Basic concepts

This section introduces some of the fundamental concepts in AI safety. Here are some good starting places:

• What is artificial general intelligence (AGI)?

• What is intelligence?

• What is AI safety?

• What are existential risks (x-risks)?

If you've already got a handle on those, try these:

• What is the orthogonality thesis?

• What is instrumental convergence?

• What is corrigibility?

• What is the difference between inner and outer alignment?

There's a lot of jargon in this field. These articles aim to clear up some terminological confusions:

• What are the differences between AGI, transformative AI, and superintelligence?

• What are the differences between AI safety, AI alignment, AI control, Friendly AI, AI ethics, AI existential safety, and AGI safety?

• What are the differences between a singularity, an intelligence explosion, and a hard takeoff?

If you're ready for some more advanced reading, there’s a later section with further concepts.