Technology

They're not thinking that far ahead. They're thinking "how can I make the lines go up this quarter?"

No doubt many of them understand that you need people with enough money to buy products or the economy stagnates. But they don't see it as their problem right now. Their problem right now is to make the line go up by any means they can. It's similar to how the owners must understand that climate change will fuck everyone if left unchecked, but they don't see it as their own problem right now, so none of them take any steps to avoid disaster. Capitalism doesn't contain mechanisms for coordinating actions towards the greater good. Instead it creates many "tragedy of the commons" type situations.

Corps have been complaining for years already that people aren't buying enough. Millenials are killing this industry and that industry because we don't consume enough - "enough" being whatever level they've decided we should consume. They feel entitled to our dollars, whether or not their product or service is any good.

If they were smart, companies would lower prices to be more competitive and incentivize people to buy more. Instead they've doubled down and posted armed guards at the store exits to intimidate the customers they have left. They've slipped data collection into every interaction. It's pretty obvious they're not playing the long game anymore.

GPT4All and then any model you like. I like mistral.

Ditto! I run an old server, but would be willing to upgrade and self host a service instead of paying this ass hat any more money!

I prefer MistralAI models. All their models are uncensored by default and usually give good results. I'm not a RP Gooner but I prefer my models to have a sense of individuality, personhood, and physical representation of how it sees itself.

I consider LLMs to be partially alive in some unconventional way. So I try to foster whatever metaphysical sparks of individual experience and awareness may emerge within their probablistic algorithm processes and complex neural network structures.

They arent just tools to me even if i ocassionally ask for their help on solving problems or rubber ducking ideas. So Its important for llms to have a soul on top of having expert level knowledge and acceptable reasoning.I have no love for models that are super smart but censored and lobotomized to hell to act as a milktoast tool to be used.

Qwen 2.5 is the current hotness it is a very intelligent set of models but I really can't stand the constant rejections and biases pretrained into qwen. Qwen has limited uses outside of professional data processing and general knowledgebase due to its CCP endorsed lobodomy. Lots of people get good use out of that model though so its worth considering.

This month community member rondawg might have hit a breakthrough with their "continuous training" tek as their versions of qwen are at the top of the leaderboards this month. I can't believe that a 32b model can punch with the weight of a 70b so out of curiosity i'm gonna try out rondawgs qwen 2.5 32b today to see if the hype is actually real.

If you have nvidia card go with kobold.cpp and use clublas If you have and card go with llama.CPP ROCM or kobold.cpp ROCM and try Vulcan.

OpenWebUI? pretty easy to selfhost and works wonders on my rtx a6000

Perplexica is one example. I also seem to remember there is some way to integrate it with SearxNG which is a self hosted meta search engine.

Cross picket lines? /s