Ep 28: LangChain CEO Harrison Chase on the Current State of Eval and Agents and The LLM Apps that Will Define 2024

Unsupervised Learning

Last week LangChain announced a $20M Series A led by Sequoia and released the paid version of LangSmith, which has already been used by 1K+ teams and driven 80K signups. On this week’s episode of Unsupervised Learning, we sat down with LangChain Co-Founder and CEO Harrison Chase to talk about the current state of LLM evaluation, observability, and the agent landscape.

(0:00) intro

(1:07) applications of AI in the sports world

(3:26) what does LangChain do?

(7:51) building with LangSmith

(10:00) best AI eval practices

(16:51) to what extent is eval generalizable?

(21:11) the current agent landscape

(29:35) balancing present and future at LangChain

(36:27) using LangServe to deploy LangChain applications

(41:37) more complex chatbots are coming

(45:51) current AI practices that will become obsolete

(48:55) over-hyped/under-hyped

(49:25) bigger surprise in building LangChain

(51:50) how ubiquitous will open-source models be in the future?

(52:43) most exciting AI startups

(56:07) being an AI “celebrity”

(58:09) Jacob and Jordan debrief

With your co-hosts:

@jacobeffron

- Partner at Redpoint, Former PM Flatiron Health

@patrickachase

- Partner at Redpoint, Former ML Engineer LinkedIn

@ericabrescia

- Former COO Github, Founder Bitnami (acq’d by VMWare)

@jordan_segall

- Partner at Redpoint