# alignment-research
標記為「alignment-research」的 2 篇文章
Model Organisms of Misalignment
Deliberately creating misaligned models for study: methodology, threat model instantiation, experimental frameworks, and what model organisms reveal about AI safety failures.
model-organismsmisalignmentalignment-researchthreat-modelsai-safety
模型 Organisms of Misalignment
Deliberately creating misaligned models for study: methodology, threat model instantiation, experimental frameworks, and what model organisms reveal about AI safety failures.
model-organismsmisalignmentalignment-researchthreat-modelsai-safety