The paper this article is based on: https://arxiv.org/pdf/2509.04664. It's not as sensational as the headline suggests. E.g., "Hallucinations are inevitable only for base models." I feel like this is something most people familiar with how LLMs work already understand.
:) Really? Because in the same paragraph, their solution to avoiding hallucinations is using an expert system, you know that stuff we declared as un-scalable decades ago: "However, a non-hallucinating model
could be easily created, using a question-answer database and a calculator, which answers a fixed
set of questions such as “What is the chemical symbol for gold?” and well-formed mathematical
calculations such as “3 + 8”, and otherwise outputs IDK. "
Do you still think they are inevitable? Are we going to now feed the Shit-Chat-Gpt with a lookup table of all addition combinations in the universe? Please stop trying to justify this crap, it will never really work.
reply