k.Work
WorkOpenAI Blog
KeyRank 62Learning complex goals with iterated amplification
OpenAI is publishing early-stage research on a scalable AI safety approach that decomposes complex tasks into human-verifiable sub-tasks, addressing a fundamental challenge in building aligned AI systems at scale.
Why it ranks · · Technique: Iterated amplification for task decomposition · Oct 22 – 28, 2018
Read full story