Harsha Nori
Director, Research Engineering
News & features
Steering at the Frontier: Extending the Power of Prompting
| Eric Horvitz, Harsha Nori, and Yin Tat Lee
We’re seeing exciting capabilities of frontier foundation models, including intriguing powers of abstraction, generalization, and composition across numerous areas of knowledge and expertise. Even seasoned AI researchers have been impressed with the ability to steer the models with straightforward, zero-shot prompts. Beyond…
Fairness and interpretability in AI: Putting people first
At the 2005 Conference on Neural Information Processing Systems, researcher Hanna Wallach found herself in a unique position—sharing a hotel room with another woman. Actually, three other women to be exact. In the previous years she had attended, that had…
Creating AI glass boxes – Open sourcing a library to enable intelligibility in machine learning
| Rich Caruana, Harsha Nori, Samuel Jenkins, Paul Koch, and Ester de Nicolas
When AI systems impact people’s lives, it is critically important that people understand their behavior. By understanding their behavior, data scientists can properly debug their models. If able to reason how models behave, designers can convey that information to end…