The Evolution of v0 and Vercel's AI SDK with Malte Ubl

yeah so I think one thing that's definitely going to happen is that this like notion of full stack developer is going to become more true because if we don't look into the future right now the models are all commoditized like Google anthropic they all have essentially equally good models so they have that backdrop of commoditized models they're going to get cheaper to invoke and in order to make products good on them they actually need access to more data and my impression is that people underestimate how much proprietary data they have

access to you're listening to the AI native Dev brought to you by [Applause] [Music] Tesla hi there and welcome to another episode of the AI native developer on today's episode we're actually going to be showing you a an episode that was

from the AI native Devcon and this is actually one of the Keynotes from mol oé who is the CTO of Vel and and mol is going to be talking with Dion Almer who is the field tto of tessle and when this session came on the conference I saw a ping in one of our chats from a guy I massively respect who says this guy speaking malol he is perhaps the single best web engineer on the planet and so when someone says that I listen to this session and in in this episode mul will

be talking about forel's place in the disruptive world of llms and he talks about how when we play with chat GPT it's great with creating text and generating text but it's not necessarily good at creating web pages so uh this one of the cell's challenges was really about creating that user experience to build web pages and and that's a hard part not just the piece that allows NM to actually create websites that make sense but what does that UI look like with a developer trying to actually

build that is it chat is it something different and and mol will talk about the AI SDK which Vel created and this is a couple of things that is mentioned in one there's the discussion about that creating that abstraction layer for effectively the apis of existing models if you're using open AI or if you're using anthropic if you want to switch between the two you want to do that with the least disruption on your code and and your interactions as possible so there's a number things which it does

including code streaming things that people tend not to want to write by themselves and that allows for that model switching to be as I mentioned far less painful uh one of the examples that was given is it's like JBC uh for the '90s and the second thing which multe mentions as part of this AIS SDK is how you can connect a a developer UI with the llm in the background and this was really interesting whereby we don't just want to pass text to the AI to the llm and get text back we might want to

interact in different ways for example if I ask a question I might want a react component back as an answer or for example if I interact with a react component on a web page I want that interaction to be represented and sent to the LM depending on what I do this is a really great session with molta and I hope you enjoy it so over to Dion and multe thanks so much for for taking the time to chat with us a little bit about AI development I know that Vel has gone through through and has built some

really cool AI developer tours and you've gone through some interesting changes there so excited to learn a little bit about that with you so to start with if we could go back in time a little bit before we go to where we are now and into the future I was curious about when the birth of this form of the AI Revolution kind of kicked in for you like when did it first hit you were you skeptical at first and was there an aha moment where you like oh maybe there's actually something to this llm thing so I joined for sell it's now almost been 3