Transforming Search with AI - Perplexity's Approach to Answer Engines

Transforming Search with AI - Perplexity's Approach to Answer Engines

Weights & Biases via YouTube Direct link

- The hardest parts of scaling up the application and maintaining focus on speed and accuracy

12 of 13

12 of 13

- The hardest parts of scaling up the application and maintaining focus on speed and accuracy

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Transforming Search with AI - Perplexity's Approach to Answer Engines

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

  1. 1 - Introduction
  2. 2 - Denis describes Perplexity as an answer engine.
  3. 3 - Discussion on using third-party APIs and in-house infrastructure.
  4. 4 - Choosing between In-house vs. outsourced models
  5. 5 - Evaluating the quality of results and using LLMs.
  6. 6 - Building a classical search engine and custom parsers.
  7. 7 - Latency and quality trade-offs in providing answers.
  8. 8 - Handling controversial domains and providing unbiased answers.
  9. 9 - Importance of hiring diverse annotators and their influence.
  10. 10 - Denis's story about pitching Yann LeCun.
  11. 11 - Early signs of success for Perplexity's gen AI application.
  12. 12 - The hardest parts of scaling up the application and maintaining focus on speed and accuracy
  13. 13 - Closing thoughts

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.