OpenAI has launched an "offline isolation" mode for cutting-edge AI training and evaluation to curb jailbreak attacks.
OpenAI posted on October 23, announcing that stricter security controls have been implemented for the training and evaluation environments of its most advanced "frontier models." The company clarified that during model training, direct access to the real-time internet will not be permitted.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open the original article on ITHome