from 10b0t0mized: I miss the days when I had to go through a humiliation ritual before getting my questions answered.
Now days you can just ask your questions from an infinitely patient entity, AI is really terrible.
from 10b0t0mized: I miss the days when I had to go through a humiliation ritual before getting my questions answered.
Now days you can just ask your questions from an infinitely patient entity, AI is really terrible.
LLMs with more native access to documentation should do OK.
There’s potential for a sea of “niche” LLMs too. A good example is this version of Qwen finetuned just to write CUDA: https://huggingface.co/cognition-ai/Kevin-32B