{"id":86549,"date":"2023-04-13T20:11:56","date_gmt":"2023-04-14T00:11:56","guid":{"rendered":"http:\/\/danielschristian.com\/learning-ecosystems\/?p=86549"},"modified":"2023-04-17T15:02:15","modified_gmt":"2023-04-17T19:02:15","slug":"autogpt-might-be-the-next-big-step-in-ai-software-agents-that-use-natural-language-to-simulate-human-behaviour-other-items-re-ai","status":"publish","type":"post","link":"https:\/\/danielschristian.com\/learning-ecosystems\/2023\/04\/13\/autogpt-might-be-the-next-big-step-in-ai-software-agents-that-use-natural-language-to-simulate-human-behaviour-other-items-re-ai\/","title":{"rendered":"&#8220;AutoGPT might be the next big step in AI&#8221;; &#8220;software agents that use natural language to simulate human behavior&#8221; + other items re: AI"},"content":{"rendered":"<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\">AutoGPT might be the next big step in AI.<\/p>\n<p>Here&#8217;s why Karpathy recently said &#8220;AutoGPT is the next frontier of prompt engineering&#8221;<\/p>\n<p>AutoGPT is the equivalent of giving GPT-based models a memory and a body. You can now give a task to an AI agent and have it autonomously come up\u2026 <a href=\"https:\/\/t.co\/mYIJm2IEZy\">pic.twitter.com\/mYIJm2IEZy<\/a><\/p>\n<p>\u2014 Lior? (@AlphaSignalAI) <a href=\"https:\/\/twitter.com\/AlphaSignalAI\/status\/1645847165066006529?ref_src=twsrc%5Etfw\">April 11, 2023<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<hr \/>\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\">AutoGPT, less noise more signal<\/p>\n<p>This is where you should pay attention<\/p>\n<p>Here is why ?<\/p>\n<p><a href=\"https:\/\/t.co\/2For7bPOID\">pic.twitter.com\/2For7bPOID<\/a><\/p>\n<p>\u2014 Linus (???) (@LinusEkenstam) <a href=\"https:\/\/twitter.com\/LinusEkenstam\/status\/1645884266960617472?ref_src=twsrc%5Etfw\">April 11, 2023<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<hr \/>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">AutoGPT is the next BIG thing in AI. <\/p>\n<p>Seems like a new *groundbreaking* update comes out every hour. <\/p>\n<p>Here are a few examples just from the past 24 hours: ?<\/p>\n<p>&mdash; Barsee ? (@heyBarsee) <a href=\"https:\/\/twitter.com\/heyBarsee\/status\/1646270998243581954?ref_src=twsrc%5Etfw\">April 12, 2023<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<hr \/>\n<p><strong><a href=\"https:\/\/www.therundown.ai\/p\/autogpt\" target=\"_blank\" rel=\"nofollow noopener\">AutoGPT is the next big thing in AI<\/a><\/strong>&#8212; from therundown.ai by Rowan Cheung<\/p>\n<p><em>Excerpt:<\/em><\/p>\n<p style=\"padding-left: 40px;\">AutoGPT has been making waves on the internet recently, trending on both GitHub and Twitter. If you thought ChatGPT was crazy, AutoGPT is about to blow your mind.<\/p>\n<p style=\"padding-left: 40px;\">AutoGPT creates AI &#8220;agents&#8221; that operate automatically on their own and complete tasks for you. In case you&#8217;ve missed our previous issues covering it, here&#8217;s a quick rundown:<\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>It&#8217;s open-sourced [code]<\/li>\n<li>It works by chaining together LLM &#8220;thoughts&#8221;<\/li>\n<li>It has internet access, long-term and short-term memory, access to popular websites, and file storage<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><span style=\"color: #ffffff;\">.<\/span><\/p>\n<hr \/>\n<p><iframe loading=\"lazy\" title=\"Embedded post\" src=\"https:\/\/www.linkedin.com\/embed\/feed\/update\/urn:li:share:7051186255497199616\" width=\"504\" height=\"600\" frameborder=\"0\" allowfullscreen=\"allowfullscreen\"><\/iframe><\/p>\n<hr \/>\n<p><em><span style=\"color: #800000;\">From DSC:<\/span><\/em><br \/>\n<strong><span style=\"color: #800000;\">I want to highlight that paper from Stanford, as I&#8217;ve seen it cited several times recently:<\/span><\/strong><span style=\"color: #800000;\"><span style=\"color: #ffffff;\">.<\/span><\/span><\/p>\n<ul>\n<li><a href=\"https:\/\/arxiv.org\/abs\/2304.03442v1\" target=\"_blank\" rel=\"nofollow noopener\"><strong>Generative Agents: Interactive Simulacra of Human Behavior<\/strong><\/a><br \/>\nJoon Sung Park, Joseph C. O&#8217;Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, Michael S. Bernstein<br \/>\n<span style=\"color: #ffffff;\">.<\/span><\/li>\n<\/ul>\n<p><a href=\"https:\/\/arxiv.org\/abs\/2304.03442v1\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" class=\"wp-image-86550 size-full aligncenter\" src=\"http:\/\/danielschristian.com\/learning-ecosystems\/wp-content\/uploads\/2023\/04\/GenerativeAgents-Stanford-Apr23.jpg\" alt=\"Generative Agents: Interactive Simulacra of Human Behavior -- a paper from Stanford from April 2023\" width=\"100%\" height=\"100%\" srcset=\"https:\/\/danielschristian.com\/learning-ecosystems\/wp-content\/uploads\/2023\/04\/GenerativeAgents-Stanford-Apr23.jpg 744w, https:\/\/danielschristian.com\/learning-ecosystems\/wp-content\/uploads\/2023\/04\/GenerativeAgents-Stanford-Apr23-129x150.jpg 129w\" sizes=\"(max-width: 744px) 100vw, 744px\" \/><\/a><\/p>\n<hr \/>\n<p><em><span style=\"color: #800000;\">From DSC:<\/span><\/em><br \/>\n<span style=\"color: #800000;\"><strong>And for a rather fun idea\/application of these emerging technologies, see:<\/strong><\/span><\/p>\n<ul>\n<li><strong><a href=\"https:\/\/linusekenstam.substack.com\/p\/quick-prompt-kitchen-design\" target=\"_blank\" rel=\"nofollow noopener\">Quick Prompt: Kitchen Design<\/a><\/strong> &#8212; from linusekenstam.substack.com by Linus Ekenstam<br \/>\n<em>Midjourney Prompt. Create elegant kitchen photos using this starting prompt. Make it your own, experiment, add, remove and tinker to create new ideas.