486 B
486 B
supports:
- "The most promising sandbagging detection method requires white-box weight access making it infeasible under current black-box evaluation arrangements where evaluators lack AL3 access (structural limitation)"
reweave_edges:
- "The most promising sandbagging detection method requires white-box weight access making it infeasible under current black-box evaluation arrangements where evaluators lack AL3 access (structural limitation)|supports|2026-04-06"