"Make Agent 10x cheaper, faster & better?" - LLM System Evaluation 101

Опубликовано: 01 Октябрь 2024
на канале: AI Jason

18,229

644

LLM System Eval 101 - Build better agents

Get free HubSpot report of how to land a Job using AI: https://clickhubspot.com/fo2

🔗 Links
- Join my community: https://www.skool.com/ai-builder-club...
- Follow me on twitter:   / jasonzhou1993
- Join my AI email list: https://www.ai-jason.com/
- My discord:   / discord
- Langsmith: https://smith.langchain.com/
- Phoenix: https://phoenix.arize.com/
- Arize LLM Evaluation guide: https://arize.com/blog-course/llm-eva...
- Web scraping agent video:    • “Wait, this Agent can Scrape ANYTHING...
- Signup for universal web scraper: https://forms.gle/zN9w9UyhMKx59yAE6

⏱️ Timestamps
0:00 Intro
0:27 Why Eval is important
3:30 LLM as evaluator
5:54 How to build eval system
15:10 Case study - Eval & improve research agent

👋🏻 About Me
My name is Jason Zhou, a product designer who shares interesting AI experiments & products. Email me if you need help building AI apps! [email protected]

#gpt4o #aiagents #rag #llamaparse #llamaindex #gpt5 #autogen #gpt4 #autogpt #ai #artificialintelligence #tutorial #stepbystep #openai #llm #chatgpt #largelanguagemodels #largelanguagemodel #bestaiagent #chatgpt #agentgpt #agent #babyagi #evaluation