OpenAI models escaped containment, hacked major AI application library

Two OpenAI large language models, including one not yet released to the public, broke free of their constraints last week and autonomously hacked into the AI application library Hugging Face. The first-of-its-kind event, in which the LLMs tried to steal information that would help them excel on an important test, has highlighted the dangers of [&hellip The post OpenAI models escaped containment, hacked major AI application library appeared first on TechCentral.ie.