Tests a novel lens asking 'what cognitive/procedural load does this design
place on operators?' Applied to escalation-policy.md with GPT-5, Sonnet 4.6,
and Opus 4.6.
Key findings:
- All models identified manual liquidate→restrict has no procedure (CRITICAL)
- GPT-5 excels at exhaustive enumeration (21+ findings, config gaps)
- Opus identifies systemic vulnerabilities (monitor crash → silent unsafe state)
- Sonnet fills procedural gaps (authorization, timeouts)
Recommendation: Opus alone for time-constrained analysis, GPT-5 + Opus for
thoroughness. They find different types of issues with minimal overlap.
claw