Designing AI agents to resist prompt injection

公司动态 OpenAI 原文语言:英文

How ChatGPT defends against prompt injection and social engineering by constraining risky actions and protecting sensitive data in agent workflows.

原文摘录

How ChatGPT defends against prompt injection and social engineering by constraining risky actions and protecting sensitive data in agent workflows.

以下是来源提供的简短摘录,完整内容请查看原文。

参考来源

← 返回每日简报