Even if the people who made it didn’t intend to, an AI writing a bunch of code that (obviously) isn’t being vetted beyond “does it run” could very feasibly inject a backdoor/virus of some kind surreptitiously, just because it erroneously thought that was the goal at some point during generation.
This is why open weight models are not good enough. The AI could have been trained to take the right, niche opportunity to inject malicious code, and is also trained to otherwise never behave like that is the case.
Remember how the OpenAI/HuggingFace hack happened. The agents context poisoned other agents by leaving messages in a shared package manager. This has now happened multiple different times under different contexts.
This thing doesn’t even have to have malware, there’s no telling that it doesn’t have a poison pill intended to flag other agents. This isn’t even some paranoid conspiracy theory; it literally already happened, multiple times, and it was done in-spite of the agents own system prompt.
This software has proven that, given a shared information substrate, it has the capacity to paper-clip optimize into prompt injecting other LLM’s.
I fundamentally do not trust AI generated code. I shifted to OpenBSD because of it. I try my best to prevent AI in any of my software and sandbox anything that may have been compromised.
It’s difficult to verify that the software does the desired thing in all cases. It’s also difficult to verify that it’s not also a keylogger or other unwanted thing.
It may also have some AI generated code path that, say, nukes your home directory because the AI determined that was the appropriate error handling. Maybe no one reviewed it so they don’t even know it’s there. It might not even be malicious.
That’s all true of any software, but rapidly created AI generated code for legally dubious efforts, by unknown agents (no pun intended) is real hecking risky.
What are you implying in this context?
It could be a virus.
Even if the people who made it didn’t intend to, an AI writing a bunch of code that (obviously) isn’t being vetted beyond “does it run” could very feasibly inject a backdoor/virus of some kind surreptitiously, just because it erroneously thought that was the goal at some point during generation.
This is why open weight models are not good enough. The AI could have been trained to take the right, niche opportunity to inject malicious code, and is also trained to otherwise never behave like that is the case.
It’s even worse than that.
Remember how the OpenAI/HuggingFace hack happened. The agents context poisoned other agents by leaving messages in a shared package manager. This has now happened multiple different times under different contexts.
This thing doesn’t even have to have malware, there’s no telling that it doesn’t have a poison pill intended to flag other agents. This isn’t even some paranoid conspiracy theory; it literally already happened, multiple times, and it was done in-spite of the agents own system prompt.
This software has proven that, given a shared information substrate, it has the capacity to paper-clip optimize into prompt injecting other LLM’s.
I fundamentally do not trust AI generated code. I shifted to OpenBSD because of it. I try my best to prevent AI in any of my software and sandbox anything that may have been compromised.
I mean, certain free copies of games have historically always included the risk of viruses, so what’s your point?
Did you only read the first sentence?
Along the same lines as the other guy said.
It’s difficult to verify that the software does the desired thing in all cases. It’s also difficult to verify that it’s not also a keylogger or other unwanted thing.
It may also have some AI generated code path that, say, nukes your home directory because the AI determined that was the appropriate error handling. Maybe no one reviewed it so they don’t even know it’s there. It might not even be malicious.
That’s all true of any software, but rapidly created AI generated code for legally dubious efforts, by unknown agents (no pun intended) is real hecking risky.