Natanox

[Insert your GitHub Link Here]

lol

[cite: 3, 4]

??

Is this whole text LLM generated and you just copy-pasted everything including the (now unlinked) citations and the orders the machine added to the text without double-checking?

Phew, to run such a model - even just 27B quantized - at a reasonable speed requires some serious GPU Power.

Best thing I have is a 7800 XT 16gb (so ROCm it would be), don’t think that’s realistic and I’d rather invest the necessary amount of money for new GPUs into sth. more useful like a small electric vehicle than a slop cannon 🥴. Happy to hear actual useful things can be retained after the bubble finally crashes though. Oh please, let it crash tomorrow… together with the housing market…

Interesting. I tested ChatGPT and Mistral and oh my god, ChatGPT was abysmal. Hallucinated way harder. Mistral is okay if being used on highest settings.

Did you create an account with Mistral? Without it they only expose a low-end model to the web, which isn’t properly declared last time I checked. Can be the free plan, I guess they just want to avoid their infrastructure being hammered.

Personally all those Silicon Valley pricks can offer whatever, I don’t even have a Google account anymore and couldn’t be happier with that. Not saying Mistral is optimal, but at least they’re not part of the current US swamp. And I at least somewhat believe they actually read the damn GDPR. I’m totally fine with it not being the “cutting-edge”, especially given the cutting-edge cuts straight through culture and people’s lifes on purpose and with maximum brutality, and I seriously liked to see their image generator being way worse as well as Mistral refusing to open sites that banned it in the past (if they changed that behaviour please let me know). Not to mention their site isn’t even remotely as infected with trackers and other junk as the others, at least that’s what I’ve read (forgot to bookmark that hackers’ analysis I’ve read a year ago unfortunately).

Quick mention about Chatbots: In general they can be useful if you already have a grasp on something, so you can detect potential nonsense better. Additionally they can act like a drug especially on lonely people, and any company tries to sell them to you as awesome code generators. Yet Mistral AI already generated an answer to me telling me to dd my encrypted root hard drive for a speed test, even doubling down on it being safe.

Not saying they can’t be useful for OP. Just that they’re like a handheld circular saw*, a powertool better only used by people who already know sufficient basics about wood.

*where the salesman got rid of the safety handle and tells you to “just let it go on its own”.

That’s the resolver’s job, Wireguard absolutely reconnects asap if the connection’s heartbeat goes out. You in your case got Cloudflare to make sure it can connect somewhere.

The only way to truely serverless’ly find each other when both parties got dynamic IPs would be IPv6 multicast (such as via Librecast). Not just is that still not supported by the network itself a lot of times (sadly) but I doubt any LLM on this planet would implement it correctly, way too niche. Any other way leads through some DNS resolver or third-party service (like Cloudflare) or a network such as Magic Wormhole.

It’s fine if the Slopware works for you, but your arguments make no sense whatsoever. The only thing you’re currently doing is making enemies in the selfhosting community, not connections.

Lolwhat, no it doesn’t…? Did an AI tell you that?

You spin up a Wireguard server yourself (or use the one in many routers), point clients to that and be happy. The only “other” server in that chain might be a (Dyn)DNS resolver, and you could even self-host that one (and therefore also omit Cloudflare).