It's more or less an abomination. Dropping the frameworks and js jazz you could have most of the features of either of these sites served in the kb range. It would save millions of dollars in electricity, billions in infrastructure, and be more secure.

Yes, it's absolutely the frameworks. That each weigh <100KB. Definitely frameworks :D

Edit:

I don't even know where you lot get these numbers from nowadays, smh.

Just checked, in Slovakia, google.com is 1MB (compressed) total with cache disabled. 400kib of those is my own extension that I installed which is counted among the 'loaded scripts'. Loads in 400ms, blink of an eye.

Framework rants are completely detached from reality, as always.

What else would it be? Google is a picture, a text box, and few buttons. Not exactly a lot of HTML

It's replying to this:

> 10MB for the Google Homepage!

Even 1MB is way too big for "a picture, a text box, and few buttons."

I could see some applications for it. But they are selling it as a mode of transportation?

Why use zig when you can use odin?

Qwen3.6 27b is a really strong model.

Yeah but that strong?

Yes that strong. Its only lacking in context length, but it's not that small there and it gets caught in circles more often then say a 1t parameter model does.

That's why a lot of people have been freaking out about local LLMs since april. There's finally a decent model that runs locally on a GPU or two that can do agentic programming at a reasonable enough tokens per second.

> it gets caught in circles more often then say a 1t parameter model does.

I've found that the Q5+ quants are less loopy than Q4. Still not perfect, but noticeably better.

> reasonable enough tokens per second

The speed has been amazing. I've been running the recent llama.cpp MTP branch with an uncensored variant of Qwen3.6-35B-A3B on my RTX 3090 over 170 tokens per second and it was able to turn a buffer overflow into a reliable shell exploit in just a few seconds (with reasoning disabled). Still a bit loopy though. Hopefully, the Qwen team will pay more attention to those looping issues. It feels like their models are especially susceptible.

Is that on a single 3090? I need to change my settings it sounds like

Yes, single RTX 3090 with this model https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-h... following these https://huggingface.co/havenoammo/Qwen3.6-35B-A3B-MTP-GGUF instructions (should add "-j 8" to last cmake command for parallel build) and llama-server with --reasoning off

Note that the MTP PR https://github.com/ggml-org/llama.cpp/pull/22673 is still under development, so things might be broken.

You see we socialize the losses and capitalize the profits. Works great for everyone

You’re absolutely right! I shouldn’t have launched the nukes. Would you like to learn more about nuclear safety?

Yea it's vibe/agentic coding. That's what about half of the current jobs are right now. It's really sad. Saw a vibe coder job today, 20bucks an hour

Interesting. I saw contractor rates dropping here too. The ones I saw recently were at pre-pandemic levels so from 6 years ago. The large increase in cost of living from that time makes it even worse. The funny part is that the skills and experience that are being asked for are at a senior level. So I guess that would be senior level vibe coder at junior rates?

Management literally doesn't realize that you can't exactly vibe code a serious project? Maybe they just don't care and it's an experiment. Super low risk I guess, depending on the city they might pay the floor cleaner more than that.

Laid off ai workers are cheaper. I saw a job posting for a vibe coder, 20 bucks an hour.

I don’t believe anyone trying to hire 20 bucks an hour for vibe coders is a serious employer. You’d make more money being a barista in some cities or a substitute teacher.

Sure, but they probably aren't living in those cities. In-person $20/hr in expensive city vs remote $20/hr in cheap cost-of-living area.

It's out there. Maybe it's not serious but it is kind of a weird thing to post on multiple job boards.

If they tried to lock down local models more people would use them. They would also have to take down a few us companies in the process who would go down fighting for certain.

Basically "screw any part about employees working together do what I say fast". What a shame. I love the AI bros who think utopia is coming, 4 day work weeks, etc. more like "get screwed, work more, for less, in worse environments".

The code and product will turn to shit, and the company won't be able to extract itself from the mud.

Employees tasked with doing 10x more work with less help don't even have to feel bad about it happening. It'll also create employment opportunity in disrupting their old employer.

These companies are willingly signing up to become IBM.

It looks like they are switching to ai only code review. It will go to shit for sure lol

AI code review with code ownership is fine. If people have to build working software, they'll do that, or you hold them accountable. Modern software dev at most organizations has far more code review than is needed outside of soc2 purposes.

Of course, once you have a big incident, then the value of more human review becomes obvious.

It's an important touch point for other code owners. I guess if no one is looking at the code anymore why even do an AI code review. It's kind of theatrical?

I seriously don't know how people are working like this now. I'm on my ass looking for work and in the last month it feels like everyone has completely lost their minds.

> I love the AI bros who think utopia is coming, 4 day work weeks, etc. more like "get screwed, work more, for less, in worse environments".

Where do you find those, seriously? That might’ve been the case a couple of years ago, where they’ve gaslighted people and played on their feelings, but now gloves are off. AI bros are literally posting about lack of sleep, dopamine hits, vibe coding on a toilet/walk/watching TV, FOMO is through the roof everywhere, prophesying doom of SE, etc.

I've seen it on here even.