Jerry Liu

Everything Jerry Liu said on any show that made the record, most notable first. Each card names its show and opens the statement there.

LATENT SPACE Insight

Liu: RAG is fundamentally just an algorithmic prompt-stuffing hack

“RAG is basically just a hack, but it turns out it's a very good hack because what is RAG? RAG is you keep the model fixed, and you just figure out a good way to, like, stuff stuff into the prompt of the language model. Everything that we're doing nowadays in t…”

Jerry Liu Oct 12, 2023 ▶ 24:45 RAG is a hack - with Jerry Liu of LlamaIndex

LATENT SPACE Insight

Liu: RAG will remain essential for managing LLM cost-performance trade-offs

“There's always going to be some curve regardless of like the performance of the best performing models of like cost versus performance. And so what RAG does is it does provide extra data points along that access because you kind of control the amount of contex…”

Jerry Liu Oct 12, 2023 ▶ 15:01 RAG is a hack - with Jerry Liu of LlamaIndex

LATENT SPACE Prediction Open · timeframe Oct 2028

Liu: Developers will eventually fine-tune new factual knowledge into LLMs

“That's one of those things where I think long-term, you definitely can. I think some people say you can't. I disagree. I think you definitely can. Just right now, I haven't gotten into work yet.”

Jerry Liu Oct 12, 2023 ▶ 29:53 RAG is a hack - with Jerry Liu of LlamaIndex

LATENT SPACE Insight

Liu: Improving vector store lookup algorithms offers low marginal gains

“I don't think the delta on, like, improving the vector store, like, embedding lookup algorithm is that high. I think this stuff has been mostly solved or at least there's just a lot of other stuff you can do to try to improve the overall performance.”

Jerry Liu Oct 12, 2023 ▶ 1:01:34 RAG is a hack - with Jerry Liu of LlamaIndex

LATENT SPACE Prediction Not checkable as stated

Liu: The final state for personalized AI memory will not be RAG

“I think a lot of people have thoughts about that, but, like, for what it's worth, I don't think the final state will be ragged. I think it will be some, like, fancy algorithm or architecture where you, like, bake it into, like, the architecture of the model it…”

Jerry Liu Oct 12, 2023 ▶ 1:10:29 RAG is a hack - with Jerry Liu of LlamaIndex

LATENT SPACE Insight

Liu: Avoid pre-GPT-4 models for tasks requiring complex reasoning

“Like, I'm one of the first to say, like, you know, you shouldn't use anything pre-GPT-IV for anything that requires, like, complex reasoning because it's just going to gonna be unreliable. Okay, disregarding stuff like fine-tuning.”

Jerry Liu Oct 12, 2023 ▶ 9:28 RAG is a hack - with Jerry Liu of LlamaIndex

LATENT SPACE Opinion

Liu: Security and access control are not P0 for enterprise apps

“I think users have asked for it, but I don't think that's like a P zero. Like, I think the P zero is more on, like, can we get this thing working before we expand this to, like, more users within the org.”

Jerry Liu Oct 12, 2023 ▶ 34:32 RAG is a hack - with Jerry Liu of LlamaIndex

LATENT SPACE Prediction Not checkable as stated

Liu: Fine-tuned LLMs will become the primary scalable evaluation solution

“No, but these models will get better and you'll probably fine tune a model to be a better judge. I think that's probably what's going to happen. So I'm like reasonably bullish on this because I don't think there's really a good alternative beyond you just huma…”

Jerry Liu Oct 12, 2023 ▶ 1:06:00 RAG is a hack - with Jerry Liu of LlamaIndex

LATENT SPACE Insight

Liu: Chain-of-thought query decomposition produces superior retrieval results

“Another example here is actually LLM based reasoning, like LLM based chain of thought reasoning. You can take a question, break it down into smaller components and use that to actually send to your retrieval system. And that gives you better results since kind…”

Jerry Liu Oct 12, 2023 ▶ 47:53 RAG is a hack - with Jerry Liu of LlamaIndex

LATENT SPACE Disclosure

Liu: LlamaIndex is de-emphasizing direct revenue generation in 2023

“I think where our revenue focus this year is kind of is less emphasized. Like, it's more just about, like, can we build some managed offering that, like, provides complimentary value to what the open source library provides.”

Jerry Liu Oct 12, 2023 ▶ 53:23 RAG is a hack - with Jerry Liu of LlamaIndex

LATENT SPACE Insight

Liu: Developers should build RAG from scratch before using framework abstractions

“Building, like, RAG from scratch. I mean, I think everybody should do it, I think. Like, I would check out the guide if you guys haven't already, and I think it's in our docs, but instead of just using you know, either the kind of, like the retriever query eng…”

Jerry Liu Oct 12, 2023 ▶ 1:12:32 RAG is a hack - with Jerry Liu of LlamaIndex

MAD Disclosure

LlamaIndex is not building a vector database, integrates with 12-20 existing ones

“We're not building our own vector database, but we have a rich set of integrations with, you know like 12 to like 20 different vector databases out there these days.”

