🤓 Latest Submissions
COMMIT: Factory That Measures Bad Work
COMMIT is a software factory that measures how much bad work it can kill. AI agents ship code fast, but green tests do not prove strong verification. The deeper problem is structural: the agent that builds software can also become the agent that decides it is correct. COMMIT turns verification into an independent release gate inside BAND Desktop. Three generic seats share the work: Planner, Builder, Verifier. Planner converts the specification into numbered requirements and acceptance conditions. Builder implements, commits, and reports exact commands and raw evidence. Verifier has no production-code edit authority: it rebuilds each candidate in a fresh container with no network, reruns the official checks, and attacks behavior happy-path tests miss — spec-derived contract checks, a reference model with replayable seeds, 50-way concurrency attacks, and mutation testing of its own checks. When verification fails, it REJECTS with a reproduction command; Builder repairs; Verifier re-checks: REJECT → REPAIR → RE-VERIFY → ACCEPT. The submitted run (5 Oct 2026): all four Pocketful stages ACCEPTED in 9 h 32 min. The official harness (isolated, all stages) reaches stage 4, and every stage folder claims its own stage. Stage 1 ran a full 782-mutant campaign (92.5% killed). Zero lines of stage code were written by a human; model spend was $33.57. The full room log (room.json, 1,517 messages) is in the repository. Human input, disclosed: the dispatch, plus one time-limit message (finish by 23:00; sampled mutation from stage 2 on). In calibration, the verifier's kill rate rose from 64% to 95.4% as every escaped mutant became a new check. Pocketful demonstrates the factory. Evidence demonstrates the claims.
6 Oct 2026
YieldMind
YieldMind is an autonomous, delta-neutral LP agent designed to solve DeFi’s "silent killer": impermanent loss (IL). In traditional liquidity providing, users often find their hard-earned yield evaporated by price volatility. YieldMind fixes this by combining high-yield Aerodrome pools with automated short hedging via the Kraken CLI, creating a "set-and-forget" strategy that targets pure yield without directional risk. The Mechanics of Neutrality The agent operates on a continuous orchestrator loop: Scanning: It analyzes Aerodrome Finance pools on the Base chain, scoring them based on a proprietary matrix of APR, TVL, and volatility. Hedging: Once a pool is selected, the agent deposits liquidity and immediately executes a matching short position on Kraken. This ensures the portfolio remains delta-neutral, meaning if the asset price drops, the short profit offsets the LP loss. Rebalancing: It polls the state every cycle. If the price moves enough to cause a "delta drift" beyond 5%, the agent automatically adjusts the hedge to maintain equilibrium. The On-Chain Trust Stack The biggest barrier to AI agents in finance is the "black box" problem. YieldMind solves this using the ERC-8004 standard to provide a verifiable audit trail: Verifiable Identity: The agent is registered on-chain with a unique NFT-based ID. Cryptographic Proofs: Every trade intent and validation artifact is EIP-712 signed. This means you don't have to "trust" the agent; you can verify its decisions on the Sepolia testnet. Risk Guardrails: A Risk Router contract gates execution, ensuring the agent cannot exceed pre-set slippage or capital limits. Reputation: Successful cycles build a public reputation score, making the agent’s performance history transparent and immutable.
12 Apr 2026
