It rusts under the rain

As long as it is still running you should be fine, but it’s better to keep your battery around 80%. There are tools that block the charge until you ask for a full charge when needed

Well it’s definitely true that you will have hard times getting true things from garbage. But funny enough, the model might hallucinate true things:)

You can train an LLM on the best possible set of data without a single false statement and it will still hallucinate. And there’s nothing to be done against that.

Without understanding of the context everything can be true or false.

“The acceleration due to gravity is equal to 9.81m/s2” True or False?

LLM basically works like this: given the previous words written and their order, the most probable next word of the sentence is this one.

Well, before SpaceX I looked at the space exploration program as a science enthusiast. The missions were rare but important for science. Then this dude came out of nowhere, saying he was about to save the Earth with electric cars and build a station on Mars. And for a moment it really worked. I genuinely thought he was a good billionaire. Then he completely loose his mind, start talking and acting like the worse moron of the universe, and I started studying his statements without the shiny distorting layer. He’s so full of shit it makes me sick. Most of the things he says is nonsense.

So I can’t tell why my brain works that way, but it does. Today I’m more exited by new ways to produce renewable energies on Earth than I am about rockets. That joy I felt for any SpaceX news slipped away.

My comment was just the realization of that. That was weird to be honest, but true.

A few years ago (already) I would have been sad and shocked. Now I don’t give a shit about SpaceTwitter. That douchebag managed to kill all the interest I had for space exploration, a topic I was passionate about for most of my life. He really is that kind of killjoy.

Well, I got a good news and a bad news.

The bad news is you won’t do shit with that my dear friend.

The good news is that you won’t need it because the duck is back.

Most of 7b-8b models run just fine in 4bits quant and won’t use more than 4 or 5 GB of VRAM.

The only important metric is the amount of VRAM as the model must be loaded in VRAM for fast inference.

You could use CPU and RAM but it is really painfully slow.

If you got an Apple Silicon Mac it could be even simpler.

That’s a nice hobby

I would suggest you to install a local instance of a LLM (mistral or llama3 for example) to widen your source of information. Go straight to Wikipedia instead of “googling” it if you don’t already.

Anyway, I didn’t know about kagi so I might take my own advice and give it a try.

Nice read. Thanks OP!

IMHO people just won’t give a flying fuck about it. Most people won’t even be aware of it.

They’ll upgrade when they’ll buy a new PC, just as usual.

Our Very Stable 4D Chess TwitterBoy Genius has become so fantastically effective in killing his brands.

First Twitter.com, then TwitterCars and the TwitterTrucks.

Will he kill SpaceTwitter too?

And what about TwitterDigger? Is this still a thing?

Hello,

If you only want to track the number of page views you can do something simpler.

On your website, add an empty image with a known name in the footer that point to your home server (no proxy needed if your website allows loading images from external site)

You should see the attempt to download the empty image in your home server logs. There are tools to parse your server logs for specific keys (I have Logstash in mind)

If you want to track anything else, just add another empty image linked to the website event you want to track.

I am interested in what tools are missing on Linux that exist on macOS?

• iOS development tools for starter.
• A good enough WebKit browser for Technical acceptance testing (GNOME Web is going better, but not quite yet)
• Visual Studio (The IDE, not the Editor)
• Quality of life Apps

macOS isn’t Unix and doesn’t contain Unix code

https://en.wikipedia.org/wiki/Darwin_(operating_system)

“Darwin is mostly POSIX-compatible, but has never, by itself, been certified as compatible with any version of POSIX. Starting with Leopard, macOS has been certified as compatible with the Single UNIX Specification version 3”

macOS also can’t just run all Linux applications. That’s nonsense. It doesn’t use the Linux kernel or its APIs and ABIs.

There are tons of ways to run Linux software on macOS https://www.maketecheasier.com/ways-run-linux-software-mac/

Now, can I talk to someone who actually knows what he’s talking about?

I do ML stuff on my Mac that even the most expensive RTX 4090 could dream of being able to do, because of a buttload of shared memory

As a developer I’ve been missing most of my tools on Linux, and the OS is just catching up.

Friendly remember that macOS is a Unix system that can run any Linux software, meaning that anything done on Linux can be done on macOS.

Proton makes Linux a perfectly fine gaming platform, with sometimes even better performance on Proton than native Windows…

Anyway Windows sucks, that we can agree on

If you think right wing extremists can’t be into gay furry porn…

TBF This is how luxury car manufacturers sell their options. Always have been.

Space Karen sells his false self-driving option for €7500 as a software option.

It is indeed. I’m switching to the instruct model to see if I can get better results for code and documentation.

Oh boy, I missed Mixtral GPTQ and only tried Mistral 7b

Currently downloading mixtral-8x7b-v0.1.Q4_K_M.gguf

Thank you!

EDIT: mixtral-8x7b-v0.1.Q4_K_M.gguf was to heavy for my Mac but mixtral-8x7b-v0.1.Q3_K_M.gguf runs fine AF

You should definitely try Mistral. It runs on a potato