I see a lot of talk about transformers LLMs being close to "topping out," which I am skeptical of for many reasons, but not the least of which is prompting/outputs other than pure text.
Preserving the speakers voice after translation is super cool. It’s one of the things you don’t really think about, but voice inflection and identity is missing with our current translation tools.
I like to watch political speeches from non english speaking politicians, and the speakers tone can easily be lost in translation. Emphasis is hard to discern when you don’t know which spoken word maps to which word in the subtitles. Dubbed speeches are even worse in that respect.
12 comments
[ 3.5 ms ] story [ 45.3 ms ] threadI see a lot of talk about transformers LLMs being close to "topping out," which I am skeptical of for many reasons, but not the least of which is prompting/outputs other than pure text.
LLaVA is the first one that comes to my mind, it takes images and text as input and outputs text.
There’s an unreleased version of GPT4 that can do that same thing.
How do our brains work? Isn't there a separation between image and text processing?
(Just like gpt4 is rumored to be a few different sub models and not just one giant model)
I like to watch political speeches from non english speaking politicians, and the speakers tone can easily be lost in translation. Emphasis is hard to discern when you don’t know which spoken word maps to which word in the subtitles. Dubbed speeches are even worse in that respect.