Planning, design, management alignment, finding customers, integrating with other products, waiting for review, etc. Basically all the human stuff that can't be automated away.

Your comment reminds me to add building a support team to the list.

Having a global monopoly on these kinds of things is part of what has let U.S. companies get away with being so anti-consumer for so long.

If you're not conscious about it in retirement, it's easy to just do nothing, waste away, and find out many years too late. You actually need different ingredients to feel satisfied.

"How do you know x?" is in fact much more common.

100-200k, is what you'd expect elsewhere. Which is still pretty good, just not astronomical.

If anything there will be less tech debt, because it's easier than ever to clean up.

Unit and end-to-end tests are free now.

Telling an agent to go through your code base and find bugs is free now.

Telling an agent to generate all possible user interaction to your API and then performance test it is free now.

Everything is so easy and takes much less time than it used to.

I'm not sure if this library or if the AI tool itself really matter all that much, but a lot of people seem to think that they do, or will anyways, which is probably why this post has no context. Because the author assumes that both the library and the tool are well known, but I think they're only well known by those in the AI world.

You know how it is. You only know what you know, and it's hard to remember what it was like when you didn't know. When you're around people who talk about the same things all the time, it's easy to just assume that's what's everyone's talking about.

There are so many of these little tools coming and going these days it's hard to keep track. Some of them might end up mattering, but most of them probably won't.

I think if you knew more musicians personally, you would feel different. What you're imagining and the day-to-day lived experience of most real musicians don't exactly overlap that much.

So in a sense you're ruining the music for yourself based on nothing but you're imagination.

I think a lot of modern life suffers from this problem. Most of us live such walled in lives now, experiencing everything second hand, from a distance. The absence of information lets us fill the gap with anything we want, which ends up being more a reflection of our own psychology than reality.

But the decline of the Roman empire took nearly 500 years.

Even the bronze age collapse, which you might say happened fast, took more than 100.

A thought I have every time someone parrots this is, "what is reasonable to expect?".

Would you have heard people saying the same thing during the civil war?

During the gilded age?

After the stock market crash?

During the 1970s oil crisis or the severe increase in violent crime during the 1970s and 80s?

Spain was an actual dictatorship in recent memory, and now you'll hear Americans fantasizing about fleeing there.

Should we not expect an empire to have ups and downs?

If you stick to targeted problems with well-described prompts, acceptance criteria, and lots of linting, unit testing, and integration testing, you'll typically get what you want with code that looks okay. And when things start to stray, it's easy to get things back on track.

It's when you start trying to have LLMs write too much without a human review that you start getting unnecessary function chains, abstractions that aren't needed, code that doesn't really match the existing style, duplicate code, missing functionality, hallucinated functionality, tautological tests, etc.

It works best when there's regular feedback in the loop about what's good and what's not good. Testing and linting can fill in some of that, but we still need a human in the loop with "taste", so to speak.

    never blame anyone for anything

Assigning blame, via agency or otherwise, and the associated social or legal consequences are additional signals in the environment that influence and change behavior.

If the actions of an individual were involved in propagating some chain of events, then it's perfectly valid to respond to their involvement, via social stigma, punishment, etc, regardless of whether or not there is "agency". The knowledge and anticipation of a similar response changes future actor's behavior, with or without free will.

This discussion itself is exactly an example of this in practice. If there's no such thing as agency, then us talking about what someone should or shouldn't do, given whether there is free will, have any influence on anything, except that it does because interacting with these ideas themselves change behavior, with or without free will.

This is what people mean when they say we should just ignore the question of free will entirely, because it doesn't really factor into how we should design the social contract.

You are clearly a naysayer. I get it. I was one too for a long time. Then I found a workflow and a model that was clearly delivering results and that's what I use now.

It's only a matter of time before it happens to everyone, even you. Once you have the aha moment where it works for you, you'll stop asking everyone whether they really know if it's better.

The LLM-based workflow above produces good code at a speed at least as fast as my previous workflow and typically many, many, many times faster with the code produced often using designs I would have never thought of before being able to bounce ideas off an LLM first. The biggest difference, besides the time obviously, is that the energy I need to spend is in very different places between the two.

Before it was thinking about what I needed to do and writing the code.

Now it's thinking about what I need to do and reviewing the code.

- Think about requirement

- Spend 0-360 minutes looking through the code

- Start writing code

- Realize I didn't think about it quite enough and fix the design

- Finish writing code

- Write unit tests

- Submit MR

- Fix MR feedback

Until recently no LLM was able to properly disrupt that, however the release of Opus 4.5 changed that.

Now my workflow is:

- Throw as much context into Opus as possible about what I want in plan mode

- Spend 0-60 minutes refining the plan

- Have Opus do the implementation

- Review all the code and nitpick small things

- Submit MR

- Implement MR feedback

    Their own achievements become meaningless.