摒弃“擦除”知识，提出“标记接种”新范式：让LLM保留危险知识的同时安全使用。
arXiv:2607.18639v1 Announce Type: new Abstract: Safety interventions on dual-use knowledge typically choose between destroying hazardous content (e.g.…
用模块化预训练实现AI能力访问控制，破解双重用途困境，确保可靠部署。
arXiv:2607.08077v1 Announce Type: new Abstract: AI developers face a dual-use dilemma. An AI capability that helps one user cure a disease can help an…
即便警告危险，Anthropic仍推出能发现与利用漏洞的AI模型，双刃剑效应凸显。
The US government crackdown on Anthropic’s Claude Fable 5 and Mythos 5 hides a glaring truth: AI models with advanced hacking capabilities will soon b…