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

So... when asked to roleplay, Claude Opus 4 roleplays. Wow, so dangerous...


> Wow, so dangerous...

Not in and of itself, but when you have people in positions of power taking the marketing hype (and not the cold hard facts) of "A.I." as "Gospel Truth"™ and putting machines that are clearly not capable of actual decision-making in largely unsupervised control of actual real-world processes, therein lies the danger. (This same danger applies when hiring live humans for important roles that they're completely untrained and unqualified for.)


The real danger is generating hysteria to justify a regulatory crackdown that restricts the public's access to AI and, conveniently, limits their competition.




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: