I’m using it to do the mundane tasks of unit testing and (some) documentation. I find that the code it spits out isn’t perfect but getting some boiler plate and fixing it up is pretty fast compared to writing from scratch.
I agree with the author that threading is quite critical to maintaining sanity.
In my experience, it's insufficient by itself. I would recommend coupling with some naming conventions around channels and discouraging group DMs for anything substantial.
I’ve used this enough that I wrapped some cli glue around it and wrote https://github.com/radoshi/llm-code
I’ve used this mostly to write Python and bash, with some Makefiles and Dockerfiles thrown in.
GPT-4 is better, albeit slower, than 3.5-turbo. HTH!