the arithmetic inside a transformer, a real softmax over scores you set, a BPE trained on your own text, and a retrieval pipeline that shows you which chunk it lost. Nothing here calls a model, so nothing here is invented.
How a Transformer Works: Step a Sequence Through the Stack
Walk a sequence through all seventeen stages of a transformer block, with the exact parameter count, tensor shape and FLOP cost of each computed from a configuration you set.
Attention Visualiser: The Mask, the Scaling and the Softmax
A real causal mask and a real softmax over a score pattern you choose, on your own sentence, with the row entropy that says how many tokens each query is really attending to.
Sampling Playground: Temperature, Top-p, Top-k and Min-p
Drag temperature and the truncation settings over a distribution you supply, and see the before and after bars, the mass discarded and the entropy that results.
Next-Token Prediction: A Model Small Enough to Check
Counts a real n-gram language model from your own text in the browser and shows the top ten candidates with the raw counts behind every probability.
Tokenizer Playground: Train a BPE and Watch Every Merge
Trains a real byte-pair encoding on text you supply, then lets you drag the merge count and watch your text regroup from characters into subwords with the token count moving as you type.
Embedding Space Walk: king − man + woman, With the Rule Shown
Vector arithmetic on vectors you supply, with the metric and the exclusion rule as switches — because the famous analogy result depends on both and neither is usually mentioned.
Embedding Projection Visualiser: How Much the Picture Lost
Projects your vectors to two dimensions by PCA and draws lines to each point's true nearest neighbours in the full space, so you can see where the flattening misleads you.
Vector Search Simulator: Walk an HNSW Graph One Hop at a Time
Builds a real HNSW index over seeded two-dimensional points and steps through the greedy walk, counting distance computations and measuring recall against a brute-force scan.
Keyword vs Semantic Search: The Same Query, Both Rankings
Runs BM25 and a vector ranking over the same documents side by side, with reciprocal rank fusion, and counts the query terms that score exactly zero on the lexical side.
RAG Pipeline Simulator: Watch the Answer Fall Out of the Context
Mark the sentence that answers your question, then drag chunk size, overlap and k and watch whether that sentence survives chunking and makes it into the retrieved context.
Reranking Demo: What Rerank Depth Can and Cannot Fix
Runs BM25 over your own documents, then shows the ceiling reranking is bounded by — because a reranker can only reorder what the first stage handed it.
Agent Loop Visualiser: Where the Tokens Actually Go
Step count on a slider, input tokens per step as bars, and the exact cost of a run — showing why an agent's bill grows with the square of its steps.
Tool Selection Demo: What Another Tool Costs You
The monthly rent on your tool schemas as the count rises, plus a pairwise overlap check that finds which two of your own tool descriptions are hardest to tell apart.
Prompt Injection Sandbox: Assemble the Prompt Yourself
Builds the literal flat prompt from your system message, your user message and untrusted content, and measures how much of it someone else wrote.
Hallucination Demonstrator: A Generator With No Truth Term
A real n-gram generator over text you paste, with a context slider that walks from gibberish through fluent nonsense to near-verbatim recitation.
Context Degradation Demo: Build the Needle Test
Generates a needle-in-a-haystack prompt at any depth, prices the full sweep, and plots the accuracy curve you measure on your own model.
Quantisation Quality Demo: Run the Quantiser
A real absmax integer quantiser on a bits slider, with exact reconstruction error, the group-size trade, and an outlier control that shows how one weight ruins its neighbours.
KV Cache Memory Simulator: Users × Context → GiB
Exact KV cache arithmetic from your model's shape, with a concurrency slider against a memory bar that shows the moment the card runs out.
Batching and Latency Simulator: The Trade, Live
Throughput and per-request latency across every batch size, from two step-time anchors you measure yourself, with the queue wait that makes high utilisation expensive.
Speculative Decoding Demo: Why Longer Drafts Stop Paying
The draft-and-verify speedup identity on a draft-length slider, with sampled cycles at your acceptance rate and the optimal k marked.
Failover Simulator
Set a failure rate for every hop in a fallback chain and read the exact traffic split, latency and cost it produces.
Rate Limit Simulator
Watch a token bucket drain, refill and start shedding as you drag the arrival rate past the refill rate.
Circuit Breaker Simulator
Tune the thresholds and see how many caller-seconds a breaker saves — and when a long open window makes a short outage worse.
Cost Explosion Simulator
One prompt change, priced at every user count from ten to ten million on a log slider.
Gradient Descent Visualiser
Drag the learning rate and watch a real optimiser walk a loss surface down, converge, crawl or diverge.
Overfitting Demonstrator
Drag polynomial degree and watch training error fall to zero while held-out error turns upward.
Neural Network Playground
Build a tiny network, train it in your browser with real backpropagation, and watch the decision boundary bend.
Scaling Laws Interactive Chart
Enter the coefficients of a scaling law, move the compute budget, and read the compute-optimal parameter and token split it implies.
AI Timeline Interactive
Drag a cursor year across seventy years of AI milestones and see the gaps between them computed.
AGI Forecast Explorer
Enter the AGI forecasts you want to compare as three quantile years each, and read them all off as probabilities at any year you choose.