I mean a couple of websites will claim 1.6gb ram on my device, what would an LLM model cause across millions of devices, when nobody even wants to use it

Google is historically terrible as a product company (and has succeeded in spite of that) As their technical innovations become less of a moat (we're already there) they won't be able to win on engineering alone (they are no longer winning on engineering alone)

They are releasing AluminumOS with their Googlebooks, which is a AI forward OS. If its good or not we have yet to see.

  > Why would I build my little web-apps and backends in the cloud when I can run things faster locally?

Folks that are interested in a way of doing work locally that doesn't suck, but which integrates LLMs, may be interested in [Barnum](https://barnum-circus.github.io/). The TLDR is that it's a programming language whose frontend is a DSL in TypeScript that is well suited for managing async and parallel work, focused on control flow, from which it is easy to invoke LLMs, and which is easy for LLMs to write. I use it to autonomously ship a very large number of PRs.

> why Google which has both Gemini and Android can't figure this out,

Not the first time an incumbent has four aces in hand and appears to be entirely unable to make anything of it.

> and if there are lessons to draw from that

Lesson 1: doing shit is hard

Lesson 2: money rules so milking the cow wins over taking the slightest risk

The only lesson I'm taking away is that we are still very early in the AI era. AI workflows look entirely different today than they did 18 months ago and I wouldn't bet on them looking the same in 18 months from now.

If you're not going to give Claude access to anything on your machine, why are you using Desktop instead of web chat? (Real question, I don't use these much!)

If you are, obviously you need the VM.

Probably because they vibecoded it

Anthropic has pretty consistently been shitty about how they roll out their software. Extreme lack of engineering rigor and thoughtfulness.

The answer is probably as simple as "no one thought not to do that."

---

I know different people work on these things so I can't do more than guess about how engineering culture cuts across teams, but given the sheer amount of carelessness and sloppiness in Anthropic's software I have to imagine they're burning investor money in training and inference because the code to do it is as bad as the rest of their software.

It kind of does though. If you want to use the product they'll need the sandbox ready.

Rule 1 with making number go up is you eliminate friction at all costs. The user's hard drive is free to you, so there's no reason to gate a feature you want them to use based on that. 98% of them will have no idea you're foisting garbage on them.

It was on my machine at least, I remember I had to do an additional install to activate that tab...

> Claude Desktop spins up a VM without no way of stopping it

I frequently make this error when I talk. My brain thinks of different ways to phrase what I want to say, but when I speak it starts with one and finishes with another. The result is almost always wrong in the way the title is, ie some variant of a double negation.

Sometimes it happens when I type, though I try to read it multiple times so often catch it.

All your RAM are belong to us

This question is answered by the post? There is reportedly actually no way of stopping it happen. Perhaps the poster had a brain fart while typing it. Maybe they speak a different dialect of English from you.

Op is nitpicking on the poorly written title. I came here to find that comment :)

I agree. Why is this a problem?

[dead]

They vibecoded it, and admitted as much. Once it was able to self-vibecode, that's all they did. That's why it's written in React and uses gigabytes of RAM as a chat client.

I uninstalled it because I have no need for Claude Desktop and there’s no way to keep the 10+ GiB VM image off of my machine

I'm with you. I have the Claude web app pinned as a PWA for quick queries, and then use the CLI for everything project-based.

I did consider experimenting with the Routines feature on the desktop app, but I'm leaning towards whipping together something with cron. I saw another poster here who has a daily PR summary routine that I think would be handy, as I have quite a few repos where I'm a sporadic contributor but would like to keep tabs.

I thought they were all in on agentic coding? They are probably just building at a surface level with only an eye towards shipping, without considering the impact of all the changes. I've seen less and less coordination between engineers as well under that model. If that's the case (Claude Code is this way). it is sort of what you get, no matter the rhetoric about "make sure to review all your changes!" It's always trade offs.

It is surprising that the Claude web app lags pretty easily when using either chromium or firefox on ubuntu linux. Chats that delay my laptop work without issues on my ipad or iphone using the app.

The web app is definitely a bit of a problem. IF there is a native app on desktop or if claude cli is much faster, i haven't tried them.

Guaranteed nobody is reading the code being merged in. It's vibes all the way down.

[dead]

There are lots of good answers in this thread but I think it's because they are AI companies and not UI companies. When you look at tools like AnythingLLM, OpenCode, pi, etc. you see all kinds of different interfaces, and while they might make disagreeable choices at least they do it with intentionality and direction.

They're some of the only new UIs to be made in the last decade. Almost everyone else stays in the browser (or something close like electron- claude code is actually mostly written in React, they couldn't get far from web dev). The problem is they need to interact with the local filesystem, and not many people have built apps for such a wide range of devices in a long time, and of that small talent pool I bet most are corpo coders- moving too slow and to focused on "the right way" to actually ship more than detailed Jira tickets. They also don't have time for stable releases because competition is so fierce.

But I almost always think of things from a talent-pool-first perspective. Perhaps there are actual technical issues like what Boris was referring to.

They are dogfooding their products like you wouldnt believe

They are releasing at breakneck pace, it's pretty funny how vibed their products feel sometimes

Many people will say it’s because of the slop. I think it’s because they have no product vision. The roadmap is pretty much a random walk, which combined with the velocity of agentic coding is like digging a moat with atomic bombs.

> Why are the UIs of the AI companies all broken in multiple ways?

Because they're vibe-coded ultra sloppy code. And it really shows.

Dogfood

No one left who could fix anything here by hand. Being able to handcraft compelling desktop apps and their plumbing is not a marketable skill anymore.

Mythos, Fable, please do the thing with the VM. Make no mistakes.

They are moving at breakneck speed deploying on scales most of us can't even imagine. They are working in a space that's completely unexplored where getting information as quickly as possible is preferred above iterating on some feature until it's "done" while your competitor has released fifteen other features, all sucky, but one of which turns out to be a killer and makes a billion bucks overnight.

Incredibly insightful. Not everyone speaks English as a first language. On top of that, the title is not ambiguous.

Wsl2.0 is literally a Linux vm built into windows. I imagine some people are using that.

Are you sure they're not using WSL2 (which is Linux, not Windows)?

I mean I’m using coding agents on windows, because I’m not just going to learn a whole new operating system just to make robots write code for me.

I want tools that meet me where I’m at, not tools that demand I change up my entire UX to interact with them.

The assumption is not “what’s wrong with Windows that it doesn’t work with <technology>,” more “what’s wrong with <technology> that it doesn’t work with Windows”

Why wouldn’t you want your thing to be cross platform

There are some English dialects with negative concord, meaning that to form the negation of a sentence, you negate all negateable words in it