LLMs are still just low code / no code software

I'm not aware of any low/no code platform which can read an error, delve the code, and create a fix. LLMs are more than just tools for generating code.

Case in point, I don't have to wait for open source maintainers to get back to me about a bug to keep making progress.

https://github.com/vllm-project/llm-compressor/issues/2914