• 0 Posts
  • 20 Comments
Joined 2 years ago
cake
Cake day: June 9th, 2023

help-circle






  • You can try, but you can’t make it correct. My ideal is to write code once that is bug-free. That’s very difficult, but not fundamentally impossible. Especially in small well-scrutinized areas that are critical for security it is possible with enough care and effort to write code with no security bugs. With LLM AI tools that’s not even theoretically possible, let alone practical. You will just need to be forever updating your prompt to mitigate the free latest most fashionable prompt injections.














  • What’s the consequences for getting caught? Even if they do detect you messing with their install image, what are they going to do about it besides tell you to put it back? Unless they’re going to make you go for psych visits over software removal, it seems to me you may as well just try it and find out.