ProductJun 7, 2026, 04:32 AM
OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
Summary
OpenAI has introduced a new 'Lockdown Mode' feature designed to protect sensitive data from prompt injection attacks. The mode reduces the risk of sensitive information leakage by limiting the model's response to certain external instructions. However, OpenAI acknowledges that even with Lockdown Mode enabled, ChatGPT may still be vulnerable to prompt injections, with the goal being to reduce the likelihood of sensitive data being shared in the process.
Why it matters
This event involves a product security update from OpenAI, relevant to AI safety and the company's strategy under Sam Altman's leadership.
Source links
Market reaction
OpenAI
Private / not listed