I made basically the same proposal here, but phrased as a task of translating between a long alien message and human languages: https://www.lesswrong.com/posts/J3zA3T9RTLkKYNgjw/is-llm-translation-without-rosetta-stone-possible See also the comments, which contain a reference to a paper with a related approach on unsupervised machine translation. Also this comment echoes your post:
I think this is a really interesting question since it seems like it should neatly split the “LLMs are just next token predictors” crows from the “LLMs actually display understanding” crowd.
I made basically the same proposal here, but phrased as a task of translating between a long alien message and human languages: https://www.lesswrong.com/posts/J3zA3T9RTLkKYNgjw/is-llm-translation-without-rosetta-stone-possible See also the comments, which contain a reference to a paper with a related approach on unsupervised machine translation. Also this comment echoes your post: