Hmm : hmm? Hmm!

You are talking locally, right? Like when you have a motherboard GPU and a vendor GPU? What kind of frznkenstein hardware do you use that can even handle that sort of mismatched hardware?

I was asking Kimi-K3 that very question and one of the possible things was a local model for VTT. I think looking at specialised models like that might be the best use case.

Another one I was thinking about last night was local semantic search through embeddings. I’m not sure if that’s actually feasible, but it would certainly be useful for when you have terabytes of PDF.

Yeah, I can see that but it’s horrendously slow, I find. I tried a 3.8 online and I just dont’ like the way it works, overall :( It goes on and on and on and never stops to ask despite that being one of my main rules.

Oh thank fuck. I thought I was going crazy… My first attempt at local models was a Qwen. A base model. I swear to god all I said was hello and the thing started and never stopped. I guess that’s what a filibuster must be like? It was both amazing, yet terrifying. I’ve a bit more xp now, but yeah Qwen and really really thinky, dear gods ! My colleague got himself an abliterated one and just leave it to run overnight trying to pentest shit in his home network, but I guess I prefer something a bit more hands on, myself.

My colleague was laughing his head off all morning. Never a good sign when we start laughing a lot, in our office :,D

Hopefully if it’s the Director of Security telling me to do it, I’m not liable, right?

It sure is back breaking work, but someone gotta do it, boss !

Damn it, I had to see your post to realise it was, in fact, not.

Nice! I’ve been wondering why this wasn’t the default distribution mode. Big ass files that a lot of people want seem like a good candidate for torrenting. I’ll have to check it out.

Preventing IP exposure? Finally I can sleep at night!

That sounds like easy to remember password generation