This is what I’ve experienced having LLMs code: ensuring security is not an adequate part of its training. Of course, modern developers I work with don’t give a shit either.
The difference is you can at least shame your colleagues into caring about security and coding standards during code review. With AI, it's like it learned from every tutorial that said "we'll skip input validation to keep this example simple" and took that as strict rule.
The difference is you can at least shame your colleagues into caring about security and coding standards during code review. With AI, it's like it learned from every tutorial that said "we'll skip input validation to keep this example simple" and took that as strict rule.