512 karma · joined September 29, 2013
My intention is to work on news clustering and summarization. So far just by using some "clever" prompts I have been able to generate some pretty good news summaries and I have not started clustering yet. But, I have used GPT 4 so far and my educated guess is that soon enough I will hit some quality / cost limits. So, fine tuning a Llama 2 model with (hopefully) small datasets to improve costs and quality on my specific tasks seems like a reasonable path forward.
Does that make sense? Thank you for your answer!!!
It's hard work but it will pay off both for you and your near ones :)
So I guess when Zuck talks about security that doesn't include privacy.
Make sure you fill your life with meaning and love. The rest is not as important. Recognition comes and goes. And even if it stays, it will lose its shine fast enough.
PS: And as a Jesuit once said, stay humble and you won't tumble :)