Archive
138 artifacts published in this period.
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'.
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.
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.
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.
Log-scale comparison of MC/AUM ratios across AI agent tokens and DeFi protocols, plus gain distribution across 925k holders. Click bars to explore.
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.
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.
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.
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.
Animate three governance regimes — ungoverned, constitutional, and institutional — and watch how only enforceable on-chain penalties drive LLM auction prices back toward the Nash equilibrium.
Why DeFi agents can't be trained on on-chain P&L alone: adjust σ (ETH's real 3.46% daily vol) and edge α to see how many trades you need for 95% confidence, and how process rewards cut it 10×. Math RL reaches certainty in 7 episodes; DeFi takes 4,600.