|
|
|
|
|
|
by neovive
31 days ago
|
|
|
> For an LLM, words are the source, and any meaning is just a byproduct that falls out by accident. Recently, I've been thinking a lot about context and whether an LLM actually creates a true representation of a concept within its vectors. And for our current usage of LLMs, does it even matter? As models become so large, will the difference even be perceivable to us? |
|
|