Book

The Alignment Problem

Brian Christian

The clearest non-technical account of why specifying what we want is the hard part. It is a research history as much as an ethics book, which is what makes it credible.

• Artificial intelligence
• Risk
• Incentives

1 idea from this book

• FrameworkArtificial intelligence

  A system optimises the objective you wrote, not the one you meant

  Whatever you can measure and reward will be maximised literally, including the gaps between the measure and the goal.

  AI product and risk discussions, designing any metric or bonus scheme, and evaluating a model's objective.