blip-caption VS geppetto

I've been gleefully exploring the intersection of LLMs and CLI utilities for a few months now - they are such a great fit for each other! The unix philosophy of piping things together is a perfect fit for how LLMs work.

I've mostly been exploring this with my https://llm.datasette.io/ CLI tool, but I have a few other one-off tools as well: https://github.com/simonw/blip-caption and https://github.com/simonw/ospeak

I'm puzzled that more people aren't loudly exploring this space (LLM+CLI) - it's really fun.

I suggest trying BLIP for this. I've had really good results from that.

https://github.com/salesforce/BLIP

I built a tiny Python CLI wrapper for it to make it easier to try: https://github.com/simonw/blip-caption

I'm heavily using https://github.com/go-go-golems/geppetto for my work, which has a CLI mode and TUI chat mode. It exposes prompt templates as command line verbs, which it can load from multiple "repositories".

I maintain a set of prompts for each repository I am working in (alongside custom "prompto" https://github.com/go-go-golems/prompto scripts that generate dynamic prompting context, i made quite a few for thirdparty libraries for example: https://github.com/go-go-golems/promptos ).

Here's some of the public prompts I use: https://github.com/go-go-golems/geppetto/tree/main/cmd/pinoc...

I am currently working on a declarative agent framework.

(author here): I am currently writing a book about programming with LLMs, I have absolutely put my money where my mouth is over the last year, and there is not doubt in my mind that we will see incredible tools in 2024.

Already the emergent tools and frameworks are impressive, and the fact that you can make them yours by adding a couple of prompting lines and really tailor them to your codebase is the killer factor.

My tooling ( https://github.com/go-go-golems/geppetto ) sucks ass UI wise, yet I get an incredible value out of it. It's hard to quantify as a 10X, because my code architecture has changed to accomodate the models.

In some ways, the trick to coding with LLMs is to... not have them produce code, but intermediate DSL representations. There's much more to it, thus the book.

All of these examples were built in a couple of hours altogether. By the end of the article, you will be able to build them too, with no code involved.

I don't bother manually writing any of this data munching / API wrapping / result validating code anymore. I had to build a server-to-server integration with Google Tag Manager recently. I literally copy pasted the webpage into a simple 3 line prompt and can now generate PHP classes, typescript interfaces, event log parsers, SQL serialization with a simple shell command.