OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
TechCrunch
Read Full Article at TechCrunch →Ad Slot — In-Article (728x90)
Even with Lockdown Mode, ChatGPT could be still vulnerable to prompt injections, but the goal is to reduce the likelihood that sensitive data gets shared in the process.
This is a summary. For the full story, read the original article at TechCrunch.
Original source: TechCrunch