I’m sick and tired of the Capitalist religion and all their fanatic believers. The Western right-wing/‘liberal’ population are the most propagandised and harmful people on Earth.

Currently they all repeat the same nonsense about world affairs, and none of them have actually sat down and researched what is going on, and why their leaders/media are lying to them. Ex. here is what really happened in and around the Ukraine project: https://www.youtube.com/playlist?list=PL6-hcqTF_eSc6PIdk3QIwtoxtTK1wr30y

Stop supporting the Epstein Class by giving in to their lies about other nations !

  • 0 Posts
  • 35 Comments
Joined 3 years ago
cake
Cake day: June 8th, 2023

help-circle
  • Sims@lemmy.mltoSelfhosted@lemmy.world•mwmbl
    link
    fedilink
    English
    arrow-up
    1
    arrow-down
    8
    ·
    2 months ago

    Don’t mind the anti-ai votes - people are frustrated af. Your p2p sharing mindset are great, thank you !

    A few ideas from the top of my head: Git service ?: Radicle is a p2p distributed Git service. You can seed your fave projects.

    Deeper search ?: Yacy is a mature/advanced distributed p2p search engine, but I don’t know how it compares to mwmble.

    [AIT] (AI topic, tag rule for this sub) Inference service ?: AIhorde is a distributed p2p inference network where you can help out with a smaller machine/model and draw on the network when you need large models. Works with pics/txt. Not sure how its going though.

    …Oh, and perhaps skip Claude - Anthropic et al. are Fscist Ucks, and for 90% of your projects, you get 90% the same quality for 90% reduced price elsewhere (claimed on a ‘trust me bro’ basis ;-) ). aihorde sounds like something for you and its self-hosted.



  • Damn, are we watching live growth of digital Fascist cancer here ? We all get spammed with this worthless, non-special OS in every information outlet, YT, SN’s and other for-profit junk outlets. People are getting paid to keep posting about it everywhere.

    Pretty disgusting to see how rich Pschos think and act, and pretty disheartening to see our ‘non-enshittified’ world be enshittified in front of our eyes! Enshittification = Capitalization.

    Boycott Omarchy by all means necessary, and help not spreading this Capitalist/Fascist cancer project anywhere.


  • USB is not good as its a huge bottleneck, and most external accelerators are (was?) passive without any ram onboard. Google Coral was/is ‘passive’ in that it resends all data all the time over the interface - Npu<->system ram.

    I were going to recommend these: https://shop.geniatech.com/product/m2-ai-inference-acceleration-module/

    40tops, ARM + Npu + 16gb ddr4 - a whole little Inference computer on a NVME interface. Kinara (Ara240) is a homegrown Chinese chip. While they are usually selling b2b, you can ask anyway. YMMW atmo. Also note that some NPU’s are less efficient at llm’s vs vision.

    …but I see that they also rose almost 4* in price since I asked for, and were offered the price of 179$ ~7M ago, which is already a long time in this space. Not sure how the current ~650$ stacks up to the rest of the offers out there at the moment, but these small active AI systems on NVME are a great way of upgrading a piss-old server, enhance a new cheap 4-8port NVME mini-NAS or similar, and there’s no clear bottleneck in the interface.

    Look for something like this instead of Nvidia Coral and other ‘passive’ sticks, that are all - imho - overpriced/underperforming.



  • ‘$1 HTML’

    Why tf do US/western kids always think its okay to monetise everything they touch !? Just make something that are free because it doesn’t cost you anything, because it was fun, or because you want to share with others, ffs ! This is the same annoying ideological mindset as new game-programming kids that have setup ad-servings in their games before they have a gameplay, assets or any other working code.

