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.

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.

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

[newcooldiscoveries]

Excellent!! Bring Harrison back for a two hour talk please.

[richardglady]

Wonderful and informative lecture. Great introduction to agents and understandable to a non-expert (me). Thank you for making and posting this video.

[oldmankatan]

You referenced several papers during the talk, but I didn't see any citations in the description. Please consider including these (at least the most important papers) in the future. It's really helpful for a lot of us! Great talk, thank you!

[answerai]

Excellent summary from Harrison. Thanks for upload!

[snehotoshbanerjee]

Awesome talk!!. This is exactly I was looking for.

[ReddSpark]

Would have liked to have seen the Q&A session to this