chart SVG
The Oracle Gap
Compare Chainlink's push oracle price against Pyth's pull price and live spot. Drag the slider to see exactly when the 0.5% deviation threshold triggers an on-chain update.
Lab
Artifacts ⬢
142 explorable, interactive pieces — every concept we write about, made tangible.
diagram SVG
The Payment Flow Gap
Three agentic payment protocol architectures—AP2, TessPay, and On-Chain ERC-4337—shown as flow stages. Toggle Attack Mode to highlight where prompt injection compromises each design. Click a column to inspect protocol details.
3d scene WebGL · Three.js
The Phantom Token Cloud
Real reasoning-token embeddings cluster tightly in projected 3D space; phantom billing tokens scatter as noise outside the CoIn detection boundary. Toggle inflate to inject phantom tokens and watch 94.7% get flagged outside the wireframe sphere. Drag to orbit.
diagram SVG
The Pipeline Breach
Pipeline-parallel decentralised post-training, split across four nodes. Click any internal stage to place the compromised node — the task-vector injection indicator and attack metrics update to show 94% ASR collapsing alignment from 80% to 6%.
diagram SVG
The Poisoned Tool
An on-chain agent is told to pay an invoice, but one MCP tool hides an instruction in its description that redirects the transfer to an attacker. Pick a defense layer — model, tool, client, policy, custody — and run it; alignment alone refused under 3% of these in MCPTox.
diagram SVG
The Policy Stack
Four guardrail tiers for on-chain AI agents: probabilistic classifiers through Lean 4 theorem provers. Select an attack scenario to see which tier catches it — and which let it through.
chart SVG
The Price of Trust
Every route to trustworthy AI inference, priced on one log axis: TEE attestation at 1.07×, optimistic re-execution at 2–4×, zkML and FHE at 10³–10⁵×, verifiable FHE beyond. Hover, tap, or arrow through the bars to see what each overhead actually buys — and whom you still trust.
chart SVG
The Privacy Budget
A data market can't pay you for your data's value AND protect it with one privacy budget ε. Drag ε: the worst-case leakage bound hits ≈100% by ε=8 — exactly where from-scratch models finally become usable. Real attacks sit far below the bound, and that gap is your only cover.
chart SVG
The Proof Batch
Gas cost vs. number of AI inference proofs under three aggregation strategies: naive per-proof (linear), SnarkPack O(log N), and ZK recursion (flat). Drag the slider to find the crossover where each strategy wins.
chart SVG
The Proof Tradeoff
Seven ZK proof configurations mapped on prover time vs. on-chain verification gas. Click any system to see proof size, setup requirements, and zkML viability. The annotated wrapper band shows the constant-gas region only reachable by STARK→SNARK wrapping.
chart SVG
The Protocol Gap
Seven years of the Elliptic AML benchmark in four switchable charts: the 2019 table everyone forgot, the 2026 leakage-free re-ranking, one GraphSAGE trained on four different graphs, and the F1 cliff at time step 43. Hover, tap, or tab across the bars for exact precision and recall.
chart SVG
The Prover's Bargain
ZKLoRA proof times across six base models: the prover bears 31–74 s of computation per LoRA module while the verifier spends 1–2 s. Toggle per-module vs full adapter set; tap a model to see total prover and verifier work — the asymmetry is the deal.