On: I stumbled upon LLM Kryptonite and no one wants to fix this model-breaking bug

[nyrikki]

It is well known that it is impossible to eliminate hallucination in LLMs

Here is a formal proof.

https://arxiv.org/abs/2401.11817

Hopefully this article helps spread the word, but this is something that will have to be mitigated within acceptable limits.

LLMs are NLP, not NLU.

[smarm52 → nyrikki]

> NLU

Natural Language Understanding

(I had to look it up. >_>)