← 返回 2026-03-09

Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation

Helena Casademunt, Bartosz Cywiński, Khoi Tran, Arya Jakkli, Samuel Marks, Neel Nanda 📅 2026-03-05 👍 3 2026-07-13 08:35

❌ 总结生成失败(process_error)

pi exited with code 1: Warning: No project session found with id 'summary-2603.05494-2a5e42a9'; creating a new session with that id. 400: {"code":"1301","message":"System detected potentially unsafe or sensitive content in input or generation. Please avoid using prompts that may generate sensitive content. Thank you for your cooperation."}