It’s not. The feature is implemented deep within WebKit so it makes sense to be on this blog.
> It’s precisely because Adaptive Dark Mode is happening deep within the WebKit browser engine that we are able to find creative ways to solve the most complex challenges, apply the transformations with great speed and power efficiency
This sounds roughly right to me, except for "maintainability". In my experience, agents really don't like deleting code unless you explicitly ask for it. If you're not careful, you end up with new better implementations of things but with the old implementation still around in perpetuity. Humans do this too of course.
They're being trained by a lot of repetitions of one-shot bugfixes and feature implementations. If they don't have to maintain code over the long term they have no incentive to not take the easy win with lower immediate risk and higher longer-term maintenance burden.
The shadow of Chesterton's Fence is relevant. The LLM doesn't know why code exists, if it doesnt start traversing up the scope of a project. Even then, it can't be sure that the code isn't a dependency of something else outside the project (especially if there's a side effect). I'm not sure it's ever going to be easy to address this concern in a straightforward and portable way.
I do sometimes see duplicate functions, which is troubling.
Humans had to get it drilled into them that "+12 -440" is a damn good line stat, and that keeping around dead code is bad, especially in the age of version control.
Not too surprised that LLMs also don't "get it" by default?
If you're reading this and you're put off by the "uses an LLM", don't be. This is not a low-effort video, quite the opposite. This is one of the best YouTube videos I have ever seen.
Mirrors my experience: LLMs are really good at optimizing, better than most humans. But also, they tend to not reach absolute peak performance where people made an effort to optimize something.
Since most problems see fairly little optimization, that's still a big win most of the time.
reply