41–50 of 63 posts
Doesn't this make the "AI" even less creative and more like full-text-search instead? What makes some data a "fact"? If everything is written in the training data, in the end, won't everything be treated like a fact? So the LLM will have 100% accuracy and 0% creativity.
"Hallucinations" are the creative aspect of LLMs, which is what they are more useful for- if anything we want more of them. We already have much simpler systems that search and regurgitate facts. We need more intelligent hallucinations that are consistent with and extend rather than conflict with the data.
We can control how diverse or creative output is via temperature. I am assuming that these new models could work at higher temperatures (i.e. more creative) while maintaining factual accuracy for things you care about. Or alternatively, keep the same temperature but have far fewer hallucinations (i.e. wrong answers).
Let's say I have a counter value, X = 100. I reduce that to 10. How can I phrase that in English?
"Value reduced to 10% of original value"
"Value reduced by 90%“
"New value is one tenth the original Value"
Using multiplication with a positive integer and saying "less" just seems incomprehensible when it flies by during a sentence and I can't stop myself from mentally saying "No", like Neo at the end of the Matrix when the three agents fire a volley of bullets at him down the corridor. "No, this sentence stops right here while I pick it apart"
Am I the only one that cringes at "10x fewer?" How do I multiply positive numbers and get something smaller? Is "1/10th" or "90% less" not better arithmetic? Maybe I should have done more gooder at math but it hurts my ears (eyes).
They are overloading "fewer" to mean division as well as subtraction. According to this logic "twice fewer" means "half as much".
More is addition, times more is multiplication (or 1 plus multiplication, oops).
I don't think anyone says "twice fewer". Or "twice more" when talking about quantities.
nit: I hate trying to work out what "10x fewer" or "10x less" mean. Let's say I have a counter value, X = 100. I reduce that to 10. How can I phrase that in English? "Value reduced to 10% of original value" "Value reduced by 90%“ "New value is one tenth the original Value" Using multiplication with a positive integer and saying "less" just seems incomprehensible when it flies by during a sentence and I can't stop mys…
The first sentence seems fine to me. The contraction much less so.
nit: I hate trying to work out what "10x fewer" or "10x less" mean. Let's say I have a counter value, X = 100. I reduce that to 10. How can I phrase that in English? "Value reduced to 10% of original value" "Value reduced by 90%“ "New value is one tenth the original Value" Using multiplication with a positive integer and saying "less" just seems incomprehensible when it flies by during a sentence and I can't stop mys…
Also the most direct translation is "value reduced by a factor of ten".
"x" means factor, "fewer" or "less" means reduced.
nit: I hate trying to work out what "10x fewer" or "10x less" mean. Let's say I have a counter value, X = 100. I reduce that to 10. How can I phrase that in English? "Value reduced to 10% of original value" "Value reduced by 90%“ "New value is one tenth the original Value" Using multiplication with a positive integer and saying "less" just seems incomprehensible when it flies by during a sentence and I can't stop mys…
Sounds good as non-native.
I couldn't tell how expensive this is up front, or what complexity it adds to the setup. Anyone know?
It's definitely an interesting idea but if you have to pay $100k for all that LoRA, what margins are left over?
It feels like the two dumb ways to customize an open LLM are fine tuning and RAG. The former is expensive and complicated, the latter adds complexity to your queries but doesn't require up front compute for retraining. I couldn't tell how expensive this is up front, or what complexity it adds to the setup. Anyone know? It's definitely an interesting idea but if you have to pay $100k for all that LoRA, what margins ar…