Retrieval-Augmented Generation

also referred to as: rag · retrieval augmented generation

15 statements across 9 episodes · 10 bullish · 1 bearish · 9 people on the record · first statement Oct 5, 2023 by Sarah Guo · across every show →

Everything said about Retrieval-Augmented Generation, oldest first

Oct 5, 2023 positive
Insight
Guo: Trustworthiness, Cost, and Freshness Drive Adoption of RAG Over Retraining
“I think of the core driver as like trustworthiness, right? Citation control of information source. And so now you have this architecture where people are using think of it as like traditional information retrieval techniques and search in combination with thes…”
Sarah Guo Oct 5, 2023 ▶ 7:54 No Priors Ep. 35 | With Sarah Guo and Elad Gil
Jan 18, 2024 bullish
Insight
Beyang Liu: RAG remains necessary for context even with fine-tuned models
“I think you're still going to want to do RAG anyways. Like, even if you have fine tuned models in the mix, RAG is still sort of this, like, last mile data or context.”
Beyang Liu Jan 18, 2024 ▶ 32:35 No Priors Ep. 47 | With Sourcegraph CTO Beyang Liu
Jan 18, 2024 positive
Insight
Beyang Liu: Keyword Search Solves Over 90% of RAG Retrieval
“I think if you talk to a lot of RAG practitioners you'll find that the kind of, like, dirty secret is that keyword search can probably get you more than 90% of the way there.”
Beyang Liu Jan 18, 2024 ▶ 11:58 No Priors Ep. 47 | With Sourcegraph CTO Beyang Liu
Feb 15, 2024 bullish
Insight
Zhao: Embeddings and RAG are eliminating the need for manual organization
“I think organization might be, we might be moving away from the organizational world. Why do you need to organize because you can retrieve? Why do you have index? Like index initially are file cabinets and little index are sitting on top of so you can find thi…”
Ivan Zhao Feb 15, 2024 ▶ 23:13 No Priors Ep. 51 | With Notion CEO Ivan Zhao
Feb 15, 2024 bullish
Opinion
Gil: RAG and Embeddings Are Under-Appreciated Relative to Impact
“I feel like RAG and embeddings are very under-discussed, or under-appreciated in some sense, relative to the impact that they really seem to be having, or starting to have, and I think Notion Q&A is a great example of that.”
Elad Gil Feb 15, 2024 ▶ 19:52 No Priors Ep. 51 | With Notion CEO Ivan Zhao
Feb 22, 2024 bullish
Assertion Partly supported
Liberty: RAG Over Internet Data Reduces LLM Hallucinations by 50%
“And you could see that if you augment all of them with RAG on, even on the internet, which is data that they were trained on, you can reduce hallucinations significantly up to 50% sometimes.”
Edo Liberty Feb 22, 2024 ▶ 5:17 No Priors Ep. 52 | With Pinecone CEO Edo Liberty
Feb 22, 2024 neutral
Insight
Liberty: RAG Levels the Playing Field Across Different Foundation Models
“Interestingly enough, many of them actually start behaving quite similarly in terms of level of accuracy, even though without RAG, they actually have quite different behaviors. So it's sort of both like a uniform improvement and a little bit of leveling the pl…”
Edo Liberty Feb 22, 2024 ▶ 5:27 No Priors Ep. 52 | With Pinecone CEO Edo Liberty
Mar 7, 2024 bullish
Opinion
Guo: Large context windows expand RAG trade-offs rather than killing retrieval
“I'm more of the belief that it just opens up the set of trade-offs you can make between retrieval, more sophisticated retrieval and model reasoning by having a larger context window versus saying, like, we don't need any ability to work with a specific data se…”
Sarah Guo Mar 7, 2024 ▶ 3:21 No Priors Ep. 54 | With Sarah Guo & Elad Gil
Mar 28, 2024 neutral
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
Jun 6, 2024 positive
Prediction Not checkable as stated
Ma: RAG Software Heuristics Will Vanish as Embedding Models Improve
“And my long term vision here is that some of the software engineering layers on top of the networks will be less and less needed when the networks are more and more clever.”
Tengyu Ma Jun 6, 2024 ▶ 22:20 No Priors Ep. 67 | With Voyage AI Co-Founder and CEO
Jun 6, 2024
Insight
Ma: RAG Response Quality Is Bottlenecked by Retrieval Quality
“Right now for implementing Rack the bottleneck seems to be that, you know, it's not very hard to implement it, right? You can just connect the components and have your Rack system ready very quickly. But the bottleneck seems to be the quality. Of the response …”
Tengyu Ma Jun 6, 2024 ▶ 7:03 No Priors Ep. 67 | With Voyage AI Co-Founder and CEO
Jun 6, 2024 positive
Prediction Not checkable as stated
Ma: Multimodal Embeddings Will Eliminate Image-to-Text Preprocessing
“So maybe in the future, you don't have to turn your images into description of images and then give it to the text embedding model. That's what people are doing right now. Like everything is turned into text and then use a text embedding model. But when the em…”
Tengyu Ma Jun 6, 2024 ▶ 23:02 No Priors Ep. 67 | With Voyage AI Co-Founder and CEO
Sep 19, 2024 negative
Insight
Taylor: RAG is woefully insufficient for meaningful enterprise customer service
“What we found in practice is that broad category of technology investment is woefully insufficient for almost any meaningful customer experience. If you think about, you know, all of the interactions you've had with brands that you care about, what percentage …”
Bret Taylor Sep 19, 2024 ▶ 10:50 No Priors Ep. 82 | With CEO of Sierra Bret Taylor
Oct 8, 2024 positive
Assertion Not checkable as stated
Goyal: 50% of enterprise AI production use cases involve RAG
“Unambiguously, people are doing rag. So that one is, you know, it's like simple and obvious. Probably around 50% of the use cases that we see in production involve rag of some sort.”
Ankur Goyal Oct 8, 2024 ▶ 6:17 No Priors Ep. 85 | CEO of Braintrust Ankur Goyal
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.