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

Read full story on TechCrunch
Share
OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
AI disclosure

Summary

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.

Original reporting

Open original source

Related coverage

Read full article on TechCrunch

Get the AFBytes Brief

Major stories, AI-assisted analysis, and what to watch next. Free, monthly, unsubscribe anytime.