theoretically, if the model is properly trained, it should grok that влъхвъ and magician semantically are the seam thus must land relatively close in the latent space. the same way a cat from an image encodes the same way, so that it can decode later in arbitrary language.
alt Hacker News
theoretically, if the model is properly trained, it should grok that влъхвъ and magician semantically are the seam thus must land relatively close in the latent space. the same way a cat from an image encodes the same way, so that it can decode later in arbitrary language.