OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
Mahi
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.
from TechCrunch https://ift.tt/HhAd4ED
from TechCrunch https://ift.tt/HhAd4ED