Shaping AI Benchmarks and Open-Source Development - Percy Liang Interview

Shaping AI Benchmarks and Open-Source Development - Percy Liang Interview

Weights & Biases via YouTube Direct link

Introduction

1 of 13

1 of 13

Introduction

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Shaping AI Benchmarks and Open-Source Development - Percy Liang Interview

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Introduction
  2. 2 Discussion on benchmarking incentives with references to Kaggle.
  3. 3 Nuanced challenges of language model overfitting.
  4. 4 How to effectively choose AI models using leaderboards.
  5. 5 Advice on selecting models for company use.
  6. 6 Importance of having a robust model evaluation framework.
  7. 7 How individuals can contribute to AI benchmarking.
  8. 8 Discussion on specialized vs. generalized model performance.
  9. 9 Insights into the complexities of benchmarking AI agents.
  10. 10 Real-world applications and limitations of AI agents.
  11. 11 Percy reflects on his TED talk regarding open vs. closed source models.
  12. 12 Introduction to TogetherAI and its mission for open AI development.
  13. 13 Combining AI with music creation.

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.