AI too unpredictable in aligning with human values

JohnMaguire · January 28, 2025, 8:06am

Designer · January 28, 2025, 10:44pm

Yes, just like humans align with each other

Topic		Replies	Views
Alignment faking in large language models the world of ai	0	24	December 23, 2024
Would anyone like for their R-1 to have more personality to it? Like the so many A.I. apps that you can chat with when bored or lonely. To have a more intuitive and personal conversation with your R-1... general chat	62	493	February 1, 2025
Rabbits Morality? general chat	49	231	August 7, 2024
The AI safety layer destroys the r1 all things rabbit	4	130	June 14, 2024
AI Pin EOL and Rabbit general chat	0	57	February 20, 2025