Answering questions about
I'm asking something else
What is AI safety?
Is AI safety about systems becoming malevolent or conscious and turning on us?
Where can I find people to talk to about AI alignment?
Why can’t we just do x?
What are some AI alignment research agendas currently being pursued?
Why might a superintelligent AI be dangerous?
What is everyone working on in AI alignment?
Why is AI alignment a hard problem?
Superintelligence sounds like science fiction. Do people think about this in the real world?
Where can I learn about AI alignment?
How close do AI experts think we are to creating superintelligence?
What are some objections to the importance of AI alignment?
OK, I’m convinced. How can I help?