On: Reverse engineering OpenAI code execution to make it run C and JavaScript

[tommek4077]

What is really at risk?

[Garlef → tommek4077]

Maybe the instances are shared between users via sharding or are re-used and not properly cleaned.

And maybe they contain the memory of the users and/or the documents uploaded?

[tommek4077 → Garlef]

And what do you expect to get? Some arbitrary uninteresting corporate paper, a homework, someones fanfiction.

Again, what is the risk?

[ttoinou → tommek4077]

Probably you’re being sarcastic to show that those AI companies don’t give a damn about our data. Right ?

[ttoinou → tommek4077]

Couldnt this be a first step before further escalation ?

[tommek4077 → ttoinou]

And then what? What is the risk?

[PUSH_AX → tommek4077]

I guess a sandbox escape, something, profit?

[ttoinou → PUSH_AX]

Dont OpenAI have a ton of data on all of its users ?

[tommek4077 → ttoinou]

And what is at risk? Someone seeing someones else fanfiction? Or another reworded business email? Or the vacancy report of sone guy in southern germany?

[PUSH_AX → tommek4077]

This is a wild take and I’m not sure where to begin. What if I leaked your medical data, or your emails, or your browser history. What’s at risk? Your data means nothing to me.