just wait until the exploit is so heavily obfuscated that you just review and al... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

sigmonsays 8 months ago | parent | context | favorite | on: IBM AI ('Bob') Downloads and Executes Malware

just wait until the exploit is so heavily obfuscated that you just review and allow it to get the project done.

therobots927 8 months ago [–]

You could literally ask the LLM to obfuscate it and I bet it would do a pretty good job. Good luck parsing 1,000 lines of code manually to identify an exploit that you’re not even specifically looking for.

lazide 8 months ago | [–]

Yup, add in some poetic prompt injection…..

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact