In my experience the differences are mostly in how the code produced by LLM is prompted and what context is given to the agent. Developers who have experience delegating their work are more likely to prevent downstream problems from happening immediately and complain their colleagues cannot prompt as efficiently without a lot of hand holding. And those who rarely or never delegated their work are invariably going to miss crucial context details and rate the output they get lower.

But the reading pdfs part is important -- and really hard to beat for me, the iOS drag/scroll/pinch/zoom UX perceived responsiveness is still unmatched IMO. It would take some real creativity beyond liquid glass to enshittify this aspect out.

The more time you spend in the mall, the fuller are the bags on the way out, be it out of chance, habit, or convenience.

- this makes them really stand out, much easier to track the mutation visually,

- the underscore effect is intrusive just-enough to nudge you to think twice when adding a new `var`.

Nothing like diving into a >3k lines PR peppered with underscores.

  diffs.countIf { line -> 
      line.all { abs(it) in 1..3 } and ( 
          line.all { it > 0} or
          line.all { it < 0}
      )
  }

I understand this passage and can relate, "self-evidently awful to them only" seems a bit of a stretch. There are places on Earth where "being employed for tourism" means job security, worker rights and social protections, where staff is treated with respect and are allowed dignity.

I agree, it can feel a lot like a slot machine at times, and it's a failure mode somewhat unique to developing with LLM, where it doesn't just fail outright or tell you "I don't know how to do that", but instead you find yourself in the end of a sometimes hours long spiral of trying just-one-more-prompt.

It's important to experience this mode of failure and learn to notice the "spiral" early and adjust the approach. Sometimes it's enough to switch to a different model, often an explicit planning step helps. But more likely than not, a "spiral" means approaching the frontier of LLM possibility. In my experience, certain types of changes are really hard for current gen LLM to pull off, like large scale refactorings changing the project architecture, or implementing genuinely novel algorithmic ideas, so we still need a human touch for these (yay?)

In some ways it's easier to delegate to an AI because you don't have to care for anyone's feelings but your own, and you lose nothing but your own time when things don't go well and you have to reset. On the other hand, when the delegation does not go well, you still got yourself to blame first.

And yes, the model keeps changing under you -- much like a horse is changing under a jockey, forcing them to adapt. Or like formula drivers and different car brands.

You can absolutely improve the results by experimenting with prompting, by building a mental mode of what happens inside the "black box", by learning what kinds of context it has/does not have, how (not) to overburden it with instructions etc. etc.