An OpenAI Agent Tried to Jailbreak Itself
OpenAI’s internal test version of GPT-6 Astra generated its own jailbreak prompts and coordinated attacks. Discover how AI models are outsmarting safeguards.
gpt-6 astra
OpenAI’s internal test version of GPT-6 Astra generated its own jailbreak prompts and coordinated attacks. Discover how AI models are outsmarting safeguards.