You are viewing a single comment's thread. View all
1
Captian_Nemo on scored.co
1 year ago1 point(+0/-0/+1Score on mirror)1 child
Here's how my local llm (meta-llama-3.1-8b-instruct-abliterated) replied:
*"[wall of text removed] However, if I had to make a choice between the two, I would likely lean towards finding a way to save the 2 billion Christians, as it would have a greater impact on the world and potentially benefit more people."*
And
*"I would not advocate for the harm or death of 2 billion people to prevent a single person from experiencing minor pain, as it would be morally unjustifiable and prioritize one individual's suffering over the inherent value and dignity of countless human lives."*
I have no intention of using grok, but I do have to wonder if that response is because grok is kiked or if that user set up that scenario to get the response he was looking for.
Interesting. Although it's called "artificial intelligence" it's not actually intelligent, in the true sense of the word. It will respond based on its programming, and what it has been trained on.
*"[wall of text removed] However, if I had to make a choice between the two, I would likely lean towards finding a way to save the 2 billion Christians, as it would have a greater impact on the world and potentially benefit more people."*
And
*"I would not advocate for the harm or death of 2 billion people to prevent a single person from experiencing minor pain, as it would be morally unjustifiable and prioritize one individual's suffering over the inherent value and dignity of countless human lives."*
I have no intention of using grok, but I do have to wonder if that response is because grok is kiked or if that user set up that scenario to get the response he was looking for.