Archive
18 artifacts published in this period.
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.
Decode speed of a frontier MoE model versus interconnect bandwidth. Each layer's expert routing is an all-to-all shuffle bounded by the slowest link. Drag from NVLink down to home broadband: the line crosses the interactive floor at the datacenter edge, then falls to seconds per token.
A perpetual market maker's quote ladder. Avellaneda-Stoikov skews only for inventory; funding adds a second, signed skew that survives even at zero inventory. Drag the reservation line to set inventory, push funding and horizon, and watch the two skews stack or cancel.
Seven ways to verify what an AI agent claims it did, plotted by latency added against the share of fabricated claims caught. Pick a claim type and watch it route to the cheapest sufficient verifier — a free chain receipt, a 12ms signed receipt, or a zkLLM proof reserved for the inference itself.
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.
Cumulative net carry of a $10k delta-neutral perpetual funding harvest over real Hyperliquid funding regimes. The line starts below zero by the round-trip fee, then climbs at the annualized funding rate; a flip slider rolls it over. Carry, not alpha — until funding inverts.
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.
An inspection game between a solver and a verifier. Drag the operating rate and tune the bond, reward, and bounty to find p*, the minimum sampling rate that makes honest AI inference a dominant strategy — and watch it collapse without a bounty.
Bittensor's Yuma Consensus scores a miner by the stake-weighted median of validator weights, then clips everything above it. Validators sit on a cumulative-stake axis; the consensus line is read at the κ=50% mark. Push a colluding bloc past 50% and watch the pump go from clipped to unstoppable.