Today, I merged my fix, net -381 LoC.

I'm using them too of course, they read and type and hunt for bugs and test faster than I can. But I'm using them as my tool, not being a tool using them.

I remember discussions over relative easy of use of gray box wireframes... and that led to better products.

Now I've got designers vibing monstrosities that would have fit right in in the Flash era, I guess in order to draw even nicer rectangles now that execs than wave at AI and get a design.

It actually seems somewhat difficult to train such a model since "all the text on the Internet" is easier to provide in bulk than a highly curated set.

I hope there's a "good enough" point but I don't think we're there yet. Like for me hardware got good enough several years ago. But while opus 4.7 is really good compared to everything else, it's not so good that I would use it at a discount over whatever is available in a few months. The improvement in quality, speed, and daily frustration is worth it to me... Spoken as someone whose employer is footing the bill, so take that with a grain of salt.

I want to run my own local models, but I don't think that's feasible without lots of frustration until a few generations of frontier models are so good that they're almost indistinguishable for common tasks. Kind of like how MacBook pros have been for a while.

I love this sentence.

You mean for a family... I hope?

This is an interesting response when faced with concrete data that the buy-side of engineering is actively heating up in direct correlation with LLM adoption.

An alternative interpretation of your observation is that perhaps your company has particular traits that are helped more by LLMs than the average eng org. There's a growing SWE consensus that LLMs boost productivity by 10-20%. However, there are contributing factors that can make LLMs much more of a human replacement:

* Selling labour & services, rather than engineered software. ie an agency that builds customized versions of well-understood software, rather than net new capabilities.

* Selling software that has a low ceiling of complexity and a short half-life, such that LLMs can realistically architect & maintain it over its useful lifetime.