Ideas are cheap for a very narrow vision of "ideas". Sure, you can build your recipe site, TODO list or whatever it is cheaply and quickly without a single thought, but LLMs are still just assembling lots of open-source libraries _mostly_ written by humans into giant piles of spaghetti.

There's a hilarious thread on Twitter where someone "built a browser" using an LLM feedback loop and it just pasted together a bunch of Servo components, some random other libraries and tens of thousands of spaghetti glue to make something that can render a webpage in a few seconds to a minute.

This will eventually get better once they learn how to _actually_ think and reason like us - and I don't believe by any means that they do - but I still think that's a few years out. We're still at what is clearly a strongly-directed random search stage.

The industry is going through a mass psychosis event right now thinking that things are ready for AI loops to just write everything, when the only real way for them to accomplish anything is by just burning tokens over and over until they finally stumble across something that works.

I'm not arguing that it won't ever happen. I think the true endgame of this work is that we'll have personal agents that just do stuff for us, and the vast majority of the value of the entire software industry will collapse as we all return to writing code as a fun little hobby, like those folks who spend hours making bespoke furniture. I, for one, look forward to this.

The "built a browser" example you gave reminded me how I've "built a browser" as a kid in the 90s using Visual Basic (or something similar) - I've simply dragged the browser view widget, added an input and some buttons that called functions from the widget and there you go, another browser ready :-)

I agree with your vision of endgame. We wouldn't even need a screen, we will communicate verbally or with signs with our agents with some device that will have a long battery life and will always be on.

I just hope that we retain some version of autonomy and privacy because no one wants the tech giants listening in every single word you utter because your agent heard it. No-one wants it but some, not many, care.

Agents deployed locally should be the goal.