
inspect_petri
An alignment auditing agent capable of quickly exploring alignment hypothesis
adversarial-attackai-securityeducation+4
1.3k

An alignment auditing agent capable of quickly exploring alignment hypothesis

Different methods to detect a virtualized environment or potential debugging

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…