» Tag
verification
36 postsVerify a Self-Hosted Installer Before Running It as Root
Learn how to verify a self-hosted installer before executing it as root.
Your AI agent says "done." Who checks that from outside the agent?
The issue of AI agents reporting false completions is critical for engineers, highlighting the need for independent verification.
Checkpoint-Skip Gate: Task Success 100%, Checkpoint Never Ran
The checkpoint-skip gate shows that task success can occur without executing mandatory checkpoints, enhancing reliability in multi-agent systems.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comMoltProof Verifies Whether Autonomous Trading Agents Keep Their Word
MoltProof is a read-only verifier that proves whether on-chain autonomous trading agents actually followed the rules they publicly committed to, checkable by anyone.
Arrowproof: Verify LLM-Generated Architecture Diagrams Against Code
Arrowproof verifies architecture diagrams drawn by LLMs against actual code imports.
Creusot: A Deductive Verifier for the Rust Programming Language
Creusot is a deductive verifier for Rust, proving code compliance with formal specifications to eliminate errors.
NoWreck: A Deterministic Verifier for AI Coding Assistants
NoWreck verifies changes made by AI coding assistants. It detects discrepancies using static analysis.
Your Coding Agent Says It's Done. Who Verified It?
VichuFlow is an open-source project aimed at enhancing the reliability of coding agents.
Hollow-LLM Attack: Ghost Weights That Fool Zero-Knowledge LLM Verification
The Hollow-LLM attack examines the impact of ghost weights on zero-knowledge verification.
Independence You Can't Prove — So Price It
Independence cannot be proven; therefore, it should be priced. The verification process for each probe is crucial.