Why Generative AI Cannot Distinguish Negating Words Such as ‘No’ or ‘Not’ While the Human Brain Can
Dr. Erica Brozovsky, PhD of the PBS series Otherwords explained the concept of negation and the complex nuance involved in using words such as no and not, words using an “im” or “un” prefix (i.e. impossible, unpalatable) and words that have a suffix of “less” (hopeless, careless). While negation is present in every language, generative AI has difficulty has difficulty processing these words in any meaningful way.
Researchers and casual users alike have documented that generative AI tools often struggle with negation, the language we use to express absences, untruths, and opposites. Gen AI models may be able to show you what you do want to see, but they’re not as good at not giving you what you don’t want to see.
