#AIExplainability brought to the next level (source: https://arxiv.org/pdf/2002.05202)
#AIExplainability brought to the next level (source: https://arxiv.org/pdf/2002.05202)
@rysiek @woody The first step in controlling or regulating AI is predicting what it will do next.
( #AIControlProblem #AISafety #AIAlignment - https://en.m.wikipedia.org/wiki/AI_alignment )
And to predict what a system will do next you have to first get good at explaining why it did what it did the last time.
The smartest researchers think we're decades away from being able to explain deep neural networks. So LLMs & self driving cars keep doing bad things.
#AIExplainability - https://en.wikipedia.org/wiki/Explainable_artificial_intelligence