Retrieval-Augmented Generation

also referred to as: rag · retrieval augmented generation

9 statements across 5 episodes · 3 bullish · 2 bearish · 5 people on the record · first statement Jun 30, 2023 by Douwe Kiela · across every show →

Everything said about Retrieval-Augmented Generation, oldest first

Jun 30, 2023
Assertion Supported
Douwe Kiela: I co-created Retrieval-Augmented Generation (RAG) at Facebook AI
“We're specifically basing it on this retrieval augmented generation, which is something that me and my colleagues at fair came up with in.”
Douwe Kiela Jun 30, 2023 ▶ 9:12 Douwe Kiela: Why Data Size Matters More Than Model Size; Why Open Source Isn't Going to Win | E1032 · 20VC with Harry Stebbings
Jun 30, 2023 positive
Insight
Douwe Kiela: Decoupling LLM memory reduces hallucinations and enables data deletion
“You decouple the memory from the generative capacity of the large language model, and this allows you to ground the generations from the language model into things you retrieved. In your memory, essentially. So you get much less hallucination. You get attribut…”
Douwe Kiela Jun 30, 2023 ▶ 9:21 Douwe Kiela: Why Data Size Matters More Than Model Size; Why Open Source Isn't Going to Win | E1032 · 20VC with Harry Stebbings
Sep 4, 2024 bullish
Prediction Not checkable as stated
Kolter: RAG systems will remain essential despite fine-tuning advances
“RAG based systems are so Are so common here, and so, and probably will remain, even with the advent of fine-tuning availability, they're going to remain a useful paradigm.”
Zico Kolter Sep 4, 2024 ▶ 24:33 Zico Kolter: OpenAI's Newest Board Member on The Biggest Questions and Concerns in AI Safety | E1197 · 20VC with Harry Stebbings
Jan 22, 2025 bearish
Opinion
Sivulka: Retrieval Augmented Generation (RAG) does not work at all
“That's a bit of a plot twist over here. We, I actually don't think RAG works at all.”
George Sivulka Jan 22, 2025 ▶ 21:26 George Sivulka, Co-Founder & CEO @Hebbia: The Future of Foundation Models | E1250 · 20VC with Harry Stebbings
Jan 22, 2025
Assertion Contradicted
Sivulka: Hebbia was first to productionize RAG in 2020
“We end up building a product studio, which is the first to productionize RAG, Retrieval Augmented Generation, also in 2020.”
George Sivulka Jan 22, 2025 ▶ 20:24 George Sivulka, Co-Founder & CEO @Hebbia: The Future of Foundation Models | E1250 · 20VC with Harry Stebbings
Feb 24, 2025
Insight
Morin: AI developers will always choose smaller models if performance matches
“What really pushes model sizes are the efficiency rather than specializing. So meaning that if you can do the same performance with a smaller model that is fine tuned with rag or whatever, then you'll do it with a smaller because again, less is better.”
Steeve Morin Feb 24, 2025 ▶ 1:06:21 Steeve Morin: Why Google Will Win the AI Arms Race & OpenAI Will Not | E1262 · 20VC with Harry Stebbings
Feb 24, 2025 negative
Opinion
Morin: RAG is a dirty workaround limited by context size
“It's a bit dirty because, of course, you know, you are limited by the amount of data you can input, right?”
Steeve Morin Feb 24, 2025 ▶ 1:04:51 Steeve Morin: Why Google Will Win the AI Arms Race & OpenAI Will Not | E1262 · 20VC with Harry Stebbings
Jul 11, 2026 positive
Assertion Contradicted
Jain: Glean was the first enterprise AI company to deploy RAG
“We actually get a lot of credit for being the first enterprise AI company in the world. The first ones to actually bring RAG into the enterprise. The first ones to build conceptual semantic search.”
Arvind Jain Jul 11, 2026 ▶ 10:45 ⁠Why OpenAI and Anthropic Won't Win the App Layer | Glean Founder · 20VC with Harry Stebbings
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 1,200 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.