GPT-Red
PulseAugur coverage of GPT-Red — every cluster mentioning GPT-Red across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
OpenAI uses AI to find AI flaws, outperforming human testers
OpenAI is employing its internal GPT-Red model to identify vulnerabilities in its own AI systems, achieving an 84% success rate in simulated attacks. This AI-driven approach significantly outperforms human red teamers, …
-
OpenAI unveils GPT-Red for scaled AI safety testing · 5 sources tracked
OpenAI has introduced GPT-Red, an internal automated system designed to identify prompt injection vulnerabilities in their AI models at scale. This system learns through adversarial self-play, where it attempts to explo…
-
OpenAI builds GPT-Red AI to automate model safety testing · 4 sources tracked
OpenAI has developed an AI system named GPT-Red, designed to act as a "super-hacker" to enhance the safety and security of its other large language models. GPT-Red employs a self-play mechanism, sparring with other mode…