Although there are a few ways to mitigate the risk, the only way to block it is to get AI to differentiate instructions from data, which is impossible today.
if the instruction is messy fuzzy human language to a system that was not coded instruction by instruction but got generated and trained then there never is a way to differentiate instructions from data if i’m not mistaken
We know that some humans can be trained to do that just fine. Humans are natural neuronal networks. That implies, neuronal networks can in principle do it. We just don’t have any human-capability artificial neuronal networks yet.
LLMs might never get there. But humans aren’t LLMs. If we ever manage to properly model a human brain, that probably will be able to do that task with human-level accuracy (which actually is pretty good if you only look at professionals of the filed).
Hopefully, it doesn’t actually need a human brain for the task - because modeling that might still be a century off.
if the instruction is messy fuzzy human language to a system that was not coded instruction by instruction but got generated and trained then there never is a way to differentiate instructions from data if i’m not mistaken
We know that some humans can be trained to do that just fine. Humans are natural neuronal networks. That implies, neuronal networks can in principle do it. We just don’t have any human-capability artificial neuronal networks yet.
LLMs might never get there. But humans aren’t LLMs. If we ever manage to properly model a human brain, that probably will be able to do that task with human-level accuracy (which actually is pretty good if you only look at professionals of the filed).
Hopefully, it doesn’t actually need a human brain for the task - because modeling that might still be a century off.
Well, good thing we’ve only poured a trillion and a half dollars into it and wrecked the economy.