Discussion and research on AI alignment. alignmentforum.org
Argues the main bottleneck for AI safety is policymakers' lack of awareness of catastrophic risk, so advocacy and engagement should be prioritised over research, with supporting evidence on NGO submissions and enforcement gaps.
An exploratory essay that maps RL policy entropy and RLHF onto psychotherapy concepts, reviews RLHS and RISE, and proposes three untested alignment training methods.
A broad review organising AI alignment into Target, Assurances and Method, covering value alignment, corrigibility, cooperation, control, debate and safety cases as an introductory framework.
Proposes that AI safety should organise as bottom-up big science with a mosaic scientific culture, arguing top-down approaches driven by competition or accidents risk narrow goals and missed unknown unknowns.