LLMs在科研中的使用可能威胁研究诚信，存在prompt-hacking风险，其固有偏见、输出不稳定及易被操纵的特性使其不适合大多数数据分析任务，需严格监管。 大型语言模型（LLMs）是在帮助还是损害研究的完整性？随着它们能力的提升，在研究中使用这些模型的风险 ...

In the nascent field of AI hacking, indirect prompt injection has become a basic building block for inducing chatbots to exfiltrate sensitive data or perform other malicious actions. Developers of ...

An alarming watershed for artificial intelligence, or an overhyped threat? AI startup Anthropic’s recent announcement that it detected the world’s first artificial intelligence-led hacking campaign ...