AI ALIGNMENT FORUMTags
AF

Iterated Amplification

•

Applied to Interpretability’s Alignment-Solving Potential: Analysis of 7 Scenarios by Evan R. Murphy at 9d

•

Applied to HCH and Adversarial Questions by Ruben Bloom at 3mo

•

Applied to My Overview of the AI Alignment Landscape: A Bird's Eye View by Neel Nanda at 5mo

•

Applied to Is iterated amplification really more powerful than imitation? by Chantiel at 9mo

•

Applied to Garrabrant and Shah on human modeling in AGI by Rob Bensinger at 10mo

•

Applied to Thoughts on Iterated Distillation and Amplification by Waddington at 1y

•

Applied to Mapping the Conceptual Territory in AI Existential Safety and Alignment by Jack Koch at 1y

•

Applied to Three AI Safety Related Ideas by Joe_Collman at 1y

•

Applied to Imitative Generalisation (AKA 'Learning the Prior') by Beth Barnes at 1y

•

Applied to Debate update: Obfuscated arguments problem by Beth Barnes at 1y

•

Applied to Meta-execution by niplav at 2y

•

Applied to Security amplification by niplav at 2y

•

Applied to Reliability amplification by niplav at 2y

•

Applied to Techniques for optimizing worst-case performance by niplav at 2y

•

Applied to Model splintering: moving from one imperfect model to another by Jérémy Perret at 2y

•

Applied to Directions and desiderata for AI alignment by Jérémy Perret at 2y

•

Applied to What are the differences between all the iterative/recursive approaches to AI alignment? by Jérémy Perret at 2y