Learning complex goals with iterated amplification

1. 1Decompose complex tasks into simpler sub-tasks
2. 2Demonstrate how to achieve each sub-task
3. 3Use iterated amplification to combine sub-tasks and achieve the overall goal
4. 4Experiment and refine the technique on simple domains before applying to more complex tasks

AI researchers and engineers on a team can benefit from this technique to develop more scalable and safe AI models, and product managers can use it to define complex behaviors for AI systems

💡 Iterated amplification allows for specifying complex behaviors and goals without relying on labeled data or reward functions

💡 Iterated amplification: a new AI safety technique to achieve complex goals by breaking down tasks into simpler sub-tasks