What does it mean for #AI to be #aligned? And how hard is #alignement? Hannah Rose Kirk from the University of Oxford explores these questions using insights from the #PRISM Alignment Dataset.
#AI #DiversityinAI #InclusiveAI #largelanguagemodels
#humanvalues #airesearch #ethicalai #prismproject #machinelearning #datarepresentation #airesearch #llm
source