OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks

OpenAI has introduced a new feature called Lockdown Mode aimed at limiting the exposure of confidential information when users interact with ChatGPT. While the feature does not fully eliminate the risk of prompt injection, it is intended to lower the chance that sensitive data is shared during a conversation.

Summary written by Kernelia from the original article by TechCrunch AI. The story and its rights belong to its author.