strix_varius

reason vibe coding specifically prohibits reading the generated code

Wait what? Are there rules to vibe coding now? Are we no true Scotsmanning slop now?

Some of the statistics in the article included audiobooks as reading. It seems like they must trigger at least a subset of the qualities of reading (like maintaining an imagined environment, parsing sentences and paragraphs into meaning, etc)

Eh, depends on what you mean by "implode."

Before the buyout (2021), twitter made $5.1 billion in ad revenue ($6.22 billion inflation-adjusted).

In 2025, it made about $2 billion.

So Twitter is now about 1/3rd of what it was (revenue wise) when purchased.

2-3 ICs

This is the real problem. If you don't have enough folks for a 4+ IC team then you don't have a team.

Yeah he's like the light side Elon. Happy with his life, his family, his choices. Content. Zen.

Buddy, read the context. I think you missed the whole point.

All x86 PCs sold by everyone are open and you can install whatever you want.

What exactly do you think an Xbox is? PS4 & PS5?

I’ll level with you – this is hard!

I'm getting tired of the monoculture where both articles I read and agents I code with speak with the same (annoying) voice.

Thought experiment: if you can solve a problem with 100 lines of dependency free code, or with 10,000 lines of code that depends on hundreds of things - which is better?

There's an obvious answer of course. And that is the direction that these effective senior engineers move towards.

This is exactly what the article is addressing:

But there is a correlation between output and LoC.

That is less true today than it ever has been, due to LLMs.

Good revision!

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.