A

ai-safety

A small, transparent experiment testing whether language models distinguish solvable prompts from prompts containing missing or contradictory information, and whether their stated confidence tracks correctness

A deterministic verification layer for AI systems. QWED verifies AI outputs using mathematics, symbolic reasoning, and formal methods (Z3, SMT, SymPy), creating an auditable trust boundary for agentic AI. Not generation. Verification.

Coordinated Agent Swarm Testing — open-source framework that deploys 100 Claude AI agents in five specialized squads (Security, Logic, Robustness, Performance, Data Integrity) to systematically analyze codebases for bugs, security issues, and code quality problems. A research-backed substitute for human beta testing. Empirical results from the published paper: 100 agents analyzed a 12,500-line React/TypeScript application in 63 minutes, identified 687 unique findings, at a total cost of $7.97 — compared to $2,000-$20,000 for equivalent human beta testing. Available via npm (cast-swarm) and as an MCP server. Apache 2.0 licensed. Published preprint available.