OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
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.
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.
Summary aggregated from TechCrunch's public RSS feed. The full reporting belongs to TechCrunch — please read it on their site.