strix_varius

I'm sure this is gated by where you work (especially by how technically savvy your manager is), but the most effective contributors at my job tend to be the ones with near-zero (or sub-zero!) net LoC.

LLMs are prolific and they love to add shit. Truly capable engineers are able to achieve more business outcomes with less code / fewer moving parts.

100%. Browsers are considered a commodity but I'd happily pay for a browser that:

1. Could do all the stuff chrome does as well as chrome. (Eg, canvas rendering speed etc). So I can actually use web apps.

2. Just doesn't ever have anti privacy code, pro ad code, etc in it.

I use brave and a self managed lan which is just an ad hoc half assed attempt to reach the above goals. Because there is no other option.

> Measuring programming progress by lines of code is like measuring aircraft building progress by weight.

https://www.goodreads.com/quotes/536587-measuring-programmin...

> It's basically the code for which insufficient people in the organisation have a meaningful understanding of how it works or what it does.

Its connotation also includes being vastly larger than needed for the purpose it serves, _if_ there is even any purpose.

If you can't trust your deeds to be respected then no rational actor would donate land. Instead the farmer would just have kept it.

Do you find it impossible to use LLMs productively without giving over your brain wholesale to them?

Exactly this. Just this week an engineer who seems to purely vibe everything submitted a +700ish LoC fix for what seemed like a pretty simple issue. Moreover it was a perf issue, which in my experience is not usually best fixed by adding more stuff.

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.

lol what? There are definitely ways to make non flashing terminal UIs without this total insanity.

Curious why you prefer 4.6 over 4.7

I've noticed and felt this trend, but I haven't ever seen it put so well or really connected the dots with figma & pretty rectangles.

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.

If there were a coding model as good as opus that didn't know multiple languages, biology, etc, I would happily use it. But I'm not aware of one - are you?

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.

Not OP but I've been thinking about this a lot (like everyone ha) and I think my answer is, yes?

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.

Maybe read the whole sentence?

Booleans as a Service

I feel you. That's been my life for a few years too.

Insurance and property taxes will never decide to occupy the house and force you to move from your home despite being willing and able to pay.

But you and I and everyone else here knows about MIT and can probably list a few major breakthroughs that came out of MIT... what's the name of your major public research university?

Most of what you've said is true, but also largely unrelated to the content of the article, which is about funding research.

> Why? Because they hunt a singular monster in professional software development: complexity.

I love this sentence.

Really? I'm pretty unimpressed. I hope I would do better and "roll with it" more if my kids did that to me. Maybe I overestimate myself.

And they, already, don't have qualified immunity while they're doing so. They are also already disallowed in many places.

> $65 is the cost of one or two fast food meals.

You mean for a family... I hope?

Is there any internal data on where students are going instead?

> The only way I can rationalize that so many people refuse to believe this is happening is that they are on the seller side and not the buyer side of engineering labor. This means they have blind sides to the buyers view of the market (some sort of information asymmetry), and secondly they exhibit cognitive dissonance to protect their self-esteem as a seller.

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.

Span of control is quite different from direct report.

Because the data shows exactly the opposite?

https://www.businessinsider.com/ai-isnt-killing-software-cod...

You can't make this shit up.

Directly from the dev of that game, who - since so few successful games have been released with Godot - often has random people point to R2V as an example:

> this game is far from being the "Godot 3D Showcase" game since I hardly even use normal maps and most of the assets are just low-poly shapes without any modern techniques (like PBR or photogrammetry)

So... One sequel that was a guaranteed success from day one, using any technology?

Slay the spire is also one of the least demanding games, in one of the least demanding genres, for a game engine. In fact the devs specifically pointed this out in their article a year or so back when they discussed testing Godot for viability.

Meanwhile, if you have more than 32 or so colors in a palette swatch, the color picker becomes permanently unusable for your project.

Godot is so driven by whatever sounds neat to work on that it has three completely different rendering systems, all buggy and mediocre. At least two shipped tilemap systems, one deprecated. And several systems like its autotiler where the community standard is to never use the built in one and to always replace it with a well known, much better add-on, and then to have to remember to avoid all the built in UI nudging you towards the built-in one.

Such a weird foundation for a project. Tons of hype but not a lot of successful games relative to usage.