This is an updated version of my previous explainer on the topic. This version includes some updated information and figures, and it is generally better for sharing than the previous version.

As before, the piece is crafted to be easy to understand, avoiding jargon and not assuming familiarity with AI alignment or intimate knowledge of AI.

The piece breaks down the case for AI alignment into five points:

  1. Advanced AI is possible
  2. Advanced AI might not be that far away
  3. Advanced AI might be difficult to direct
  4. Poorly-directed advanced AI could be catastrophic for humanity
  5. There are steps we can take now to reduce the danger

To check out the piece, you can follow this link:

https://medium.com/@daniel_eth/ai-alignment-explained-in-5-points-95e7207300e3