Building projects with language models
summary
Overview of what large language models are and what they can do, practical challenges to keep in mind when building projects with them (limitations and pitfalls), and libraries that can help integrate and work with these models.
AI-written summary · about
chapters (19)
- 0:00Welcome
- 3:51Speaker intro
- 4:12Why use language models
- 5:40Choosing first model
- 8:10Prompt engineering
- 12:02Prompt management tools
- 12:45Model quality evaluation
- 17:21Reliability and stability
- 19:49RAG architecture
- 21:14Data logging
- 23:03Error handling
- 24:50Privacy and security
- 26:34Performance monitoring
- 28:24User limits
- 29:28Caching optimization
- 31:59Project cost
- 33:02Feedback and fine-tuning
- 34:26Fine-tuning models
- 35:29Q&A
related talks
50mGenerative language models
30mLarge Language Models and Prompt Engineering for Developers
36mLarge Language Models for Real-World Applications - A Gentle Intro
51mTowards a Pragmatic Understanding of Large Language Models
49mA Practical Approach to Using LLMs: Peculiarities and Pitfalls
15mFuture with Large Language Models
47mCurrent Security Threats in Large Language Model Applications
56mLarge Language Models for Python Specialists