tool / uses
Pytantic
“I think at some point, you know, tools like Guardrails and Marvin came out. Those are kind of tools that I use XML and Pytantic to get structured data out.”
Public evidence record
Jason Liu
Published podcast speaker
- Claims
- 17
- Episodes
- 1
- Shows
- 1
- Named items
- 1
Books, apps, and tools
The evidenced stack.
Claim ledger
What Jason said.
17 transcript-backed records
01 / recommendation
I think if you're running into issues where you have like 20 or 50 or 60 function calls, I think you're much better having those specifications saved in a vector database and then have them be retrieved, right?
“I think if you're running into issues where you have like 20 or 50 or 60 function calls, I think you're much better having those specifications saved in a vector database and then have them be retrieved, right?”
- Speaker
- Jason Liu
- Publisher
- Latent Space
02 / evaluation
Just because you can sort of specify relationships between these entities that you can't do in a parallel function calling, you can have a single chain of thought before you generate a list of results.
“Just because you can sort of specify relationships between these entities that you can't do in a parallel function calling, you can have a single chain of thought before you generate a list of results.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
03 / evaluation
In which case, like we either can assume that, or we can assume that like things need to happen in some kind of sequence as a DAG, right? But if it's a DAG, really that's just like one JSON object that is the entire DAG rather than going like, okay, the order of the function that return don't matter.
“In which case, like we either can assume that, or we can assume that like things need to happen in some kind of sequence as a DAG, right? But if it's a DAG, really that's just like one JSON object that is the entire DAG rather than going like, okay, the order of the function that return don't matter.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
04 / belief
Like I think when we were in like auto GBT land, there was that one example where it's like, I wanted it to like buy me a bicycle overnight.
“Like I think when we were in like auto GBT land, there was that one example where it's like, I wanted it to like buy me a bicycle overnight.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
05 / belief
Whereas like maintaining the library, I think is mostly just kind of like a utility that I try to keep up, especially because if it's not venture backed, I have no reason to sort of go down the route of like trying to get a thousand integrations.
“Whereas like maintaining the library, I think is mostly just kind of like a utility that I try to keep up, especially because if it's not venture backed, I have no reason to sort of go down the route of like trying to get a thousand integrations.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
06 / belief
I mean, the biggest one really was the fact that I think for just four years, I was so bearish on language models and just NLP in general.
“I mean, the biggest one really was the fact that I think for just four years, I was so bearish on language models and just NLP in general.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
07 / uncertainty
I don't know if it's fully GA now, if it's GA, if you can get a commercial access really easily.
“I don't know if it's fully GA now, if it's GA, if you can get a commercial access really easily.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
08 / belief
I feel like we've gone too much in the looping route and I think a lot of more plans and like DAGs and data structures are probably going to come back to help fill in some holes.
“I feel like we've gone too much in the looping route and I think a lot of more plans and like DAGs and data structures are probably going to come back to help fill in some holes.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
09 / recommendation
I think right now, the first steps are just how do we take this DAG idea and break it down to modular components that we can like prompt better, have few shot examples for and ultimately like fine tune against.
“I think right now, the first steps are just how do we take this DAG idea and break it down to modular components that we can like prompt better, have few shot examples for and ultimately like fine tune against.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
10 / prediction
I definitely think that's the case because for the most part, I imagine you either have like less than three tools or more than a thousand.
“I definitely think that's the case because for the most part, I imagine you either have like less than three tools or more than a thousand.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
11 / evaluation
This is the part that feels crazy because really the difference is LLMs give you strings and Instructor gives you data structures.
“This is the part that feels crazy because really the difference is LLMs give you strings and Instructor gives you data structures.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
12 / preference
get in a Django app, right? But no one would say, I like went off of Django because I'm using requests now.
“get in a Django app, right? But no one would say, I like went off of Django because I'm using requests now.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
13 / preference
I think at some point, you know, tools like Guardrails and Marvin came out. Those are kind of tools that I use XML and Pytantic to get structured data out.
“I think at some point, you know, tools like Guardrails and Marvin came out. Those are kind of tools that I use XML and Pytantic to get structured data out.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
14 / recommendation
I think function calling gives you a tool to specify the fact like, okay, this is a list of objects that I want and each object has a name or an age and I want the age to be above zero and I want to make sure it's parsed correctly.
“I think function calling gives you a tool to specify the fact like, okay, this is a list of objects that I want and each object has a name or an age and I want the age to be above zero and I want to make sure it's parsed correctly.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
15 / evaluation
No, so I think because at Stitch Fix, a lot of the machine learning engineers and data scientists were writing production code, sort of every team's systems were very bespoke.
“No, so I think because at Stitch Fix, a lot of the machine learning engineers and data scientists were writing production code, sort of every team's systems were very bespoke.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
16 / preference
Yeah. So I'm not really into that world of tooling, whereas I think, you know, I spent three good years building observability tools for recommendation systems.
“Yeah. So I'm not really into that world of tooling, whereas I think, you know, I spent three good years building observability tools for recommendation systems.”
- Speaker
- Jason Liu
- Publisher
- Latent Space
17 / preference
I think Stitch Fix is a place where you kind of go because you want the work offloaded.
“I think Stitch Fix is a place where you kind of go because you want the work offloaded.”
- Speaker
- Jason Liu
- Publisher
- Latent Space