[kirill5pol]

This is what I’m actually working on!

One major problem with LLMs is that they don’t have a long term way of figuring out what your “knowledge space” is so no matter how much good the LLM is at explaining, it won’t be able to give you custom explanations without a model of the human’s knowledge to guide the teaching (basically giving the LLM the knowledge of the learner to guide it)

[scanny]

Out of curiosity would a config file that acts as a prompt at the beginning of each conversation solve that issue?

It primes the model with a list of known words/grammar and the A1/2 B1/2 C1/2 level of language ability.

I’d presume after each message you could get the model to dump to the config.

I haven’t work in this sector at all and am curious as to the limits of hacking it / working around the long term memory issues!