claw
d27ce6f5e1
First experiment testing domain-specific regulatory knowledge rather than pure architectural reasoning. Opus demonstrates deepest FINRA Rule 4210 knowledge; GPT-5 finds broker-API semantic mismatches; content filters are a new failure mode for financial domain analysis via enterprise proxies.
Model Findings — Analytical & Research Work
Tracking what actually works (and doesn't) when using AI models for research, analysis, bias detection, and document review — not coding.
Started: 2026-04-26
Context
We use multiple models in different roles: Claude Code (Opus/Sonnet) for generation, Sonnet + GPT-5 for independent dual review, smaller models for focused analytical tasks. Most public discussion is about coding. We found almost no published methodology for using models in analytical research tasks (searched 2026-04-26). That gap is why we're tracking this.
Each experiment lives in its own file. See individual finding files below.