ChatGPT's new Lockdown Mode lets you disable web access and more to protect sensitive data from prompt injection
Quick Answer
OpenAI's ChatGPT introduces Lockdown Mode, disabling web access and certain features to mitigate prompt injection risks.
Quick Take
While it enhances data protection, it doesn't eliminate the threat, as prompt injection remains a challenge.
Key Points
- Lockdown Mode disables web access, Deep Research, and Agent Mode.
- It aims to make data theft via prompt injection more difficult.
- Prompt injection attacks are still a significant unresolved issue.
- The mode only blocks the final step in data exfiltration.
- OpenAI continues to address the ongoing challenges of prompt injection.
Source Excerpt
OpenAI's new Lockdown Mode for ChatGPT disables web access, Deep Research, and Agent Mode to make data theft through prompt injection attacks harder. The mode doesn't fully prevent such attacks, it only blocks the final step in an exfiltration chain. Prompt injection remains an unsolved problem.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
