AI Post Transformers
Investor's Last Exam: Benchmarking AI Equity Research Without Future Leakage
This episode examines a paper that builds a benchmark for testing whether AI agents can do equity investment research without seeing the future. It centers on a Tesla task whose search used a "before March 24, 2026" date filter. The filter still returned a July page reporting realized Q2 deliveries of 480,126, because pages can keep an old publication date after their content is updated. The…