Language model

We're talking about a co-founder or an expert that is made of artificial intelligence, right? So I'm curious, what does its brain consist of? What LLM, if any, does it run on? um where is it data coming from like is it is it gleaning insights from shopifying is it tied to larger data sets like where does the this advice come from i was wondering if you could break down more of like the functionality of what makes a great ai co-founder

yeah uh so sidekick uh it's Its architecture is basically an LLM driving it.

And this LLM is, you can think of it like as a loop, looping through different tool calls or having different skills.

This LLM in particular, right now we're running on the Sonnet model from Anthropic, hosted on Google's infrastructure on GCP.

And that's also, uh, changing also because Google actually as user interface is inserting more and more AI answers into the experience.

So even those people who aren't using LLMs or large language models like ChatGPT or whatever to do their research, they're using Google instead.

Google in of itself is changing to have an AI overview on top of that now.

So I think it's unavoidable that AI will probably be the primary kind of user surface by which we, you know, get our information from.

So in the search era, right, we had a vendor, for the most part, Google, who had a algorithm that somebody architected and programmed.

Now they kept that secret and then the whole industry of SEO was really around reverse engineering that and figuring out how you kind of play to that algorithm and optimize for it.

Well, these LLMs are not an algorithm, right? Nobody programmed these LLMs to have a particular behavior.

They are, again, we use this term non-deterministic.