Why Humans Can’t Trust Ai: You Don’t Know How It Works, What It’s Going To Do Or Whether It’ll Serve Your Interests

AI systems are becoming increasingly ubiquitous in our lives, but their inner workings are often impenetrable and unpredictable, making it difficult to trust them. Deep learning neural networks are used to build many AI systems, which contain trillions of parameters that affect the strength of connections between neurons. This makes it difficult to explain why AI systems make the decisions they do, leading to the AI explainability problem. An example of this is the Trolley Problem, where an AI must decide whether to run over a child or swerve and crash, potentially injuring its passengers.