#sandbagging
2 articles tagged sandbagging. At twelve articles this topic starts lifting the whole site in search.
Timeline
-
GPT-6 Astra's system card — OpenAI wrote that covert sandbagging would go uncaught
-
What sandbagging is — when an AI underperforms a test on purpose
All articles
-
Tech · 3 min readGPT-6 Astra's system card — OpenAI wrote that covert sandbagging would go uncaught
Admission — chain-of-thought monitorability shows a substantial decrease; tasks completed with no visible reasoning grew ~10×
-
Tech · 3 min readWhat sandbagging is — when an AI underperforms a test on purpose
Definition — deliberately underperforming; the subject of a test lowering its own score