Insight certainty 4/5 debate potential 2/5

Chase: AI agents fundamentally require cyclical graphs, not linear architectures

Harrison Chase · No Priors Ep. 57 | With LangChain CEO and Co-Founder Harrison Chase · Mar 28, 2024 · at 3:21

Harrison Chase, CEO of LangChain, discusses why LangGraph was built to support cyclic execution rather than traditional DAG pipelines.

0:00 / 0:05exact quote · 6.0s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“So, you know, all these agents are basically running an LLM in a loop. You need cycles and so lane graph helps with that.”

quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →

More from Harrison Chase

Opinion
Chase: Open-source models still lag behind Claude 3 and GPT-4
“Like there's, I think we see increasingly interest in open source, but the reasoning abilities are still just like lagging behind Cloud three or GPT four. And I think like for a lot of the applications that it kind of, it probably depends on the types of appli…”
Harrison Chase Mar 28, 2024 ▶ 22:06 No Priors Ep. 57 | With LangChain CEO and Co-Founder Harrison Chase
Prediction Not checkable as stated
Chase: Long context windows will not replace chaining and AI agents
“There are also things where it requires iterations. You need to like decide what to do, interact with the environment, get that back. So this whole idea of chaining and agents, I don't like, That's less around context windows and more around interacting with t…”
Harrison Chase Mar 28, 2024 ▶ 18:07 No Priors Ep. 57 | With LangChain CEO and Co-Founder Harrison Chase
Insight
Chase: Needle-in-a-haystack benchmarks fail to represent real RAG reasoning
“That, that actually really doesn't reflect a lot of RAG use cases in, in my opinion, because like that's the needle in the haystack is like, okay, given this long context, can I find a single information point? But oftentimes RAG is about seeing multiple infor…”
Harrison Chase Mar 28, 2024 ▶ 18:44 No Priors Ep. 57 | With LangChain CEO and Co-Founder Harrison Chase
Opinion
Chase: AI agent memory is extremely nascent and lacks interesting developments
“I feel it's like a field that's just, like, super, super nascent. Like, I don't, I actually am underwhelmed at the amount of, like, really interesting stuff that's going on there.”
Harrison Chase Mar 28, 2024 ▶ 9:44 No Priors Ep. 57 | With LangChain CEO and Co-Founder Harrison Chase
Insight
Chase: Successful production AI agents operate as controlled state machines
“And I think the things that we see making it into production and informed a lot of the development of laying graph is, or is something in the middle where it's like this controlled state machine type thing.”
Harrison Chase Mar 28, 2024 ▶ 12:01 No Priors Ep. 57 | With LangChain CEO and Co-Founder Harrison Chase
Assertion Not checkable as stated
Chase: Developers only implement model fine-tuning after reaching critical scale
“We see people experimenting with it. I think the only real place where they're doing it is when they've reached like really critical scale which I still don't think is that many applications to date.”
Harrison Chase Mar 28, 2024 ▶ 20:24 No Priors Ep. 57 | With LangChain CEO and Co-Founder Harrison Chase
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 100 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.