| ▲ | paulddraper 10 hours ago | |||||||||||||
There are many models modalities, some of which are language. | ||||||||||||||
| ▲ | semiquaver 10 hours ago | parent [-] | |||||||||||||
In fact, many of these “large language models” are actually trained directly on language, images and sound! names stick past their aptness. Y’know: come to think of it that’s the same three things our own brains are mostly trained on… I’m sure that without mammalian proprioception and weird physically-motivated limitations like saccades the result is just sparkling cognition though. | ||||||||||||||
| ||||||||||||||