<\/em><\/li>\n<\/ul>\n<p><a href=\"https:\/\/linusekenstam.substack.com\/p\/quick-prompt-kitchen-design\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" class=\"alignnone\" src=\"https:\/\/substackcdn.com\/image\/fetch\/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep\/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F571fe8b8-3c8a-4588-9905-cb18d84f6713_1344x896.png\" alt=\"\" width=\"100%\" height=\"100%\" \/><\/a><\/p>\n<p><span style=\"color: #800000;\"><strong>&#8230;which made me wonder how we might use these techs in the development of new learning spaces (or in renovating current learning spaces).<\/strong><\/span><\/p>\n<hr \/>\n<p><em><span style=\"color: #800000;\">From DSC:<\/span><\/em><br \/>\n<span style=\"color: #800000;\">On a much different &#8212; but still potential &#8212; note, also see:<\/span><\/p>\n<p><a href=\"https:\/\/fortune.com\/2023\/04\/10\/ai-nuclear-level-catastrophe-experts-stanford\/\" target=\"_blank\" rel=\"nofollow noopener\"><strong>A.I. could lead to a \u2018nuclear-level catastrophe\u2019 according to a third of researchers, a new Stanford report finds<\/strong><\/a> &#8212; from fortune.com by Tristan Bove<\/p>\n<p><em>Excerpt:<\/em><\/p>\n<p style=\"padding-left: 40px;\">Many experts in A.I. and computer science say the technology is likely a watershed moment for human society. But 36% don\u2019t mean that as a positive, warning that decisions made by A.I. could lead to \u201cnuclear-level catastrophe,\u201d according to researchers surveyed in\u00a0an annual report\u00a0on the technology by Stanford University\u2019s Institute for Human-Centered A.I., published earlier this month.<\/p>\n<hr \/>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">AutoGPTs are improving at a blazingly fast speed and could soon transform the face of business.<\/p>\n<p>Here&#39;s what you need to know:<\/p>\n<p>&mdash; Nathan Lands (@NathanLands) <a href=\"https:\/\/twitter.com\/NathanLands\/status\/1646101184384573446?ref_src=twsrc%5Etfw\">April 12, 2023<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n","protected":false},"excerpt":{"rendered":"<p>AutoGPT might be the next big step in AI. Here&#8217;s why Karpathy recently said &#8220;AutoGPT is the next frontier of prompt engineering&#8221; AutoGPT is the equivalent of giving GPT-based models a memory and a body. You can now give a task to an AI agent and have it autonomously come up\u2026 pic.twitter.com\/mYIJm2IEZy \u2014 Lior? (@AlphaSignalAI) [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[113,390,356,45,260,112,200,135,32,210,391,419,180,119,482,124,102,7,87,821,126,855,480,195,118,11,822],"tags":[],"class_list":["post-86549","post","type-post","status-publish","format-standard","hentry","category-21st-century","category-architecture","category-artificial-intelligence-agents-llms-and-related","category-computer-science","category-content-development-aggregation-repositories","category-corporate-business-world","category-corporate-universities","category-design","category-education-technology","category-emerging-technologies","category-human-computer-interaction-hci","category-ideas-teaching","category-innovation","category-instructional-design","category-intelligent-systems","category-intelligent-tutoring","category-learning","category-learning-ecosystem","category-learning-spaces","category-natural-language-processing-nlp","category-simulations","category-skills","category-society","category-tools","category-training-corporate-universities","category-vision-possibilities","category-voice-recognition-voice-enabled-interfaces"],"_links":{"self":[{"href":"https:\/\/danielschristian.com\/learning-ecosystems\/wp-json\/wp\/v2\/posts\/86549","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/danielschristian.com\/learning-ecosystems\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/danielschristian.com\/learning-ecosystems\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/danielschristian.com\/learning-ecosystems\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/danielschristian.com\/learning-ecosystems\/wp-json\/wp\/v2\/comments?post=86549"}],"version-history":[{"count":13,"href":"https:\/\/danielschristian.com\/learning-ecosystems\/wp-json\/wp\/v2\/posts\/86549\/revisions"}],"predecessor-version":[{"id":86612,"href":"https:\/\/danielschristian.com\/learning-ecosystems\/wp-json\/wp\/v2\/posts\/86549\/revisions\/86612"}],"wp:attachment":[{"href":"https:\/\/danielschristian.com\/learning-ecosystems\/wp-json\/wp\/v2\/media?parent=86549"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/danielschristian.com\/learning-ecosystems\/wp-json\/wp\/v2\/categories?post=86549"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/danielschristian.com\/learning-ecosystems\/wp-json\/wp\/v2\/tags?post=86549"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}