Live data from Hacker News

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

twitter.com

61–70 of 89 posts

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

#61
post #60

It’s crazy I’m so afraid of this kind of security failures that I wouldn’t even think of releasing an app like that online, I’d ask myself too many questions about jailbreaking like that. But some people are fine with this kind of risks ?

What is really at risk?

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

#62
post #60

It’s crazy I’m so afraid of this kind of security failures that I wouldn’t even think of releasing an app like that online, I’d ask myself too many questions about jailbreaking like that. But some people are fine with this kind of risks ?

What is really at risk?

I guess a sandbox escape, something, profit?

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

#63
post #60

It’s crazy I’m so afraid of this kind of security failures that I wouldn’t even think of releasing an app like that online, I’d ask myself too many questions about jailbreaking like that. But some people are fine with this kind of risks ?

What is really at risk?

Couldnt this be a first step before further escalation ?

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

#65

Given it’s running in a locked-down container: there’s no reason to restrict it to Python anyway. They should parter/use something like replit to allow anything! One weird thing - why would they be running such an old Linux? “Their sandbox is running a really old version of linux, a Kernel from 2016.”

It’s running gVisor which currently reports its kernel version as 4.4.0, even though it’s actually implementing a much more recent version of Linux.

I know this because at Modal.com we also use gVisor and our users occasionally ask about this.

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

#68
post #48

Earlier quoted context omitted.

This works on humans too. Normie: How do I do X in Linux? Linux nerds: RTFM, noob. vs. Normie: Linux sucks because you can't do X. Linux nerds: Actually, you can just apt-get install foo and...

All due respect, but that's the average experience in Arch Linux forums, unfortunately. At least we now have LLMs to RTFM for us.

From what I've heard I'm really happy that I never ventured too deep into the Arch forums.

The wiki however was (is?) absolutely fantastic. I used it as a general-purpose Linux wiki before I even switched to Arch, I distinctly remember the info on X Multi-Head being leagues above other resources I could find.

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

#69

Earlier quoted context omitted.

Because it's deterministic, accurate, and correct. All of which the LLM would be unable to do.

That depends. If the problem has been solved before and the answer is known and it is in the corpus, then it can give you the correct answer without actually executing any code.

Is it not generally true? If the information (i.e. problem and its answer) exists in the model's training corpus, then LLMs can provide the correct answer without directly executing anything.

Ask it what the capital of France is, and it will tell you it is Paris. Same with "how do I reverse a string in Python", or whatever problem you have at hand that needs solving (sans searching capability, which makes things more complicated).

So does not the problem need to be unique if you want to be able to claim with certainty it indeed has been executed? I am not sure how you account for the searching capability, and I am not excluding the possibility of having access to execution tools, pretty sure they do.

Post reply on HN