Do you understand StockFish filled the gap only after using NNs as well in the evaluation function? And that was a direct consequence of AlphaZero research.
Local LLMs are terrible compared to Claude/ChatGPT. They are useful to use as APIs for applications: much cheaper than paying for OpenAI services, and can be fine tuned to do many useful (and less useful, even illegal) things. But for the casual user, they suck compared to the very large LLMs OpenAI/Anthropic deliver.
I don't think local LLM's are being marketed "for the casual user", nor do I think the casual user will care at all about running LLM's locally so I am not sure why this comparison matters.
Yep, unfortunately those local models are noticeably worse. Also models are getting bigger, so even if a local basement rig for a higher quality model is possible right now, that might not be so in the future. Also Zuck and others might stop releasing their weights for the next gen models, then what, just hope they plateau, what if they don't?
they are the only thing you can use if you don't want to or aren't allowed to hand over your data to US corporations and intelligence agencies.
every single query to ChatGPT/Claude/Gemini/etc will be used for any purpose, by any party, at any time. shamelessly so, because this is the new normal. Welcome to 2024. I own nothing, have no privacy, and life has never been better.
>(and less useful, even illegal) things
the same illegal things you can do with Notepad, or a pencil and a piece of paper.
