Memory isolation failure in ChatGPT: context leaked across sessions

> Don’t trust ChatGPT with sensitive content or critical tasks — until OpenAI provides...

Don't do that anyway. For a company that large, the average Joe suing for breach of policy is damned near impossible, so don't post sensitive data to a black box like that even if they pinky swear it's safe to do so

what? you have a multitenant system with isolation between users not within a user. OpenAI has literally been working on "memory" and context across everything you have done, they obviously are storing and retrieving recent context. I see no indication in this at all that they are using browser or local storage for anything, because we know they run other models to summarize and extract info from context. Likely you could turn it off if thats configurable yet.