Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Desktop spawns 1.8 GB Hyper-V VM on every launch, even for chat-only use

github.com

Post reply on HN
Print view View original

101–110 of 324 posts

Re: Claude Desktop spawns 1.8 GB Hyper-V VM on every launch, even for chat-only use

#101

Post by rbalicki »

z2 wrote: post #14

This all feels like a race where the model companies try to solve doing work locally in a way that doesn't suck, before the major operating systems companies figure out AI integration into their OS that doesn't suck. It also makes me wonder why Google which has both Gemini and Android can't figure this out, and if there are lessons to draw from that.

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.

Re: Claude Desktop spawns 1.8 GB Hyper-V VM on every launch, even for chat-only use

#102

Post by didericis »

fasterik wrote: post #53
inigyou wrote: post #40

Earlier quoted context omitted.

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.

Not only did they decide to write a terminal application in React, but it's 500K lines of code. It's strange because I'm sure Claude is capable of writing a decent TUI in C. It says a lot about the engineering culture at Anthropic, at least on the software side.

Had to make a decision for a TUI I'm working on and opted for curses rather than something like textual. If I wasn't using an LLM to do some of the plumbing I'd probably have used textual to avoid the inconvenience.

There's a lot of opportunity to leverage LLMs to make codebases less bloated and less reliant on complex but human user friendly dependencies that not many people seem to be taking advantage of.

Re: Claude Desktop spawns 1.8 GB Hyper-V VM on every launch, even for chat-only use

#103

Post by drummojg »

caycep wrote: post #93
ddarolfi wrote: post #21

Earlier quoted context omitted.

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

"What do you mean, an Aluminum Falcon?!"

"WHO'S 'THEY?????'"

Re: Claude Desktop spawns 1.8 GB Hyper-V VM on every launch, even for chat-only use

#104

Post by what »

SpaceManNabs wrote: post #77
tkcranny wrote: post #20

I’ve stopped using Claude on the desktop, just because of how slow the app is to start up and interact with. It’s an absolute clunker; I’m mystified why they can’t ship something that works well given their rhetoric about ai.

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.

All of the LLM web interfaces have serious lag when typing after a few turns, at least on iOS safari. I’m talking seconds to start rendering input after typing or when it needs to line wrap the input.

Re: Claude Desktop spawns 1.8 GB Hyper-V VM on every launch, even for chat-only use

#107

Post by reactordev »

esseph wrote: post #74
elxr wrote: post #59

Earlier quoted context omitted.

I'm obviously not just prompting agents for everything. What are you on about? Why would I build my little web-apps and backends in the cloud when I can run things faster locally?

> Why would I build my little web-apps and backends in the cloud when I can run things faster locally? Because in a lot of companies, your machine is actually just a portal to a remote desktop.

The Venn diagram of “Corporate” vs “Company” definitely has VDI and ServiceNow at the center of it.

Re: Claude Desktop spawns 1.8 GB Hyper-V VM on every launch, even for chat-only use

#108

Post by jstummbillig »

newobj wrote: post #99
z2 wrote: post #14

This all feels like a race where the model companies try to solve doing work locally in a way that doesn't suck, before the major operating systems companies figure out AI integration into their OS that doesn't suck. It also makes me wonder why Google which has both Gemini and Android can't figure this out, and if there are lessons to draw from that.

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)

How are Google products anything but outstanding in their categories? What are you comparing to?

Re: Claude Desktop spawns 1.8 GB Hyper-V VM on every launch, even for chat-only use

#109

Post by antonvs »

tom_ wrote: post #75
echelon_musk wrote: post #57

Earlier quoted context omitted.

There's no dialect of English in which this is correct.

That could be true, but I don't think I'd bet on it myself.

Good call. The original comment is making fun of the incorrect double negative. “Without no way” means there is a way.
Post reply on HN