The places where I've seen unequivocal wins with AI are repetitive tech debt tasks that apply the same transformation across a large amount of code or refactor under a pre-existing test suite with good coverage. It's great for initial research, brainstorming, and can be good (despite the sycophancy) as a rubber duck conversation partner. I use AI constantly, for work and in my personal time, but we've hit a ceiling where I no longer find it helpful for the models to absorb more of the intellectual labor. They get things wrong more aggressively, and more elaborately. They're inadequately curious. I cannot keep up with the endless bad technical writing, and it makes it harder to spot factual errors and bad reasoning.

Here's what I want: I want AI as an assistant that helps me make decisions, and ensures that I'm in the driver's seat. AI as an over-confident prodigy on speed is what we're getting lately, and it's losing me.

It's odd but only enlightenment and post-enlightenment thinkers seem to approach their work this way, as if it were an absolute step forward which will never need to be revisited. You don't generally find it in ancient or medieval philosophers, who are much more interested in eking out nuance and exposing difficulties than in laying absolute groundworks and so on. In the enlightenment (at least in philosophy), progressivism and delusional absolutism always go hand in hand.

> Ed is generous enough to flag errors, yet prudent enough not to overwhelm the novice with verbosity.