News Leader
The latest natural-language system generates tweets, pens poetry, summarizes emails, answers trivia questions, translates languages and even writes its own computer programs. This summer, an artificial intelligence lab in San Francisco called OpenAI unveiled a technology several months in the making. This new system, GPT-3, had spent those months learning the ins and outs of natural language by analyzing thousands of digital books, the length and breadth of Wikipedia, and nearly a trillion words posted to blogs, social media and the rest of the internet. Mckay Wrigley, a 23-year-old computer programmer from Salt Lake City, was one of the few invited to tinker with the system, which uses everything it has learned from that vast sea of digital text to generate new language on its own. Mr. Wrigley wondered if it could imitate public figures — write like them, perhaps even chat like them. One of his experiments involved a pop psychologist, Scott Barry Kaufman. The system took in Mr. Kaufman’s name and a topic for discussion: creativity. Then, when asked “How do we become more creative?” GPT-3 responded instantly:I think creative expression is a natural byproduct of growing up in a diverse world. The more diverse the world is, the more you get exposed to different people, to different opportunities, to different places and to different challenges. And the more diverse that is, the more likely you’ll be to be able to put the dots together to form something new. And in many ways, I think if you want to be creative, you have to go for it. If you want to be a writer, you have to write, if you want to be a musician, you have to create music, if you want to be a comedian, you have to create comedy, and the more you create, the more likely it is that you’ll stumble onto some interesting stuff. Later, when Mr. Wrigley posted the paragraph on Twitter, somebody looped in the real Scott Barry Kaufman. He was stunned. “It definitely sounds like something I would say,” the real Mr. Kaufman tweeted, later adding, “Crazy accurate A. I.”In the weeks since its arrival, GPT-3 has spawned dozens of other experiments that raise the eyebrows in much the same way. It generates tweets, pens poetry, summarizes emails, answers trivia questions, translates languages and even writes its own computer programs, all with very little prompting. Some of these skills caught even the experts off guard. For many artificial intelligence researchers, it is an unexpected step toward machines that can understand the vagaries of human language — and perhaps even tackle other human skills.“It is surprising to me, and to a lot of people,” said Melanie Mitchell, an A. I. researcher at the Santa Fe Institute, an independent lab in New Mexico, who is among those experimenting with the system. “It is hard to figure out exactly what this thing is doing.”GPT-3 is far from flawless. It often spews biased and toxic language.
All data is taken from the source: http://nytimes.com
Article Link: https://www.nytimes.com/2020/11/24/science/artificial-intelligence-ai-gpt3.html
#system #newsnbc #newszoo #newsyearresolution #newsshow #newshalloween #