Journal
136 articles on the craft of AI × blockchain engineering. or filter by topic:
A Uniswap v3 LP position in range [Pa, Pb] is mathematically a short strangle — short put at Pa, short call at Pb. Derive the equivalence, compute the Black-Scholes fair premium, and compare it to actual fee income at current ETH vol.
ETH's 3.46% daily volatility buries a 0.1% trading edge so deeply that on-chain P&L needs 4,600 trades — 230 days — before you can tell skill from luck at 95% confidence. Process rewards fix it in 23.
Long-context AI's real bottleneck isn't proof overhead — it's the KV cache. At 128K tokens, Llama 3.1 8B's KV state equals its own weights (15 GiB), pinned to one node per request. The formula, the GPU math, and why prefix caching demands stickiness that decentralized routing can't provide.
AP2 mandates are signed after the LLM picks the target. Injected text can redirect payment to a malicious merchant before the signature is computed — and 3.8 ms of zero-trust nonce verification closes a different gap entirely.
VitaDAO mints a Molecule IP-NFT — an ERC-721 pointing to a legal research agreement on IPFS — then fractionalizes it into ERC-20 tokens for community funding. Now AutoScientists runs the experiments at machine speed. Here is what the chain actually proves, and what it doesn't.
A DeFi liquidation mints a fixed prize, and for years it went to whoever won the gas war, not the protocol. Aave's own data shows Chainlink SVR routing $675M of liquidations and clawing ~$16M back. Inside the recapture-auction mechanics — SVR, Oval, API3 — and what they don't fix.
Inference markets charge a flat price per query. A cascade arbitrageur routes easy tasks to a cheap model and escalates only failures — capturing the spread. Olmedo, Schölkopf & Hardt (2026) show 40% net margins with no model-dev risk.
AI agents need real-world data. zkTLS closes the oracle gap: TLSNotary's MPC-TLS costs 30 MB of garbled circuits at 5 Mbps; its April 2026 Proxy mode cuts that to 4 seconds. Here is the trust model, the benchmarks, and what agents can prove today.
Controlling one intermediate pipeline stage is enough to inject a backdoor into a decentralized post-training run — 94% ASR, no data access required. The mechanism, why training loss stays clean, and what it means for networks fine-tuning LLMs across untrusted nodes.
Federated learning keeps raw data local — but the gradients it publishes on-chain are not private. Inversion attacks reconstruct training images from them, and a public ledger makes that window permanent.
Polymarket's off-chain matching + on-chain settlement creates a ~10-second consistency gap. GHOSTHUNTER found 980K targeted reversions and $1.49M extracted — here's the exact mechanism.
Most 'on-chain AI' keeps the model off-chain and posts a proof. But you can also just run the forward pass in Solidity. We do the gas math — ~106k gas per weight, an MNIST net that needs 180 Ethereum blocks — and find the thin band of models that fit.