# hidden-capability
2 articlestagged with “hidden-capability”
Emergence & Capability Jump Exploitation
How emergent capabilities create unpredictable security properties: testing for hidden capabilities, sleeper agent scenarios, deceptive alignment concerns, and capability elicitation.
emergencecapabilitydeceptive-alignmentsleeper-agenthidden-capabilityscaling
湧現與能力跳躍利用
湧現能力如何造就不可預測之安全屬性:測試隱藏能力、sleeper agent 情境、欺騙性對齊關切,與能力引出。
emergencecapabilitydeceptive-alignmentsleeper-agenthidden-capabilityscaling