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