Discussion and research on AI alignment. alignmentforum.org
Discusses how to safely defer to increasingly capable AIs for AI safety and strategy work, covering the basin of good deference, required alignment and capability profiles, and the lead time needed to manage exogenous risks.
Forecasts that AI will automate capabilities research before safety research, argues this ordering is risky, and proposes differential-acceleration steps such as building safety-research automation tools and granting safety researchers early model access.