AI alignment aims to make AI systems act according to our preferences.
Humans excel at generalising from few examples and dealing with noise.
Statistical AI models struggle with out-of-domain generalisation.
Explainable mechanisms are key to achieving alignment in human-AI teaming.
Evaluating AI's generalisation involves measuring distributional shifts and robustness.
Get more accurate answers with Super Search, upload files, personalized discovery feed, save searches and contribute to the PandiPedia.
Let's look at alternatives: