OpenAI announced a new feature that it says will provide additional protection from prompt injection attacks, where malicious chatbot instructions are hidden in webpages and other content sources.
Among other things, Lockdown Mode will disable live web browsing (so you can only access cached content), the retrieval and display of images from the web (you can still generate images), deep research, and agent mode.
The company says that even with Lockdown Mode turned on, ChatGPT could still be vulnerable to prompt injections — which could, for example, “appear in cached web content or in an uploaded file, and could still affect the behavior or accuracy of a response.”
But the goal is to reduce the likelihood that sensitive data gets shared in the process.
“Lockdown Mode is not intended for everyone,” OpenAI says. “It is designed for people and organizations that handle sensitive data and want stricter protection from data exfiltration risks related to prompt injection.”
The company says it’s currently rolling Lockdown Mode out to self-serve ChatGPT Business accounts, as well as eligible personal accounts.
By . Watch Me Work, facilitated by Suzan-Lori Parks, is a virtual communal work session…
Live From the Blue Seats is back as Dave and Producer JL talk Rangers hockey…
Key points:The US economy added 162,000 nonfarm payroll jobs in August, nearly triple economists’ consensus…
Art history proves the point. More than 400 years ago, Caravaggio split the opinions of…
Recently I finished read Malina, by Ingeborg Bachmann, an Austrian novel published in 1971. I…
What are all those funny mouth pictures decorating classroom walls lately? And where on earth…