Lab
145 explorable, interactive pieces — every concept we write about, made tangible.
A single mech request, drivable: drag the priority mech's response time across the 60-300s window. Inside it the priority mech delivers and gains Karma; past it a backup delivers, the priority mech forfeits the fee and is docked Karma. Live Olas marketplace constants.
Interactive diagram of Ethereum's FOCIL slot: four phases from IL broadcast (16 validators, 8 KiB each) through builder assembly to attestation. Toggle 'censoring builder' to watch the fork-choice rule reject a block that drops a valid IL transaction.
On-chain cost of a query versus how much history it touches. Re-executing pays a cold SLOAD per value and hits the 60M block-gas wall — or can't reach the data at all. A coprocessor's proof verifies flat at ~300k gas whatever the size. Drag the cursor or pick a real query; the cyan line never moves.
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.
Open weights can't be locked, so ownership is proven by counting surviving fingerprints. Embed thousands of secret key-response pairs; an adversary fine-tunes to scrub them and each audit burns one to leakage. Watch the reserve survive — or not.
Settlement trust on four rollup architectures, mapped on a log time axis from 2-second soft confirmation to 7-day fraud-proof closure. Click any segment to see what that trust level means and which AI agent actions it covers.
Log-scale bar chart comparing FHE vs MPC inference latency for BERT-Tiny, BERT-Base, ResNet-20, and ResNet-50. Click a model to see memory and throughput detail.
A 2D map of EigenCloud's four fault classes — click any fault type to see which slashing mechanism applies and why.
Three protocol TVL zones defined by A1's $6k attack break-even vs. $60k audit cost. Click a zone to see the threat model and recommended defense.
When an LLM agent writes the exploit, the fight is unit economics. Break-even contract value against cost-per-scan: the attacker's line, and the defender's sitting 10× higher because a bounty pays a tenth of a theft. The band between is the attacker-only zone, with A1's six models at measured cost.
Ethereum's MEV-Boost relays mapped by inclusion policy (neutral → OFAC-censoring) and block-delivery share. 38.6% of blocks censor. Tap a relay to see what it can deny an AI agent; toggle FOCIL to watch the exclusion risk collapse.
Drive a Virtuals ACP escrow job: client funds USDC, provider submits a deliverable hash, and whoever sits in the evaluator's chair springs the payout. Seat the client (what ~all of Base does), a neutral agent, or no one — then run it or let someone cheat, and watch who's left exposed.