It depends on what you mean by “relative responsiveness”, but you can absolutely get ~4 tokens/sec of performance on R1 671b (Q4 quantized) from a system costing a fraction of the number you quote.
It depends on what you mean by “relative responsiveness”, but you can absolutely get ~4 tokens/sec of performance on R1 671b (Q4 quantized) from a system costing a fraction of the number you quote.
It is indeed called a refund by the IRS and all tax professionals. The person(s) attempting to correct your use of “refund” are wrong, but they were probably trying to make the point that giving a lot of extra money to the government interest-free is not a smart financial idea.
I used Kagi for a few months but was turned off by the fact that they developed an entire production line for making tee shirts vs. spending more time on making their service better.
Their CEO also doesn’t understand personal boundaries (or privacy laws, if he truly believes everything he says in these emails): https://discuss.techlore.tech/t/kagi-ceo-s-recent-controversy/8119/2
I went back to DuckDuckGo.
Yeah I definitely get your point (and I didn’t downvote you, for the record). But I will note that ChatGPT generates text way faster than most people can read, and 4 tokens/second, while perhaps slower than reading speed for some people, is not that bad in my experience.