LLM Agents and Tools

How do you suppose to build a tool-using LLM that doesn't do that?

Why not just use a standard LLM prompt?

I would fully expect an LLM to not get natively good at this but to know how to reach out to another tool in order to get good at this

You have it write a program to analyze it. I think a lot of people fail to understand that you don't always need the LLM to do the thing, have it write a program to do the thing for you.

There should be a standard template/language to structurally prompt LLMs. Once that is good, all good LLMs should use the doc to fine tune it to take in that standard. Right now each model has their own little way to best prompt it and you end up needing programs like this to sit in between and handle it for you

Read this, it might change your mind on the usefulness of large language models:https://langchain.readthedocs.io/en/latest/modules/agents/ge...

Any interesting examples of methods to make LLMs more "programmable?"

`llm` might be the closest thing to that right now.https://github.com/simonw/llm

Either LLM / ai becomes perfect or we will start writing code/frameworks which makes it much easier for LLM/ai to use them.

Exactly! The way in which the LLM is used here is very, very basic and outdated. This experiment should be redone in a proper „agentic” setup where there is a feedback loop between the model and the runtime plus access to documentation / internet. The goal now is not to encapsulate all the knowledge inside single LLM - this is too problematic and costly. LLM is a language model not knowledge database. It allows to interpret and interact with knowledge and text data from multiple sources.