Retrieval-Augmented Generation

also referred to as: rag · retrieval augmented generation

17 statements across 15 episodes · 7 bullish · 4 bearish · 15 people on the record · first statement May 31, 2023 by Edo Liberty · across every show →

Everything said about Retrieval-Augmented Generation, oldest first

May 31, 2023 positive

Insight

Liberty: Even naive RAG implementation significantly reduces AI hallucinations

“Like, you can play with it in a million different ways, but even if you do it relatively naively, that already gives you a huge bump in, in inaccuracy or reduction in hallucination, depending on how you want to measure it.”

Edo Liberty May 31, 2023 ▶ 21:21 Long Term Memory for AI with Pinecone Founder & CEO, Edo Liberty

Jul 12, 2023 positive

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

Sep 6, 2023

Insight

RAG systems need dedicated hallucination detectors to verify LLM outputs

“If you want to make sure that there's not a, that the model doesn't hallucinate, you probably want a hallucination detector on top, right? Something that classifies an answer and confirms, is this answer really part of my database?”

Milos Rusic Sep 6, 2023 ▶ 12:35 From NLP Start-Up to Generative-AI Platform: Milos Rusic (deepset) Unpacks Product-Market Fit

Sep 27, 2023 bullish

Opinion

RAG is the definitive way to build generative AI today

“Rag is the way to build you know, these models today”

Shreya Rajpal Sep 27, 2023 ▶ 46:33 Guardrails AI: The Playbook for Safer, Hallucination-Free LLMs — Shreya Rajpal Explains

Dec 21, 2023 positive

Disclosure

Moody's Research Assistant Uses GPT-4 Alongside Custom RAG System

“We use ChatGPT-IV as the LLM, although we've tried a lot of, we talked about in our prep, we have tried different, ah, large language models, and we've also developed our own RAG.”

Cristina Pieretti Dec 21, 2023 ▶ 8:14 How Moody’s Analytics Is Using AI to Transform Credit Risk | Cristina Pieretti & Yimei Fan

Feb 15, 2024 negative

Insight

Van Luijt: Current industry RAG implementations are primitive

“The way we, and I, with we, I mean like everybody in this room working on this stuff, are doing RAC right now, is actually pretty primitive, right?”

Bob van Luijt Feb 15, 2024 ▶ 3:27 Vector databases and the $8 trillion open source market | Bob van Luijt, CEO of Weaviate

Feb 15, 2024

Assertion Not checkable as stated

Van Luijt: RAG was the first unique vector database use case

“And reg was the first unique use case, if you will, that emerged around the ecosystem of vector databases.”

Bob van Luijt Feb 15, 2024 ▶ 2:05 Vector databases and the $8 trillion open source market | Bob van Luijt, CEO of Weaviate

Feb 15, 2024 positive

Insight

Van Luijt: RAG carries less hallucination risk than model fine-tuning

“That is something that is, works better than fine-tuning, for example, because if you fine-tune, then you're still dealing with potential hallucination Fair enough, with RAC that's possible too, but it's like, it's less it's less risky.”

Bob van Luijt Feb 15, 2024 ▶ 3:09 Vector databases and the $8 trillion open source market | Bob van Luijt, CEO of Weaviate

Feb 29, 2024

Disclosure

Traynor: Intercom uses RAG rather than per-customer model fine-tuning

“We're not yet building models per customer or tuning models per customer. We're doing rag.”

Des Traynor Feb 29, 2024 ▶ 30:55 How Intercom transitioned to being AI-first | Des Traynor, Co-Founder of Intercom

Jul 25, 2024 negative

Insight

RAG and prompt engineering are just search techniques, not real AI

“Today when people are running RAG or prompt engineering those are search. That's not AI. It's like keeping the AI frozen and fixed.”

Sharon Zhou Jul 25, 2024 ▶ 41:05 Making AI Work: Fine-Tuning, Inference, Memory | Sharon Zhou, CEO, Lamini

Dec 12, 2024 neutral

Insight

Douetteau: RAG tools and AI agent builders are becoming commoditized

“Ultimately lots of those technology can become, in isolation, pretty much commoditized. Meaning it's not hard to build RAG or agent builder.”

Florian Douetteau Dec 12, 2024 ▶ 27:14 Dataiku's Secret to Scaling AI in Global Enterprises | Florian Douetteau, CEO, Dataiku

Mar 6, 2025

Assertion Contradicted

Kiela: FAIR was the first team to build a generative RAG model

“Why RAG became the way you name these things is because it's generative, right? So we were the first ones to have a generative model there.”

Douwe Kiela Mar 6, 2025 ▶ 18:38 Top AI Researcher on GPT 4.5, DeepSeek and Agentic RAG | Douwe Kiela, CEO, Contextual AI

Apr 24, 2025 positive

Insight

Arvind Jain: AI agents are shifting from RAG to process automation

“Agents are now getting a lot more powerful. They are, You know, they're getting they're sort of shifting from sort of basic two step rack kind of application flow where you take a task, you find some information, and then you make AI work on it to generate the…”

Arvind Jain Apr 24, 2025 ▶ 30:19 Glean’s Breakthrough: CEO Arvind Jain on Scaling AI Agents & Search

May 29, 2025 positive

Assertion Contradicted

Hebbia was the first company to productionize RAG in 2020

“Hebbia were actually the first to turn that into a product. So it's like a very close thing to my heart. So back in 2020, we were the first people to actually productionize it, roll it out.”

George Sivulka May 29, 2025 ▶ 29:06 AI That Ends Busy Work — Hebbia CEO on “Agent Employees”

Jul 17, 2025 negative

Opinion

Laskin: Traditional RAG agents fail for any meaningful software engineering query

“It'll grab it, and then that's all you have, and most likely, for any meaningful query it will not have given you the information that you need to actually go do the task. So rag agents are actually, are pretty weak.”

Misha Laskin Jul 17, 2025 ▶ 12:57 Ex‑DeepMind Researcher Misha Laskin on Enterprise Super‑Intelligence | Reflection AI

Aug 7, 2025 negative

Assertion Supported

Cherny: Claude Code does not use RAG for codebase memory

“And so quad code actually doesn't use this technique called rag. Instead, what it does is it just searches files the same way that a human would.”

Boris Cherny Aug 7, 2025 ▶ 30:34 Anthropic's Surprise Hit: How Claude Code Became an AI Coding Powerhouse

Apr 2, 2026 neutral

Prediction Not checkable as stated

RAG will shift from universal use to handling long-tail distribution cases

“Maybe it changes in a way that, you know, like it doesn't need to trigger RAG for like everything, but I'm pretty sure that they're going to be some tail of the distribution that we're going to do RAG still for it.”

Mostafa Dehghani Apr 2, 2026 ▶ 58:09 AI is Already Building AI — Google DeepMind’s Mostafa Dehghani

Retrieval-Augmented Generation

Everything said about Retrieval-Augmented Generation, oldest first

Turn any episode into a week of clips.