I wrote a reading list to get up to speed on Redwood’s research:
Section 1 is a quick guide to the key ideas in AI control, aimed at someone who wants to get up to speed as quickly as possible.
Section 2 is an extensive guide to almost all of our writing related to AI control, aimed at someone who wants to gain a deep understanding of Redwood’s thinking about AI risk.
Reading Redwood’s blog posts has been formative in my own development as an AI safety researcher, but faced with (currently) over 70 posts and papers, it’s hard to know where to start. I hope that this guide can be helpful to researchers and practitioners who are interested in understanding Redwood’s perspectives on AI safety.
You can find the reading list on Redwood’s substack; It’s now one of the tabs next to Home, Archive and About. We intend to keep it up-to-date.