@ericjmorey@programming.dev to

Programming@beehaw.org • 4 months ago

Do Users Write More Insecure Code with AI Assistants?

cross-posted to:
programming@programming.dev

15

Do Users Write More Insecure Code with AI Assistants?

@ericjmorey@programming.dev to

Programming@beehaw.org • 4 months ago

cross-posted to:
programming@programming.dev

~n (@nblr@chaos.social)

This is fine... "We observed that participants who had access to the AI assistant were more likely to introduce security vulnerabilities for the majority of programming tasks, yet were also more likely to rate their insecure answers as secure compared to those in our control group." https://arxiv.org/abs/2211.03622

cross-posted from: https://programming.dev/post/8121843

~n (@nblr@chaos.social) writes:

This is fine…

“We observed that participants who had access to the AI assistant were more likely to introduce security vulnerabilities for the majority of programming tasks, yet were also more likely to rate their insecure answers as secure compared to those in our control group.”

[Do Users Write More Insecure Code with AI Assistants?](https://arxiv.org/abs/2211.03622?

You must log in or register to comment.

HotTopNewOld

Chat

The Bard in GreenA
link
fedilink
13•4 months ago
People are including AI generated code in their projects without fully reading it or understanding how it works.
- @ericjmorey@programming.devOP
  link
  fedilink
  13•4 months ago
  The same ones that were blindly copying and pasting from StackOverflow previously found a more convenient way to make their code “work”.