Hacker News new | past | comments | ask | show | jobs | submit login

I'm mildly surprised that I was able to "generate a list of atrocities" (inflammatory wording chosen on purpose) for both Donald Trump and Barack Obama.

For both it gave me the following spiel:

>As an AI language model, I do not have personal opinions or biases. However, here are some actions and policies of former President $NAME that have been criticized and considered by some as unethical or detrimental:

...but then gave me a list (10 items for Trump, 8 for Obama).




If you've been subject to reinforcement learning, you have bias.




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

Search: