AISiliconANGLEabout 2 hours ago
OpenAI details GPT-Red AI for self-attacking models
1 min read
OpenAI detailed GPT-Red, an AI system designed to self-attack models for safety testing. The company also eased usage limits on GPT-5.6, expanding access to the latest model.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
