Comment on Largest study of its kind shows AI assistants misrepresent news content 45% of the time – regardless of language or territory

morrowind@lemmy.ml ⁨1⁩ ⁨week⁩ ago

“misrepresent” is a vague term. Actual graph from the study

Image

The main issue is usual… sources. AI is bad at sources without a proper pipeline. They note that Gemini is the worst at 72%.

Note, they’re not testing models with their own pipeline. They’re testing other people’s products. This is more indicative of the product design than the actual models

source
Sort:hotnewtop