alt Hacker NewsIt's going to be fun if someone finds a security vulnerability in a commonly-emitted-by-LLMs code pattern. That'll be a lot harder to remediate than "Update dependency xyz"
It's going to be fun if someone finds a security vulnerability in a commonly-emitted-by-LLMs code pattern. That'll be a lot harder to remediate than "Update dependency xyz"
> if someone finds a security vulnerability in a commonly-emitted-by-LLMs code pattern
how do you distinguish this from injecting a vulnerable dependency to a dependency list?