On the one hand this is exactly the right solution to prevent lethal trifecta exfiltration attacks.

The existence of lockdown mode does however imply that ChatGPT, in its default settings, does not provide robust protection against sufficiently determined data exfiltration attacks!

▲

berlianta 4 hours ago | parent | next [-]

Related: Simon Willison’s post on OpenAI’s new Lockdown Mode (he coined the “lethal trifecta” term this is based on): https://simonwillison.net/2026/Jun/5/openai-help-lockdown-mo...

▲

jameshart 4 hours ago | parent [-]

Related: simonw is Simon Willison

	▲	berlianta 3 hours ago \| parent [-]
		Yeah I know the source references him (replying to his comment), that's exactly why I'm giving credit where it's due

▲

Noumenon72 3 hours ago | parent | prev [-]

I hadn't realized that deep research or generating images that I paste into Twitter were possibly exfiltrating my data. Yikes.