Post #3285002
2026-05-31 13:28 UTC
Idk. LLMs don't seem like a good solution because of how many resources they need to train and run compared to specialized models.
Replies (1)
-
@Zos_Kia@jlai.lu 2026-05-31 17:58
I know it's in bad taste to quote myself but i wrote an explanation of why this isn't necessarily a bad solution [here](https://jlai.lu/post/38363402/21350511)