Speakers in the public record
Claim mix
belief 16evaluation 5uncertainty 3recommendation 3prediction 1preference 1
Evidence policy
Every row below preserves an exact excerpt. Identified speakers are linked; unresolved voices are labeled and excluded from people counts.
Claim ledger
The useful parts, with receipts.
29 published records
“In terms of like, for you, it's one of the, you know, the model IO modules and that's it. But like, you seem very personally, very passionate about it, but I don't know what the Langchain specific angle for this is, for fine-tuning local models, basically.”
- Publisher
- Latent Space
“I think, you know, LLMs aren't perfect. And I think there's a lot of discussion around the pitfalls of using LLMs to evaluate themselves.”
- Publisher
- Latent Space
“I mean, I think buried in ModelIO is some stuff around like few-shot example selectors that I think is really powerful.”
- Publisher
- Latent Space
“I think JSONformer and stuff like that are still really interesting for like local models, for sure.”
- Publisher
- Latent Space
“I expect that it will probably get better over time as everything in this field.”
- Publisher
- Latent Space
“Cause I think like the best thing is you stumble upon a really good idea and you build something really awesome.”
- Publisher
- Latent Space
“Again, like I think the main thing that even I find valuable about Langsmith is just like the debugging aspect of it.”
- Publisher
- Latent Space
“I was, yeah, I was a bit surprised to see that as well, but I think there's generally a lot of interest in agents and it's also really hard to get them to work.”
- Publisher
- Latent Space
“I think there is your daily rhythm, which I've seen you, you work like a, like a beast man, like mad impressive.”
- Publisher
- Latent Space
“Like, I don't think, like I think like there's, which I know is very hypocritical to say.”
- Publisher
- Latent Space
“The difference I think at the Databricks keynote, you said chains are like predetermined steps and agents is models reasoning to figure out what steps to take and what actions to take.”
- Publisher
- Latent Space
“I think there's also like, you know, like if there is, if there's just more options available, like prices are going to go down.”
- Publisher
- Latent Space
“I think about it as like a prompt registry and you store them and you A-B test them and you do that.”
- Publisher
- Latent Space
“Like one, like, you know, if we think about what it takes to build a really reliable, like context-aware reasoning application, there's probably a bunch of different nodes that are doing a bunch of different things.”
- Publisher
- Latent Space
“I think a few places where we've started to see this be like one of the main things is the AI simulation that came out.”
- Publisher
- Latent Space
“I think another example of this, I mean, Langsmith, which we can maybe talk about was like very kind of like, I think we worked on that for like three or four months before announcing it kind of like publicly, two months maybe before giving it to kind of like anyone in beta.”
- Publisher
- Latent Space
“There was actually my first article on the Twilio blog with a Python script to like predict pricing of like Daily Fantasy players based on my past week performance. Yeah, I don't know.”
- Publisher
- Latent Space
“Then you have a concept called Agents, which I don't know if exactly matches what other people call Agents.”
- Publisher
- Latent Space
“Yeah, we'll probably go. And yeah, we'll do more of that because I think that's definitely part of the application of a chain or agent is you start with a default one, then you improve it over time.”
- Publisher
- Latent Space
“I was looking it up for the podcast and the first tweet was on, I think October 24th.”
- Publisher
- Latent Space
“I think maybe orchestration is a little bit more than 5%, but I like agree that those are like really big pain points that get exacerbated when you have these complex chains and agents where you can't really see what's going on inside of them.”
- Publisher
- Latent Space
“Yeah, I mean, I think that's, you know, you talk about like, again, this whole space is just changing so fast, but you talk about something that could like really change how, because like, you know, a lot of lang chain is kind of like a data orchestration tool in some sense.”
- Publisher
- Latent Space
“To reduce hallucinations, we did a webinar on like evaluating RAG this past week. And I think there's this great project called RAGOS that evaluates four different things across two different spectrums.”
- Publisher
- Latent Space
“I have said that that piece of research is the best bull case for Lang chain and all the vector companies, because it means you should do chains.”
- Publisher
- Latent Space
“You probably start with like a zero-shot prompt. But I think that's a really powerful one that's probably just talked about less because you don't need it right off the bat.”
- Publisher
- Latent Space
“I definitely think probably the main ones, like basically the LLM. So the reason I think the debugging in Lancsmith and debugging in general is so needed for these LLM apps is that if you're building, like, again, let's think about like what we want people to build in with LangChain.”
- Publisher
- Latent Space
“We still think there's, it's just really application specific. So we prioritized instead, making it easy for people to write custom evaluators and then run them client side and then upload the results so that they can manually inspect them because I think manual inspection is still a pretty big part of evaluation for better or worse.”
- Publisher
- Latent Space
“There's a bunch of vector databases that are killing each other out there to get people to embed data in them, and you're like, I love you all.”
- Publisher
- Latent Space
“I don't know if those are like underappreciated though, because I think a lot of people talk about text splitting as being a hard part, and it is a really important part of creating these retrieval applications.”
- Publisher
- Latent Space