News for hackers. Stuff that matters.
Re:AI Copilots Are Changing How Coding Is Taught by ben_w on Saturday May 04, 2024 @06:02AM (#40256340)
It's definitely possible to inject malicious code that humans don't spot, there was a whole competition dedicated to humans doing this in C well before LLMs: https://en.wikipedia.org/wiki/Underhanded_C_Contest

Now I'm wondering, can you put in a comment which the LLM will pay attention to such that it generates subtle back-doors? And can this comment be such that humans looking at the code don't realise this behaviour will be due to the comment?

Re:AI Copilots Are Changing How Coding Is Taught by golergka on Saturday May 04, 2024 @12:52PM (#40258835)
This once again proves that C is the best language to write backdoors.