Mauve 👁💜 @mauve@mastodon.mauve.moe

@okdistribute Unsure about all languages. I find even with just JS the thing is sitting at around 3.5 gigs.

I'm just so used to nano taking less than a mb and booting up instantly :P

Fortnite is like Garry's Mod if it looked good and had a default set of game modes that were well made

I get I'm a weirdo but it still boggles my mind how much RAM vs code gobbles during normal operation. Especially when you have a "language server" running. This rust one is taking like 2.5 GB for a ~200 line file.

Every time I see my system chug to a halt when I add a new token to the tree for it to analyze I keep wanting to go back to nano. 😿

@yosh Yeah I saw one of your blog posts about it which was neat. I'm gonna try using tokio streams for now and just bend whatever else to their interface

Say what you will about Node.js but having async streams be a standard part of any io APIs makes it pretty easy to mess with different data sources and sinks. I'm trying to do something similar in Rust and it appears there's a billion ways to do io.

One of my clients needs #Rust for some #p2p stuff using #veilid and #iroh and I'm gonna see how far I can get with just telling #Phi3 to make changes to the code using continue.dev :P

My guess is it's gonna suck, but we'll see.

@hermeticvm@convo.casa What are the main issues you have with them? I found Dolphin and Nautilus pretty much got the job done when I used them. Portfolio hasn't worked as well for me since it's more for mobile. Right now my XDG desktop portals and KDE themes are kinda fucked since I'm building a wayland desktop environment from scratch, but with the standard GNOME/Plasma setups it seemed fine.

Then again I am usually in the command line anyway >:P

The complaints about Linux needing way too much command line tinkering are valid.

Luckily for me I like tinkering in the command so much I use my "file browser" like twice a month at this point and do the rest with bash.

Just finished playing Stray. Ending made me cry NGL

@ryanramage yeah feel free to follow the main repo: https://github.com/RangerMauve/mind-goblin

Gonna push my latest version in the next week or so.

@ryanramage All within a few seconds with as little power or ram usage possible.

@ryanramage I'm giving the agent a tool call to use LLaVA to "see". I'm going to allow it access to the screen, an image file, or the camera.

I want a flow along the lines of:
- "Hey, save this text as a reminder for later"
- tool("see", "extract the text from the image") => take a pic and run through llava
- tool('save', "{summarized text}", ["reminder"]) => save to local database for later
- response: "Saved!"

- "What was the last reminder you saved?"
- tool('load', 'reminder', {limit: 1})

Ordered a glasses mounted camera to feed to my local AI when I'm on the go

@starshine @delta Oh my bad! Misunderstood the last part.

@starshine @delta is doing some cool stuff. I think grant funding has been useful for getting these protocols set up.

I also use Matrix on the daily and it fits the criteria.