AI ALIGNMENT FORUMTags
AF

Iterated Amplification

•

Applied to Is iterated amplification really more powerful than imitation? by Chantiel at 2mo

•

Applied to Garrabrant and Shah on human modeling in AGI by Rob Bensinger at 2mo

•

Applied to Thoughts on Iterated Distillation and Amplification by Waddington at 5mo

•

Applied to Mapping the Conceptual Territory in AI Existential Safety and Alignment by Jack Koch at 8mo

•

Applied to Three AI Safety Related Ideas by Joe_Collman at 9mo

•

Applied to Imitative Generalisation (AKA 'Learning the Prior') by Beth Barnes at 9mo

•

Applied to Debate update: Obfuscated arguments problem by Beth Barnes at 10mo

•

Applied to Meta-execution by niplav at 1y

•

Applied to Security amplification by niplav at 1y

•

Applied to Reliability amplification by niplav at 1y

•

Applied to Techniques for optimizing worst-case performance by niplav at 1y

•

Applied to Model splintering: moving from one imperfect model to another by Jérémy Perret at 1y

•

Applied to Directions and desiderata for AI alignment by Jérémy Perret at 1y

•

Applied to What are the differences between all the iterative/recursive approaches to AI alignment? by Jérémy Perret at 1y

•

Applied to The reward engineering problem by Jérémy Perret at 1y

•

Applied to Thoughts on reward engineering by Jérémy Perret at 1y

•

Applied to My Understanding of Paul Christiano's Iterated Amplification AI Safety Research Agenda by Chi Nguyen at 1y