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 ...

On Thursday, a few Twitter users discovered how to hijack an automated tweet bot, dedicated to remote jobs, running on the GPT-3 language model by OpenAI. Using a newly discovered technique called a ...