Comment by dyauspitr
9 hours ago
You will never have a 100% secure LLM just like you don’t have 100% secure people. But what will be secure and deterministic is the code it writes. Any time you need certainty it will just write code for it.
9 hours ago
You will never have a 100% secure LLM just like you don’t have 100% secure people. But what will be secure and deterministic is the code it writes. Any time you need certainty it will just write code for it.
The poisoned prompt will cause the wrong code to be written
> Any time you need certainty it will just write code for it.
Meanwhile: you give it the same exact model the same exact prompt 5 times and get 5 wildly different output