Interpretable machine learning through teaching
OpenAI developed a method for AIs to teach each other using human-interpretable examples, automatically selecting the most informative samples to convey concepts.
Excerpt
We’ve designed a method that encourages AIs to teach each other with examples that also make sense to humans. Our approach automatically selects the most informative examples to teach a concept—for instance, the best images to describe the concept of dogs—and experimentally we found our approach to be effective at teaching both AIs
Read at source: https://openai.com/index/interpretable-machine-learning-through-teaching