Having AI systems try to outwit one another could help judge their intentions

Having AI systems try to outwit one another could help judge their intentions

  • May 6, 2018
Table of Contents

Having AI systems try to outwit one another could help judge their intentions

Take, for instance, an AI system designed to defend against human or AI hackers. To prevent the system from doing anything harmful or unethical, it may be necessary to challenge it to explain the logic for a particular action. That logic might be too complex for a person to comprehend, so the researchers suggest having another AI debate the wisdom of the action with the first system, using natural language, while the person observes.

Further details appear in a research paper.

Source: technologyreview.com

Tags :
Share :
comments powered by Disqus

Related Posts

Facebook Open Sources ELF OpenGo

Facebook Open Sources ELF OpenGo

Inspired by DeepMind’s work, we kicked off an effort earlier this year to reproduce their recent AlphaGoZero results using FAIR’s Extensible, Lightweight Framework (ELF) for reinforcement learning research. The goal was to create an open source implementation of a system that would teach itself how to play Go at the level of a professional human player or better. By releasing our code and models we hoped to inspire others to think about new applications and research directions for this technology.

Read More
Embodied Question Answering: A goal-driven approach to autonomous agents

Embodied Question Answering: A goal-driven approach to autonomous agents

Facebook AI Research (FAIR) has developed a collection of virtual environments for training and testing autonomous agents, as well as novel AI agents that learn to intelligently explore those environments. To test this goal-driven approach, FAIR are collaborating Georgia Tech on a multistep AI task called Embodied Question Answering, or EmbodiedQA.

Read More
Announcing PyTorch 1.0 for both research and production

Announcing PyTorch 1.0 for both research and production

PyTorch 1.0 takes the modular, production-oriented capabilities from Caffe2 and ONNX and combines them with PyTorch’s existing flexible, research-focused design to provide a fast, seamless path from research prototyping to production deployment for a broad range of AI projects. With PyTorch 1.0, AI developers can both experiment rapidly and optimize performance through a hybrid front end that seamlessly transitions between imperative and declarative execution modes. The technology in PyTorch 1.0 has already powered many Facebook products and services at scale, including performing 6 billion text translations per day.

Read More