Task Paralysis and AI

I’ve been using CC as my GTD-buddy. All the usual plaintext files in a git repo, all the usual processes and workflows and constraints; but I’ve written two skills that have taken the activation energy out of what used to be the hard parts for me: /process-inbox and /weekly-review. Process-inbox interviews me item by item, making suggestions which I accept or amend, and it does the bookkeeping. I tell it when I want to do something and what calendar I want it on and it makes the calendar event. Weekly-review walks through an overview of everything done that week, all my open tasks and projects, makes sure everything has a scheduled next action. Sometimes I make a note, cancel something, reschedule something, whatever.

This is nothing I couldn’t do on my own, and in fact, it’s a lot slower than just manually editing files myself. But: this way it’s actually getting done :)

There’s too much hyperbole on this subject, so I won’t add to it; but it has solved a lot of very-long-running problems of mine.

I have a feeling that after enough slop has entered the system, the AI will also have difficulty debugging/understanding it.

My questions are: will the AI get to be above our level at creating grokkable source code before it comes unmanageable? And even if not: will the models' ability to understand and modify slop outpace it's ability to create it?

For our jobs, I hope neither is true. But we'll see. Even in the best case we'll have a lot of cleaning up to do.

I wonder if this is a new thing or if it is a repeat of the past.

Like ...

When I was young, I wrote this REALLY tight assembly code - loops that were measurably better than C or other high-level languages.

Then obviously assembly was minimized, then forgotten.

Then years later, I found I was happy using even interpreted languages, not even using a compiler.

When first using perl and having a data structure not be as useful to the final output, in a line of code I used a different data structure and sorted the output exactly like I wanted. Too much effort if it had been C, and very much so for assembly language. But I got what I reall

Is AI a repeat of this? instead of assembly language, instead of C, instead of python, do we become high-level-english-language tech folks? Will AI just let us hand off our code and physical design to a fab, and will it make us happier?

I also wonder if SoA to you is how it behaves or how it is, and does it matter if you stop looking at the code just like I stopped comparing the code the C compiler generated to the assembly language I wrote. And what about years later with -O3, will AI have -O3?

Why is this on the front page? Probably the least interesting thing I've read all week

> The gambling trope is so tired...

>>> That sounds like a process problem. LLMs, like any tool, work better if you don't use them in the naive "do this" way...

The "you're holding it wrong" trope is even more tired than the gambling trope.