Harrison Chase - Agents Masterclass from LangChain Founder (LLM Bootcamp)

New course announcement ✨ We're teaching an in-person LLM bootcamp in the SF Bay Area on November 14, 2023. Come join us if you want to see the most up-to-date materials building LLM-powered products and learn in a hands-on environment. https://www.scale.bythebay.io/llm-workshop Hope to see some of you there! --------------------------------------------------------------------------------------------- In this video, Harrison Chase, co-creator of LangChain, discusses "agents": tool-using language models with long-term memory. Download the slides and read the talk summary here: https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/chase-agents Watch the rest of the LLM Bootcamp videos here: https://www.youtube.com/playlist?list=PL1T8fO7ArWleyIqOy37OVXsP4hFXymdOZ Outro music made with Riffusion: https://github.com/riffusion/riffusion 00:00 What are "agents"? 01:18 Why use agents? 04:12 ReAct: Reasoning to Act 07:50 Challenge: controlling tool use 11:07 Challenge: parsing tool invocations 12:54 Challenge: long-term memory and coherence 16:08 Challenge: evaluation 17:39 Agent memory and adaptability 19:29 Example: AutoGPT 20:22 Example: BabyAGI 21:08 Example: CAMEL 22:19 Example: "Generative Agents" paper