11–20 of 46 posts
Neat. I was just thinking that one thing you can do that current large language models don't do is use a calculator to check your work. So, the first thing I'd want to try is hooking up some basic arithmetic to see if its math gets more reliable. And if not, why not? Seems like someone would have tried this already?
It's built-in :-)
Could you use this to provide better support chat bots? That is, support bots obviously need to be scoped so that they only give information the user asking has rights to, e.g. "Show me the stocks in my portfolio". Assuming the user has logged into the interface showing the chat, is there a way to pass that user's unique access token through to one of these Fixie Agents to ensure that the data being accessed is scope…
Neat, this is like a SaaS version of Langchain[1]. For those who haven't already seen it, Langchain is a framework that gives you the ability to do this as well as integrate out of the box solutions for other common problems like memory. [1] https://langchain.readthedocs.io/en/latest/
Langchain is awesome. Another great library is GPT Index. This field is apparently being called "prompt orchestration" (getting data from external sources, chaining going back and forth with an LLM, etc).
Looks interesting, can you show us more use cases on the landing page? The stock price example is okay, but I want to see what I can use this for that I can't currently do easily. What problems does this solve?
What exactly is running on my infrastructure? Do I need to buy GPUs? What state needs to live on Fixie cloud infrastructure?