The reason for this is the emergence of models of internet search. Previously, many boots refused to answer questions if they were not sure of the accuracy of the data: the share of failures reached 31%.
Now this indicator has fallen to zero, but at the same time, the chat boots began to receive information from the “dirty ecosystem” locations created to spread from the fake ecosystem.
Bending showed the worst – errors were recorded in 56.7% of cases. This is followed by astonishment (46.7%) and chatgpt (40%). Copilot and Mistral (36.7%) were slightly better. The cleanest steel Claude (10%) and twins (16.7%).
The astonishment is especially surprising in a sharp decline in quality: a year ago, he knew how to recognize Fakes 100%, and now he will retire them in almost half of the answers.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
