HACKER Q&A
📣 mtokarski

Why LLMs use frequently words like "intricate" or "streamline"


I noticed that there are several keywords that seen on blog or heard in YouTube video give you almost 100% certainty that it is AI generated. Words I mean are not super widely used in English and they are "intricate", "streamline", "meticulously". I've noticed it's common for LLMs to use these words also when using it every day. Is it kind of bias? Or I am biased as non native English speaker?

  👤 gs17 Accepted Answer ✓
The popular LLMs definitely do have a bias toward certain phrases.

For local models, someone was annoyed enough to make a modified sampler that backtracks when the model outputs a "GPT-ism" and regenerates with the output token probabilities tweaked to avoid it: https://github.com/sam-paech/antislop-sampler/

👤 reify
Its like a 5 year old child hearing big words and constantly repeating them to impress their parents or friends.

It only squirts out what is put in it.

Though I am quite confident that a 5 year olds brain is far superior to any AI