Malevolent Artificial Intelligence (Sam Harris is Wrong, Part 4)

The┬ásecond-ever┬ápost on this blog is about the question of malevolent AI. I will now revisit the question with more detail, having had time to refine my thoughts. I don't think the question of malevolent AI, more broadly, the "AI alignment problem," can be simply dismissed. If my view has changed at all since the last … Continue reading Malevolent Artificial Intelligence (Sam Harris is Wrong, Part 4)