OpenAI said it hired more than 1,000 workers for this purpose. Others estimate that companies are already investing between millions and tens of millions of dollars on it annually. ![]() AI researchers and engineers say such human input will continue to be essential as OpenAI and other companies hone the technology.Īlexandr Wang, chief executive of Scale AI, one outsourcing company that provides contractors to OpenAI for reviewing and categorizing content, tweeted in February that companies could soon spend hundreds of millions of dollars a year to provide AI systems with human feedback. Much of this work was benign, for instance, teaching ChatGPT to be an engaging conversationalist or witty lyricist. OpenAI marshaled a sprawling global pipeline of specialized human labor for over two years to enable its most cutting-edge AI technologies to exist, the documents show. ![]() “My experience in those four months was the worst experience I’ve ever had in working in a company," Alex Kairu, one of the Kenya workers, said in an interview. The company used the categorized passages to build an AI safety filter that it would ultimately deploy to constrain ChatGPT from exposing its tens of millions of users to similar content. Many of the passages contained descriptions of violence, harassment, self-harm, rape, child sexual abuse and bestiality, documents reviewed by The Wall Street Journal show. Even before it created ChatGPT, it hired workers in Kenya to review and categorize thousands of graphic text passages obtained online and generated by AI itself. Given the right prompts, a large language model can generate reams of toxic content inspired by the darkest parts of the internet.ĬhatGPT’s parent, AI research company OpenAI, has been grappling with these issues for years. The vast data supercharges its capabilities, allowing it to act like an autocompletion engine on steroids. ![]() In recent years, low-paid workers in East Africa engaged in an often-traumatizing effort to prevent chatbot technology from spitting out offensive or grotesque statements.ĬhatGPT is built atop a so-called large language model-powerful software trained on swaths of text scraped from across the internet to learn the patterns of human language. For now, though, the technology relies on a different kind of human labor.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |