High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works

Public evidence record

Jerry Liu

Published podcast speaker

Claims
25
Episodes
1
Shows
1
Named items
0

Claim ledger

What Jerry said.

25 transcript-backed records

01 / belief

I actually, I think I was back then actually when I was working on Quora, I think the thing that everybody was fascinated in was just like general like deep learning advancements and stuff like GANs and generative like images and just like new architectures that were evolving.

“I actually, I think I was back then actually when I was working on Quora, I think the thing that everybody was fascinated in was just like general like deep learning advancements and stuff like GANs and generative like images and just like new architectures that were evolving.”
Speaker
Jerry Liu
Publisher
Latent Space

02 / belief

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 human annotating a bunch of data sets, um, and then trying to like just manually go through and curating, like evaluating eval metrics.

“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 human annotating a bunch of data sets, um, and then trying to like just manually go through and curating, like evaluating eval metrics.”
Speaker
Jerry Liu
Publisher
Latent Space

03 / belief

Like, I think I actually think that I don't think anyone's like, 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 right.

“Like, I think I actually think that I don't think anyone's like, 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 right.”
Speaker
Jerry Liu
Publisher
Latent Space

04 / belief

There's some structured annotations and there's some like unstructured texts. And so like, um, somehow combining all the expressivity of like SQL with like the flexibility of semantic search is something that I think is going to be really important.

“There's some structured annotations and there's some like unstructured texts. And so like, um, somehow combining all the expressivity of like SQL with like the flexibility of semantic search is something that I think is going to be really important.”
Speaker
Jerry Liu
Publisher
Latent Space

06 / belief

I think in the end, like this is a very fast moving space and we want to just like be one of the, you know, like dominant forces and helping to provide like production quality outline applications.

“I think in the end, like this is a very fast moving space and we want to just like be one of the, you know, like dominant forces and helping to provide like production quality outline applications.”
Speaker
Jerry Liu
Publisher
Latent Space

09 / belief

Um, and I think that will probably just expand the query sophistication of these vector stores and basically make it so that users don't have to think about whether they would just call this like hybrid querying.

“Um, and I think that will probably just expand the query sophistication of these vector stores and basically make it so that users don't have to think about whether they would just call this like hybrid querying.”
Speaker
Jerry Liu
Publisher
Latent Space

10 / belief

The second piece is like, take, there's like certain components in there that might not be directly related to the LLM app that would be nice to just like have people use, uh, an example is the PDF viewer, like the PDF viewer with like citations. I think we're just going to give that right.

“The second piece is like, take, there's like certain components in there that might not be directly related to the LLM app that would be nice to just like have people use, uh, an example is the PDF viewer, like the PDF viewer with like citations. I think we're just going to give that right.”
Speaker
Jerry Liu
Publisher
Latent Space

12 / belief

I think if there was a universal default, that would be amazing. But I think increasingly we found, you know, people are just defining their own like custom parsers for like PDFs, markdown files for like, you know, SEC filings versus like Slack conversations.

“I think if there was a universal default, that would be amazing. But I think increasingly we found, you know, people are just defining their own like custom parsers for like PDFs, markdown files for like, you know, SEC filings versus like Slack conversations.”
Speaker
Jerry Liu
Publisher
Latent Space

13 / belief

I know. But like, I just think, uh, from like the AGI, like, you know, just modeling like the human brain perspective, I think that there is something nice about just like being able to optimize that system.

“I know. But like, I just think, uh, from like the AGI, like, you know, just modeling like the human brain perspective, I think that there is something nice about just like being able to optimize that system.”
Speaker
Jerry Liu
Publisher
Latent Space

16 / belief

I was like, oh, I'll play around with LLMs a bit and then hacked around on stuff. And I think I've told the story a few times, but you know, I was like trying to feed in information into GPT-3.

“I was like, oh, I'll play around with LLMs a bit and then hacked around on stuff. And I think I've told the story a few times, but you know, I was like trying to feed in information into GPT-3.”
Speaker
Jerry Liu
Publisher
Latent Space

17 / prediction

Like probably not as for some people, the three lines of code might work, but I think increasingly, like honestly, 90% of the users I talked to have questions about how to improve the performance of their app.

“Like probably not as for some people, the three lines of code might work, but I think increasingly, like honestly, 90% of the users I talked to have questions about how to improve the performance of their app.”
Speaker
Jerry Liu
Publisher
Latent Space

18 / prediction

Um, the way I think about this is kind of like, obviously RAG is the default way, like to be clear, RAG right now is the default way to actually augment stuff with knowledge.

“Um, the way I think about this is kind of like, obviously RAG is the default way, like to be clear, RAG right now is the default way to actually augment stuff with knowledge.”
Speaker
Jerry Liu
Publisher
Latent Space

19 / evaluation

I think in general, when I talk to founders about like the fundraise process, it's never like the most fun period, I think, because it's always just like, you know, there's a lot of logistics, there's lawyers you have to, you know, get in the loop.

“I think in general, when I talk to founders about like the fundraise process, it's never like the most fun period, I think, because it's always just like, you know, there's a lot of logistics, there's lawyers you have to, you know, get in the loop.”
Speaker
Jerry Liu
Publisher
Latent Space

21 / evaluation

Um, but this kind of relates to the initial like AI engineering posts that you put out and then also just like the role of an AI engineer and the skills that they're going to have to learn to truly succeed because there's an entire On one end, you have people that don't really, uh, like understand the fundamentals and just want to use this to like cobble something together to build something.

“Um, but this kind of relates to the initial like AI engineering posts that you put out and then also just like the role of an AI engineer and the skills that they're going to have to learn to truly succeed because there's an entire On one end, you have people that don't really, uh, like understand the fundamentals and just want to use this to like cobble something together to build something.”
Speaker
Jerry Liu
Publisher
Latent Space

22 / recommendation

There's like a certain amount of just like LLM ops, like tooling and concepts and just like practices that people will kind of have to internalize if they want to optimize these. And so I think that the reason I think being able to build like RAG from scratch is important is it really gives you a sense of like how things are working to get, help you build intuition about like what parameters are within a RAG system and which ones actually tweak to make them better.

“There's like a certain amount of just like LLM ops, like tooling and concepts and just like practices that people will kind of have to internalize if they want to optimize these. And so I think that the reason I think being able to build like RAG from scratch is important is it really gives you a sense of like how things are working to get, help you build intuition about like what parameters are within a RAG system and which ones actually tweak to make them better.”
Speaker
Jerry Liu
Publisher
Latent Space

23 / prediction

I actually think once the multimodal models come out, I think there's just like mathematically nicer properties of you can just get like join multiple embeddings, like clip style.

“I actually think once the multimodal models come out, I think there's just like mathematically nicer properties of you can just get like join multiple embeddings, like clip style.”
Speaker
Jerry Liu
Publisher
Latent Space

24 / evaluation

One is like RAG is basically just, 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 and everything that we're doing nowadays in terms of like stuffing stuff into the prompt is just algorithmic.

“One is like RAG is basically just, 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 and everything that we're doing nowadays in terms of like stuffing stuff into the prompt is just algorithmic.”
Speaker
Jerry Liu
Publisher
Latent Space

25 / prediction

Because I think what I also ended up discovering was the fact that there was starting to become a wave of developers building on top of GPT-3 and people were starting to realize that what makes them really useful is to apply them on top of your personal data.

“Because I think what I also ended up discovering was the fact that there was starting to become a wave of developers building on top of GPT-3 and people were starting to realize that what makes them really useful is to apply them on top of your personal data.”
Speaker
Jerry Liu
Publisher
Latent Space
Search evidence