Couple of years ago I'd look at those Chinese-text diagrams and feel sad and isolated because they represent knowledge that is too foreign for me to read. Nowadays it may as well just be another piece of well-written technical documentation. We are truly lucky to live in this age of wonders and this is really only the opening phase of LLMs as a technology.
Are there general LLMs that can translate text 'on image', as opposed to spitting out the translation as text? I feel like it would be easier to reason about in images that are very text-heavy like some of these diagrams, but from what I remember, last time I tried, chatgpt and claude would only give me a text translation
didn't realize that since the last time i looked at these docs, seems like they've added lots of nice block diagrams for all the different parts of the machine. neat!
Couple of years ago I'd look at those Chinese-text diagrams and feel sad and isolated because they represent knowledge that is too foreign for me to read. Nowadays it may as well just be another piece of well-written technical documentation. We are truly lucky to live in this age of wonders and this is really only the opening phase of LLMs as a technology.
Are there general LLMs that can translate text 'on image', as opposed to spitting out the translation as text? I feel like it would be easier to reason about in images that are very text-heavy like some of these diagrams, but from what I remember, last time I tried, chatgpt and claude would only give me a text translation
In this specific case , it is a svg, so you can ask to translate the svg source.
Google Lens does exactly that.
didn't realize that since the last time i looked at these docs, seems like they've added lots of nice block diagrams for all the different parts of the machine. neat!
Maybe I’m dating myself but when I read “Support Vector” I assumed it was talking about SVM models.