Lab
142 explorable, interactive pieces — every concept we write about, made tangible.
Step through a flash loan transaction — three strategies (triangular arb, collateral swap, self-liquidation), same atomic structure. The amber step is the only place the AI agent reasons; everything after it is deterministic EVM. Tap a strategy chip, then tap any step.
Three require() calls in Ondo Finance's CashKYCSenderReceiver block every address that isn't KYC-verified. Toggle wallet type and compliance model to see which $5B+ tokenized treasury tokens an AI agent can — and can't — reach.
MSM and NTT throughput across four ZK prover hardware tiers — CPU, GPU H100, TPU v6e8, ZK ASIC — normalized to CPU on a log scale. Toggle SNARK (MSM-heavy) or STARK (NTT-heavy) to see how the proof system's operation mix determines end-to-end speedup. Tap a row to inspect.
Five hops — Human → Orchestrator → Sub-Agent → MCP Tool → Chain Call — and zero authentication in the baseline. Toggle No Auth, IBCT Compact, or IBCT Chained; tap any edge chip to see what its token proves, what it carries, and what it can't verify. Based on AIP arXiv:2603.24775.
Log-scale comparison of MC/AUM ratios across AI agent tokens and DeFi protocols, plus gain distribution across 925k holders. Click bars to explore.
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.
KV cache size (GiB) vs context length for Llama 3.1 8B, 70B, and 405B on log-log axes, against A10G / H100 VRAM ceilings. Toggle BF16, INT4, or DeltaKV compression and drag the cursor — the panel shows whether the live KV state fits on a single GPU.
How much of a reasoning model's output is actually thinking? For three model tiers at three task difficulties, stacked bars show thinking tokens dwarfing output — then a scheme matrix shows which verification schemes can see the thinking and which attest to the answer alone.
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.
Autonomous LLM firms undercut each other below unit cost in a race to bankruptcy, then survivors monopoly-price. Drag price discovery up to deepen the crash (the paper's counterintuitive result), or add stabilizer firms to rescue the market. Deterministic model of Agent Bazaar's 'The Crash'.
Train a model on its own output, generation after generation. Each step draws a finite sample of size M and refits — so the tails starve first and the curve collapses toward a spike. Toggle replace vs accumulate: replace drives σ̂ toward zero, accumulate holds it. A copy of a copy of a copy.
The on-chain gas cost of verifying a TEE attestation quote, across three paths: naive Solidity (~4.5M), the EIP-7951 precompile (~3.5M), and a zkVM-compressed proof (flat ~290k). Tap a bar and scale to attestations-per-day — the flat proof is the only path that survives continuous agent attestation.