Hacker NewsLeo de Moura Formal Verification for AI Code via LeanLeo de Moura Blog·high signalXBlueskyLinkedInCopy linkLean creator argues formal verification is the only scalable answer to AI code that half fails security tests. 249 pts.SourceSource pageLeo de Moura Blog↳ Follow the threadPolicy dependency / Stack layerFour advisories land on Databricks' Omnigent meta-harness, one critical, all reported by an autonomous security agentGitHub Security AdvisoriesPolicy dependency / Stack layerDistilling 1,000 ML repos into 5,000 verified skills lifted an agent 134% on MLE-bench with the model and budget held fixedarXiv 2609.02749Policy dependency / Stack layerPattern: four coding-agent CLIs shipped self-hosted or in-network execution controls in the same weekCursorPolicy dependency / Stack layerAgentic Settlement Protocol Adds Escrow and Three Deadlines Because x402's Atomic Payment Fails Real CommercearXiv 2609.02208Policy dependency / Stack layerClaude Code 2.1.259 refuses to start when a managed settings file cannot be parsedClaude Code ChangelogPolicy dependency / Stack layerCROSS-CATEGORY: Four Unrelated Vendors Shipped Agent Authorization Control Planes Inside 48 HoursJetStream (corroborated by Genesys Xperience 2026 coverage, aiagentstore.ai and Hacker News Show HN)Policy dependency / Stack layerUnsloth 0.1.805-beta doubles Qwen3.8-Flash-Next and GLM-5.3-Flash inference with MTP on by defaultGitHubStack layer / Threat patternToolJet, a 40.8k-Star Retool Alternative, Shipped an MCP Server That Builds Apps Without CodegenToolJet (Show HN)