The thing about this is that in a different codebase, even just that search for the trumpet guy could either burn a ton of tokens and come back with nothing or find it but light the ocean on fire in the process. This is because trumpet guy would be named "asset-ds1f23nbiq35421fsda.jpg", and it would be located in an images folder with thousands of other similar assets. So the agent starts by grepping for reasonable names, discovers nothing but finds an image directory, and then searches inside. In the worst case, I guess it starts analyzing each image. Or maybe it checks the article like he mentions, but the codebase uses a component library and the filename thing is still true, so it analyzes every image in the page. This is a bit of hyperbole, of course. Please allow it for the sake of comedic example.

Many of his other prompt examples also illustrate this. The author is massively leveraging the architecture of the organization through familiarity. It could well be the case that even an LLM was used to set that up, but I doubt it happened in one prompt or without critical thought. To be fair, I guess he's sort of trying to point that out, but by saying "Look how lazy I am while it still works" or something like that in order to look cool, I think all he's conveying is "Look how easy this is", when it's potentially not and could increasingly cost him/his company wildly varying amounts of money based on how he goes about it. When tokens were virtually free, no one cared. This is increasingly not true. Many are drawing comparisons to early cloud architecture.

I find this is sort of similar to the problematic idea that in theory anyone can clone your repo and get a local dev environment running in a few seconds. So then you try it with a non-technical staff member and quickly realize how unrealistic that is as you run into abstraction after abstraction that is completely foreign to them.