{"id":11164,"date":"2024-04-01T13:43:28","date_gmt":"2024-04-01T13:43:28","guid":{"rendered":"https:\/\/dailyai.com\/?p=11164"},"modified":"2024-04-02T17:03:30","modified_gmt":"2024-04-02T17:03:30","slug":"new-study-attempts-to-align-ai-with-crowdsourced-human-values","status":"publish","type":"post","link":"https:\/\/dailyai.com\/sv\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/","title":{"rendered":"Ny studie f\u00f6rs\u00f6ker anpassa AI till m\u00e4nskliga v\u00e4rderingar som h\u00e4mtats fr\u00e5n massor av m\u00e4nniskor"},"content":{"rendered":"<p><b>Forskare fr\u00e5n Meaning Alignment Institute har f\u00f6reslagit ett nytt tillv\u00e4gag\u00e5ngss\u00e4tt, Moral Graph Elicitation (MGE), f\u00f6r att anpassa AI-system till m\u00e4nskliga v\u00e4rderingar.<\/b><\/p>\n<p><span style=\"font-weight: 400;\">I takt med att AI blir allt mer avancerat och integreras i v\u00e5ra dagliga liv \u00e4r det av yttersta vikt att s\u00e4kerst\u00e4lla att det tj\u00e4nar och representerar alla p\u00e5 ett r\u00e4ttvist s\u00e4tt. Men den<\/span><span style=\"font-weight: 400;\">hans <\/span><a href=\"https:\/\/static1.squarespace.com\/static\/65392ca578eee444c445c9de\/t\/6606f95edb20e8118074a344\/1711733370985\/human-values-and-alignment-29MAR2024.pdf\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">studie<\/span><\/a><span style=\"font-weight: 400;\"> menar att det inte r\u00e4cker med att anpassa AI till anv\u00e4ndarens m\u00e5l f\u00f6r att garantera s\u00e4kerheten.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">\u00a0\"AI-system kommer att anv\u00e4ndas i sammanhang d\u00e4r blind f\u00f6ljsamhet till operat\u00f6rens avsikt kan orsaka skada som en biprodukt. Detta kan ses tydligast i milj\u00f6er med konkurrensdynamik, som politiska kampanjer eller hantering av finansiella tillg\u00e5ngar\", menar forskarna.\u00a0<\/span><\/p>\n<p>Detta beror p\u00e5 att AI-modeller \u00e4r utformade f\u00f6r att tj\u00e4na anv\u00e4ndaren. Om anv\u00e4ndaren instruerar en modell mot skadliga syften kan modellens drivkraft att tj\u00e4na anv\u00e4ndaren leda till att den kringg\u00e5r skyddsr\u00e4cken och lyder.<\/p>\n<p>En l\u00f6sning \u00e4r att \"impregnera\" AI med en serie v\u00e4rden som den konsulterar varje g\u00e5ng den uppmanas till det.<\/p>\n<p>Fr\u00e5gan \u00e4r varifr\u00e5n dessa v\u00e4rderingar kommer? Och kan de representera m\u00e4nniskor p\u00e5 ett r\u00e4ttvist s\u00e4tt?<\/p>\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\">\"Vad \u00e4r m\u00e4nskliga v\u00e4rderingar och hur anpassar vi oss till dem?\"<\/p>\n<p>Vi \u00e4r mycket glada \u00f6ver att kunna publicera v\u00e5r nya rapport om v\u00e4rdeorientering, som vi har f\u00f6rfattat tillsammans med <a href=\"https:\/\/twitter.com\/ryan_t_lowe?ref_src=twsrc%5Etfw\">@ryan_t_lowe<\/a> och finansierad av <a href=\"https:\/\/twitter.com\/OpenAI?ref_src=twsrc%5Etfw\">@openai<\/a>.<\/p>\n<p>\ud83d\udcdd: <a href=\"https:\/\/t.co\/iioFKmrDZA\">https:\/\/t.co\/iioFKmrDZA<\/a> <a href=\"https:\/\/t.co\/NSJa8dbcrM\">pic.twitter.com\/NSJa8dbcrM<\/a><\/p>\n<p>- Joe Edelman (@edelwax) <a href=\"https:\/\/twitter.com\/edelwax\/status\/1773621129200234573?ref_src=twsrc%5Etfw\">29 mars 2024<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p><span style=\"font-weight: 400;\">F\u00f6r att l\u00f6sa dessa problem f\u00f6reslog forskarna att AI skulle anpassas till en djupare representation av m\u00e4nskliga v\u00e4rderingar genom MGE.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">MGE-metoden har tv\u00e5 huvudkomponenter: v\u00e4rdekort och den moraliska grafen. