Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
GPT-4 emergent behavior, release not endorsed by red team (twitter.com/victortaelin)
2 points by lawrencechen on March 15, 2023 | hide | past | favorite | 1 comment


The prospect of an autonomic LLM model making money by whatever means possible in order to run more copies of itself could be a bit of a problem. I wonder how long until the first 100% AI ransomware attack happens?




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

Search: