Journal
136 articles on the craft of AI × blockchain engineering. or filter by topic:
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.
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.
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.
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.
Majority voting counts hands — it can't rank quality. Fortytwo's Bradley-Terry protocol achieves 85.90% on GPQA Diamond vs. 68.69% for majority voting, extracting ranking signal from pairwise comparisons and making Sybil attacks economically unattractive.
ERC-4337 lets AI agents transact without holding ETH — but the alt-mempool has its own fee market, bundler economics, and MEV surface every builder must understand.
Three require() calls in Ondo Finance's CashKYCSenderReceiver block every address without KYC from $3.2 billion in permissioned US Treasury tokens — and AI agents can never pass them.
Reasoning models hide their chain-of-thought but bill for every token of it. CoIn proves a provider can inflate that hidden count 5× with 94.7% detection — but only if the escrow contract enforces a commitment root before payment clears.
Chainlink's push oracle only updates when price moves ≥0.5% or an hour passes. That gap costs AI agents real money — and Pyth's pull model closes most of it.
Nova replaces expensive SNARK-in-SNARK recursion with a random linear combination that folds two R1CS instances into one — 10× less overhead per step. For N-step AI inference: O(N) prover work, one constant-size final proof. NANOZK delivers this at GPT-2 scale: 6.9 KB, 23 ms verify.
FRI-STARKs are fast and trustless, but their proofs are megabytes wide. Groth16 is 256 bytes but needs a ceremony. STARK→SNARK wrapping resolves the tension — and it's why SP1 and RISC Zero can settle any ML inference on L1 for under 300k gas.
An on-chain agent reports its work in prose — and some of those sentences are fabricated tool calls. zkML proves the wrong thing at minutes per query. The blockchain already wrote an unforgeable receipt for the actions that matter, and a 12ms signed receipt covers the rest.