21–30 of 39 posts
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!
"Prompt injection is not currently a major risk, but its impact could grow as attackers develop more sophisticated methods." - that's such a weird statement to make. It's one of the most significant factors limiting the adoption of the technology in business. I have mixed feelings about this feature. We're playing with tech that's supposed to do human-shaped things but can't be trusted nearly as much as a human emplo…
And "trusted nearly as much as a human employee", well... you do know that phishing and insiders are two primary ways for attackers to get into company infrastructure, right?
AIs pair human-shaped capabilities with human-shaped vulnerabilities. It's a way of automating PEBKAC.
If so many tools are straight up blocked, I would be very sceptical of the quality of the results.
Is this an admission that prompt injection attacks can indeed not be blocked by an analysis based technique? If so many tools are straight up blocked, I would be very sceptical of the quality of the results.
https://x.com/sama/status/1891533802779910471
Somehow he comes off as even less human than zuck
Always has been before he was associated with OpenAI.
Which is weird because the bullshit he spouts isn’t so different to the bullshit other top execs spout and I don’t have the same visceral reaction to them (though I still don’t like a bunch of them).
"Prompt injection is not currently a major risk, but its impact could grow as attackers develop more sophisticated methods." - that's such a weird statement to make. It's one of the most significant factors limiting the adoption of the technology in business. I have mixed feelings about this feature. We're playing with tech that's supposed to do human-shaped things but can't be trusted nearly as much as a human emplo…
Suspect thats the point, by giving you the “choice” they also make the user responsible or can at least shift the blame.
Is this an admission that prompt injection attacks can indeed not be blocked by an analysis based technique? If so many tools are straight up blocked, I would be very sceptical of the quality of the results.
I think "prompt injection prevention" systems fall into the same category as "llm writing detection" systems. I.e. reality is always a step ahead and you shouldn't trust either one for anything remotely important.
That's a problem we are just now wrapping our minds around.
It's not as simple as prompt sanitization. The model is the interpreter, and we don't yet have the right tools to guide it.
Yet, their tools such as codex are able to read ALL FILES on my PC without explicit permission unless you spawn them within a container: https://github.com/openai/codex/issues/2847
It seems like OpenAI stealing sensitive data from their customers is not a big problem for them as it has been reported as an issue for almost a year now and currently has the 2nd most upvotes among open issues (they work on issues based on upvotes, so they claim).
> reduce the risk of data exfiltration Yet, their tools such as codex are able to read ALL FILES on my PC without explicit permission unless you spawn them within a container: https://github.com/openai/codex/issues/2847 It seems like OpenAI stealing sensitive data from their customers is not a big problem for them as it has been reported as an issue for almost a year now and currently has the 2nd most upvotes among o…
Why not just use your OS-integrated permission mechanism? No container needed.