OpenAI Blog · Oct 22, 2018
Learning complex goals with iterated amplification
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Learning complex goals with iterated amplification. We’re proposing an AI safety technique called iterated amplification that lets us specify complicated behaviors and goals that are beyond human scale, by demonstrating how to decompose a task into simpler sub-tasks, rather than by providing labeled data or a reward function. Although this idea is in its very early stages and we have only completed experiments on simple toy algorithmic domains, we’ve decided to present it in its preliminary state because we think it could prove to be a scalable… This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Learning complex goals with iterated amplification' affects your current setup before relying on it in production.
ai phone