AI★★★★OpenAI · Wed, 15 Ju
GPT-Red: Enhancing AI Safety via Automated Red Teaming
OpenAI introduces GPT-Red, an automated red teaming system that leverages self-play to boost AI safety, alignment, and resistance to prompt injection.
📌 Key points
- GPT-Red utilizes self-play mechanisms
- Enhances AI safety and alignment
- Improves resistance to prompt injection
本页为 gitzw.com 基于公开来源的 AI 中文解读,非原文转载。