Harrison Chase - Agents (LLM Bootcamp)

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 …

act agents bootcamp challenge evaluation langchain language language models llm long-term memory parsing react reasoning tool video