Eno Reyes

It's like, look, maybe it doesn't matter what's going on inside, as long as you can model it.

And so...

From there, going to Microsoft and seeing like a very large organization, software development lifecycle, experimenting with ML strategies and techniques, and then hugging face where most of these ML models were hosted.

I think that there was sort of this clear side of like what software development looked like at different scales.

how people were thinking about different deep learning and ML strategies.

Transformers had very recently become apparently the strongest method for most deep learning techniques.

And it really was seeing how people

we're very fixated on the, the singular use cases of transformers.

Like we want to build a classifier or we want to build a, you know, uh, entity recognition system, uh, that when LLM started to become strong, seeing how general they were and how they started to eat all the different use cases, uh,

It became clear that there was a different approach towards software development that wasn't going to involve piecemeal things like, oh, now we have autocomplete.

Now we have a tool for classifying whether the code has a bug in it or not.

And so...

All of that bubbled when basically the LLM APIs came out in a way that was accessible to a software developer where you could just call OpenAI's API.

You could just call Cohere was actually a popular API at the time.

And so I think that there was a couple of folks in the open source community, including myself, who basically just said, what if we put this in a while loop?

Like, what if we what if we keep seeing what the LLM can do?

What if we add structured parsing?

And so I think those ideas were all bubbling up right around 2023, early 2023.

And seeing it actually all come together.

Like when I met my co founder, it was actually a seven day period from the time we met.