ChatGPT: what a neural network can do for working with texts

Kateryna Kushnir , editor, content marketer, author of the Telegram channel  “Not just an editor” , played with ChatGPT .

What can be said

it is still too early to expect the disappearance of the profession of authors and editors, but some people should be worried .

I generated texts on medical topics, questions for interviews with doctors and blog posts. In some places, the result is even frightening: the neural network writes better than many people, but it also has weaknesses.

What artificial intelligence cannot do

Correctly work with telegram database users list  information in all cases. It must be said that he copes with many requests. For example, ChatGPT generated an answer to the question of what antioxidants are and whether it is necessary to take supplements with them, almost like a real author – everything strictly according to modern recommendations. It turned out better and more correct than 90% of the articles that the search engine gives. 

telegram database users list

However the algorithm does poorly with ambiguous questions such

as whether wisdom teeth Využijte k zachycení nových zákazníků!  should be treated or whether they should always be removed. Here we need a person who can analyze several sources.

read research and opinions of authoritative organizations

understand where the truth lies. Even the quality of the text from the point of view of aqb directory readability is worse in such cases – it is probably difficult for AI to generate something understandable due to the fact that there is little data on the Internet. 

Leave a comment

Your email address will not be published. Required fields are marked *