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

A quote from The Verge live blog: "Early red teaming showed that the model could help plan attacks" on things like schools. "We don't want to aid in illegal activity." So the model is used to act as a bad actor to test the model itself.

Based on that last sentence, I think I have a good idea now how AGI will take over humanity. ;)

(Not implying that the current tech is anywhere close to AGI.)



> Early red teaming showed that the model could help plan attacks" on things like schools. "We don't want to aid in illegal activity.

As if that wasn't possible with conventional search engines.


And this was a huge public concern when the internet/search engines initially got popular. "Omg you can Google the ingredients to build a bomb! This shouldn't be allowed!!"




Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

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

Search: