Question: For things like this to be truly worthwhile, do you have to ensure the training, post-training of LLM's is filled with brilliant memelang code? The models are probably already good at 'thinking' in SQL at the moment, but if they aren't trained on memelang, surely they will have to use more effort to translate in context to produce equivalent quality queries?
Wouldn't surprise me if in the next few generations we start seeing more LLM generated languages that LLM's prefer to use for expressability, conciseness, etc.
interesting attempt but would need the next generation of LLMs to be trained on memelang code and it's documentations so we don't waste more tokens in context windows trying to instruct the model on how to use memelang to save a smaller amount than we waste.
2 comments
[ 0.24 ms ] story [ 12.3 ms ] threadWouldn't surprise me if in the next few generations we start seeing more LLM generated languages that LLM's prefer to use for expressability, conciseness, etc.