How Will Super Alignment Work? Challenges and Criticisms of OpenAI's Approach to AGI Safety & X-Risk

bci/acc: A Pragmatic Path to Compete with Artificial Superintelligence, by Trent McConaghy

What is 'AI alignment'? Silicon Valley's favorite way to think about AI safety misses the real issues

PDF) The alignment problem from a deep learning perspective

Artificial General Intelligence and how (much) to worry about it

AGI safety — discourse clarification, by Jan Matusiewicz

The Future of Artificial General Intelligence (AGI) – Future Disruptor

Survey XII: What Is the Future of Ethical AI Design?, Imagining the Internet

I Would Have Solved Alignment, But I Was Worried That Would Advance Timelines — LessWrong

Preventing an AI-related catastrophe - 80,000 Hours

Paul Christiano: Current work in AI alignment — EA Forum

OpenAI's Planning For AGI And Beyond - by Scott Alexander