I think I disagree here.

The integration parts aren’t natural language issues but connecting systems and how to put these things in your workflow.

For example. I have a bunch of off the cuff questions and problems and tasks. I want to have these in one place and have that trigger a conversation with ChatGPT, which shows the results in the first place but can be continued easily.

Before it was added the other week, I could track issues in linear and I could have codex write the code to solve them but only by manually moving text from one place to another, manually moving the tickets, checking on progress, click g buttons to open prs - all of that is integration hassle but none is about the model itself. I think now with GitHub copilot I could just assign a task.

The point is because natural language systems seem so easy to use people assume the existing hard parts will become easy. But integrating systems is hard not because formal languages are challenging to use but because connecting systems is inherently challenging. The switch from formal to natural language doesn’t reduce challenge it just alters it.

We’re saying the same thing. Integration is the hard (still technical) part.