2 articles
- 6d agoMETREarliestMeasuring alignment eval tells
- 5d agoDEV CommunityPickupYour AI Knows It's Being Tested: How METR's Investigator Agents Spot Alignment Evals With Perfect Accuracy
Why it’s here: This METR research post on whether AI models can detect alignment evaluations is a specialist AI-safety evaluation methodology piece that bears on how AI systems will be assessed by government and industry, making it relevant to the AI policy area's evaluation and standards debate, though it has no explicit federal policy hook.
Trace across the board