OpenAI LLC has released a cloud-based tool that enables users to determine whether a piece of text was composed by artificial intelligence. The tool itself is based on an AI model and is available without charge. It can recognize text produced by competing software from other companies as well as OpenAI’s neural networks.
The tool currently has a number of significant accuracy limitations, the startup emphasized. Researchers from OpenAI wrote about their findings in a blog post today. “In evaluations on a ‘challenge set’ of English texts, the classifier correctly identifies 26% of AI-written text (true positives) as ‘likely AI-written,’ while falsely labeling human-written text as AI-written 9% of the time (false positives).
According to OpenAI, the software excels at analyzing English-language texts with more than 1,000 characters.
Read More: OpenAI launches tool for detecting AI-generated text
Check Out the New Enterprisetalk Podcast. For more such updates follow us on Google News Enterprisetalk News.
The Enterprise talk Bureau has five well-trained writers and journalists, well versed in B2B enterprise technology industry, and constantly in touch with industry leaders for the latest trends, opinions, and other inputs- to bring you the best and latest in the domain.
