My experience with AI tools is the opposite. The biggest energy thieves for me are configuration issues, library quirks, or trivial mistakes that are hard to spot. With AI I can often just bulldoze past those things and spend more time on tangible results.

When using it for code or architecture or design, I’m always watching for signs that it is going off the rails. Then I usually write code myself for a while, to keep the structure and key details of whatever I’m doing correct.

For me, LLMs always, without fail get important details wrong.

- incessantly duplicating already existing functionality: utility functions, UI components etc.

- skipping required parameters like passing current user/actor to DB-related functions

- completely ignoring large and small chunks of existing UI and UI-related functionality like layouts or existing styles

- using ad-hoc DB queries or even iterating over full datasets in memory instead of setting up proper DB queries

And so on and so forth.

YYMV of course depending on language and project

Sounds to me like you'd benefit from providing detailed instructions to LLMs about how they should avoid duplicating functionality (which means documenting the functionality they should be aware of), what kind of parameters are always required, setting up "proper DB queries" etc.

... which is exactly the kind of thing this new skills mechanism is designed to solve.

> Sounds to me like you'd benefit from providing detailed instructions to LLMs about how they should avoid duplicating functionality

That they routinely ignore.

> which means documenting the functionality they should be aware of

Which means spending inordinate amounts of time writing down about every single function and component and css and style which can otherwise be easily discovered by just searching. Or by looking at adjacent files.

> which is exactly the kind of thing this new skills mechanism is designed to solve.

I tried it yesterday. It immediately duplicated functionality, ignored existing styles and components, and created ad-hoc queries. It did feel like there were fewer times when it did that, but it's hard to quantify.

100%. It’s like managing an employee that always turns their work in 30 seconds later; you never get a break.

I also have to remember all of the new code that’s coming together, and keep it from re-inventing other parts of the codebase, etc.

More productive, but hard work.

I have a similar experience. It feels like riding your bike in a higher gear - you can go faster but it will take more effort and you need the potential (stronger legs) to make use of it

It's more like shifting from a normal to an electric bike.

You can go further and faster, but you can get to a point where you're out of juice miles from home, and getting back is a chuffing nightmare.

Also, you discover that you're putting on weight and not getting that same buzz you got on your old pushbike.

Hey, that's a great analogy, 10/10! This explains in a few words what an entire article might explain.

Considering the last 2 years, has it become harder or easier?

Definitely harder.

A year ago I was using GitHub Copilot autocomplete in VS Code and occasionally asking ChatGPT or Claude to help write me a short function or two.

Today I have Claude Code and Codex CLI and Codex Web running, often in parallel, hunting down and resolving bugs and proposing system designs and collaborating with me on detailed specs and then turning those specs into working code with passing tests.

The cognitive overhead today is far higher than it was a year ago.

Also better and faster though!! It's close to a Daft Punk type situation.

Copilot is the perfect name.

Woah, that's huge coming from you. This comment itself is worth an article. Do it. Call it "AI tools make development harder work".

P.s. always thought you were one of those irrational AI bros. Later, found that you were super reasonable. That's the way it should be. And thank you!