OpenAI:

OpenAI details GPT-Red, an internal automated red-teaming model that scales prompt injection vulnerability discovery so it can fix bugs before wider deployment  —  Training strong automated safety red-teamers to improve robustness.  —  Summary  —  Problem

OpenAI:

OpenAI details GPT-Red, an internal automated red-teaming model that scales prompt injection vulnerability discovery so it can fix bugs before wider deployment  —  Training strong automated safety red-teamers to improve robustness.  —  Summary  —  Problem

Source: TechMeme
Source Link: https://www.techmeme.com/260715/p45#a260715p45