    You managed to enshittify your entire ‘fun’ project before it was even released. I think that is a horrible, childish, capitalist mindset/project, and I don’t think sharing/open-source people would want to support your selfish for-profit kid-project - ‘fun’ or not…



  • Sims@lemmy.mltoSelfhosted@lemmy.world•just realized whoogle is dead now
    link
    fedilink
    English
    arrow-up
    4
    arrow-down
    61
    ·
    4 months ago

    You should look into why so many people isn’t angry at Russia and are now blaming US. Your anger is exactly how US manufactures consent for all their wars, and it keeps you from discovering why people doesn’t hate Russia and even blame US/the west for starting it. They simply create a lynchmob - an echo-chamber - where people won’t listen to counter points bco anger. It works.

    ALL US moral attacks on their ‘enemies’ (Ussr/Russia, N.Korea, China, Iran and oc ALL nations that wont be dictated how to live by the US elite) are such manufactured BS, and it all runs on the anger they create in people, and from there, they can do what they want in the name of ‘war against evil’. It will continue as long as people keep believing US and their controlled information bubble.

    Give it a try, just read all the headlines in this list: What really happened in Ukraine?

    If you couldn’t, or you still refuse the idea of foul play after reading - they got to you…









  • Compute prices are not going down. If you want a budget friendly compute, then you may need to look for NPU’s. They are slower, and is unfortunately also getting more expensive pr TOPS. Electricity prices in the West are going up as a low output gets bought up by datacenters instead. The newest GPU’s are more efficient in re. to power pr Top, but they are not budget friendly.

    I have not seen a recent comparison of GPU vs Npu; TOPS vs price vs power consumption, but @ aliexpress, I saw a small 40 TOPS Npu as a nvme stick with 16gb ram that draws 10 watts, or so (search for ‘ai accelerator nvme’). This little thing can scan files 24/7 and your i5 can help out in peaks. Afaik you can run a distributed model that also runs in, and uses your i5 memory/compute, so if you max out i5 memory, perhaps the combined compute is enough for a larger model ? Maybe a few Npu sticks can work together on the same model ?

    Alternatively, you could look for the next version of a Huawei gpu card (first had baby kinks afaik), or one of the other upcoming producers from China. They’ll come faster and faster, but are earmarked for local consumption first.

    Another suggestion is to buy one of the old P40/80 (from the ‘pascal’ chipset, I think) (or was it k40/80 ??). They should still support a descent range of modern quantization needs and often have 24gb ram. A refurbished miner card cost around 50-70$+ - cant remember exactly tho.

    Lastly, you could try something different. If the i5, with enough memory, can run a large model slowly, you could add a dedicated KV cache, so most of the tokens won’t need to be recalculated. Memory and bandwidth are the most important here, but any old server could be upgraded to be a dedicated KV cache server (might need a network upgrade tho!).

    Anyway, Ideas are easy and cheap. If I were you, I would ask an AI for a little python app where you can add a product and it returns a graph where it compares with other products and show optimality over time given prices/power and Tops - Gpu vs Npu. Good hunting…





  • I don’t know, but allow me a soft rant about the ‘distributed’ part;

    Couldn’t selfhosters try to ‘organize’ and share these burdens ? Why pay for external cloud backup, or anything, when selfhosters can just help each other storing parts of others backup. Then everyone have an automatic back-up.

    The tools seem to be there, but Its like there are all these super-skilled infra-structure selfhosters that know everything about self-hosting solutions, but they lack the self-organizing ability to sollve these typical - and a bit trivial, lets be honest - problems in a full p2p style. The result looks to be that all self-hostings solution above the threshold of an average individual selhoster, have to be done in the cloud, and everyone is ‘siloed’ in their own mini data center.

    But, with existing tools, AI and a little imagination, it shouldn’t be too hard to ‘organize’ a little (though here) design a self-hosting p2p backup solution from existing tools. …or a solution for most of the other cloud services we still rely on…

    But maybe its something else ? …to me, it just seems unnecessary for a high expertise self-hoster community that - when combined - are an absolute gargantuan cloud-service infrastructure …to still have such basic capacity issues (no offense meant to op, or anyone!), and still have so high reliance on cloud services. Seems odd to me…