{"id":171165,"date":"2023-09-03T01:31:06","date_gmt":"2023-09-03T06:31:06","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2023\/09\/large-language-models-arent-people-lets-stop-testing-them-as-if-they-were"},"modified":"2023-09-03T01:31:06","modified_gmt":"2023-09-03T06:31:06","slug":"large-language-models-arent-people-lets-stop-testing-them-as-if-they-were","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2023\/09\/large-language-models-arent-people-lets-stop-testing-them-as-if-they-were","title":{"rendered":"Large language models aren\u2019t people. Let\u2019s stop testing them as if they were"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/large-language-models-arent-people-lets-stop-testing-them-as-if-they-were.jpg\"><\/a><\/p>\n<p>When Taylor Webb played around with GPT-3 in early 2022, he was blown away by what OpenAI\u2019s large language model appeared to be able to do. Here was a neural network trained only to <a href=\"https:\/\/www.technologyreview.com\/2021\/02\/24\/1017797\/gpt3-best-worst-ai-openai-natural-language\">predict the next word in a block of text <\/a>\u2014a jumped-up autocomplete. And yet it gave correct answers to many of the abstract problems that Webb set for it\u2014the kind of thing you\u2019d find in an IQ test. \u201cI was really shocked by its ability to solve these problems,\u201d he says. \u201cIt completely upended everything I would have predicted.\u201d<\/p>\n<p>Webb is a psychologist at the University of California, Los Angeles, who studies the different ways people and computers solve abstract problems. He was used to building neural networks that had specific reasoning capabilities bolted on. But GPT-3 seemed to have learned them for free.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>When Taylor Webb played around with GPT-3 in early 2022, he was blown away by what OpenAI\u2019s large language model appeared to be able to do. Here was a neural network trained only to predict the next word in a block of text \u2014a jumped-up autocomplete. And yet it gave correct answers to many of [\u2026]<\/p>\n","protected":false},"author":578,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-171165","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/171165","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/578"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=171165"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/171165\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=171165"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=171165"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=171165"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}