logoalt Hacker News

palmoteayesterday at 1:15 PM3 repliesview on HN

Don't worry, I'm sure this was all an AI agent's fault, so no one to blame and all they need to do is update their code review prompts to not make mistakes.


Replies

markbooyesterday at 2:04 PM

AI agent: sorry for that, I'll build the next version will be the most secured one

show 1 reply
HPsquaredyesterday at 1:49 PM

Also add the word "secure" a lot.

show 1 reply
DrammBAyesterday at 2:42 PM

Actually they are taking one from Anthropic's playbook and saying it's the user's fault for misunderstanding what "sharing" means.