Jerry Liu Jul 12, 2023 ▶ 9:20 Building LlamaIndex: Jerry Liu on Scaling Retrieval-Augmented AI

MAD Disclosure

LlamaIndex focuses on data infrastructure while LangChain builds broader application frameworks

“Blind train is a great application framework for you to just like get us out of building blocks for a lot of different components, for instance, from like LL modules to prompts to some basic like retrieval and vector database abstractions to like also agent fr…”

Jerry Liu Jul 12, 2023 ▶ 12:23 Building LlamaIndex: Jerry Liu on Scaling Retrieval-Augmented AI

MAD Insight

Liu: LLM data pipelines differ from traditional ETL stacks due to unstructured content comprehension

“If we're building this new age of L-empowered applications, The kind of requirements for the type of data that like you want to load as well as how you want to extract information from that data will be a little bit different than the existing ETL stack. The r…”

Jerry Liu Jul 12, 2023 ▶ 18:57 Building LlamaIndex: Jerry Liu on Scaling Retrieval-Augmented AI

MAD Assertion Contradicted

Liu: Uber and Instabase use LlamaIndex for enterprise data applications

“We've seen people build these workflows at different settings from, for instance, like hacks on projects at startups building, for instance, like track GPT, like, plugin over, like, your Slack or your Notion all the way to kind of, like, bigger companies, for …”

Jerry Liu Jul 12, 2023 ▶ 26:58 Building LlamaIndex: Jerry Liu on Scaling Retrieval-Augmented AI

MAD Insight

Liu: Generating long-form content over custom data remains a hard problem

“Generating something that's like a paragraph is pretty easy for ChatGPT to do. Generating like an entire blog post or essay, especially over your data is a pretty challenging problem.”

Jerry Liu Jul 12, 2023 ▶ 28:37 Building LlamaIndex: Jerry Liu on Scaling Retrieval-Augmented AI

LATENT SPACE Disclosure

Liu: LlamaIndex closed its Greylock seed round in under a week

“What we really wanted to do was because for us, like, time was of the essence, like, we wanted to ship very quickly and still kind of build mindshare in this space, we just kept the fundraising process very efficient. I think we basically did it in, like, a we…”

Jerry Liu Oct 12, 2023 ▶ 16:12 RAG is a hack - with Jerry Liu of LlamaIndex

LATENT SPACE Assertion Not checkable as stated

Liu: 90% of users ask how to improve LLM app performance

“Honestly, 90% of users I talk to have questions about how to improve the performance of their app.”

Jerry Liu Oct 12, 2023 ▶ 37:08 RAG is a hack - with Jerry Liu of LlamaIndex

MAD Insight

Jerry Liu: Injecting metadata into text chunks improves LLM retrieval performance

“Second is being able to inject metadata actually is quite important to actually improve retrieval performance of like the downstream application, because like, you know, let's say you're splitting up like a sec, 10 K filing into a bunch of chunks within a sing…”

Jerry Liu Jul 12, 2023 ▶ 8:23 Building LlamaIndex: Jerry Liu on Scaling Retrieval-Augmented AI

MAD Assertion Supported

Liu: LlamaHub features over 100 community-contributed data loaders

“And so these days, like Lama Hub is a very rich repository of, like, you know, the hundred plus, like, different data loaders from all different services and formats, and it's growing, like, every day.”

Jerry Liu Jul 12, 2023 ▶ 15:39 Building LlamaIndex: Jerry Liu on Scaling Retrieval-Augmented AI

MAD Assertion Supported

Liu: LlamaIndex enables data querying in three or four lines of code

“Because in about three or four lines of code, you can load data and just it index it and then query it.”

Jerry Liu Jul 12, 2023 ▶ 21:17 Building LlamaIndex: Jerry Liu on Scaling Retrieval-Augmented AI

MAD Disclosure

LlamaIndex adopted Keras's design philosophy of progressive disclosure of complexity

“A key philosophy that we launched and like zero dot six auto that we're continuing to build towards is this idea that was inspired by Karis, which is this idea of like progressive disclosure of complexity, where in the beginning things are very high level and …”

Jerry Liu Jul 12, 2023 ▶ 24:38 Building LlamaIndex: Jerry Liu on Scaling Retrieval-Augmented AI

MAD Assertion Supported

Liu: OpenBB integrated LlamaIndex as its natural language layer

“OpenBB, which is the open source, like financial analysis tool, and they recently incorporated Lama Index as a natural language layer to help power, like their, basically, open source Bloomberg vibe, right?”

Jerry Liu Jul 12, 2023 ▶ 27:48 Building LlamaIndex: Jerry Liu on Scaling Retrieval-Augmented AI

MAD Disclosure

Jerry Liu: LlamaIndex is building a production-grade enterprise version

“So we're Actually building out and scoping out initial version of what, like kind of production grade Lama index would look like.”

Jerry Liu Jul 12, 2023 ▶ 29:38 Building LlamaIndex: Jerry Liu on Scaling Retrieval-Augmented AI

Show 3statements(3 left)

The other half of the tape: Jerry Liu's own voice is left out of every number here. Other people bring the name up 5 times in 4 episodes across the shows. every mention, with the transcript →

Who brings them up most Matt Turck 2Jason Liu 1

Every mention by year

One line per show, most statements first. The link opens Jerry's full record on that show: the calibration, argument clarity, speaking style and every statement made there.

Show	Role there	Eps	Statements	Record
MADLEDGER	Co-founder & CEO, LlamaIndex	1	14	75% 3/4	full record on the MAD Podcast →
LATENT SPACELEDGER	Co-founder & CEO, LlamaIndex	1	13	—	full record on Latent Space →