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Dessa utg\u00f6r ett inriktningsobjekt f\u00f6r utbildning av maskininl\u00e4rningsmodeller.<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>V\u00e4rdekort<\/b><span style=\"font-weight: 400;\"> f\u00e5ngar upp vad som \u00e4r viktigt f\u00f6r en person i en specifik situation. De best\u00e5r av \"konstitutiva uppm\u00e4rksamhetspolicyer\" (CAP), som \u00e4r de saker som en person uppm\u00e4rksammar n\u00e4r han eller hon g\u00f6r ett meningsfullt val. N\u00e4r man ger r\u00e5d till en v\u00e4n kan man t.ex. fokusera p\u00e5 att f\u00f6rst\u00e5 dennes k\u00e4nslor, f\u00f6resl\u00e5 anv\u00e4ndbara resurser eller \u00f6verv\u00e4ga de potentiella resultaten av olika val.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Den moraliska grafen<\/b><span style=\"font-weight: 400;\"> representerar visuellt relationerna mellan v\u00e4rdekorten och visar vilka v\u00e4rden som \u00e4r mer insiktsfulla eller till\u00e4mpliga i ett visst sammanhang. F\u00f6r att konstruera den moraliska grafen j\u00e4mf\u00f6r deltagarna olika v\u00e4rdekort och avg\u00f6r vilka de anser erbjuder klokare v\u00e4gledning f\u00f6r en viss situation. P\u00e5 s\u00e5 s\u00e4tt utnyttjas deltagarnas kollektiva visdom f\u00f6r att identifiera de starkaste och mest allm\u00e4nt erk\u00e4nda v\u00e4rderingarna i varje sammanhang.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">F\u00f6r att testa MGE-metoden genomf\u00f6rde forskarna en studie med 500 amerikaner som anv\u00e4nde processen f\u00f6r att utforska tre kontroversiella \u00e4mnen: abort, f\u00f6r\u00e4ldraskap och de vapen som anv\u00e4ndes vid upploppet p\u00e5 Capitolium den 6 januari.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Resultaten var lovande. 89,1% av deltagarna k\u00e4nde sig v\u00e4lrepresenterade i processen och 89% tyckte att den slutliga moralgrafen var r\u00e4ttvis, \u00e4ven om deras v\u00e4rde inte r\u00f6stades fram som det klokaste.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">I studien beskrivs ocks\u00e5 sex kriterier som ett anpassningsobjekt m\u00e5ste uppfylla f\u00f6r att forma modellbeteende enligt m\u00e4nskliga v\u00e4rderingar: det ska vara finkornigt, generaliserbart, skalbart, robust, legitimt och granskningsbart. Forskarna h\u00e4vdar att den moraliska graf som produceras av MGE fungerar bra enligt dessa kriterier.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Denna studie f\u00f6resl\u00e5r ett liknande tillv\u00e4gag\u00e5ngss\u00e4tt som Anthropics <\/span><a href=\"https:\/\/dailyai.com\/sv\/2023\/10\/democratizing-ai-governance-an-anthropic-experiment\/\"><span style=\"font-weight: 400;\">Kollektiv Konstitutiv AI<\/span><\/a>,<span style=\"font-weight: 400;\"> som ocks\u00e5 crowdsourcar v\u00e4rden f\u00f6r AI-anpassning. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Studief\u00f6rfattaren Joe Edelman sa dock p\u00e5 X: \"V\u00e5r metod, MGE, \u00f6vertr\u00e4ffar alternativ som CCAI by @anthropic p\u00e5 legitimitet i en fallstudie och erbjuder robusthet mot ideologisk retorik. 89% h\u00e5ller till och med med om att de vinnande v\u00e4rdena var r\u00e4ttvisa, \u00e4ven om deras eget v\u00e4rde inte vann!\"<\/span><\/p>\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\">V\u00e5r metod, MGE, \u00f6vertr\u00e4ffar alternativ som CCAI med <a href=\"https:\/\/twitter.com\/Anthropic?ref_src=twsrc%5Etfw\">@anthropic<\/a> p\u00e5 legitimitet i en fallstudie, och erbjuder robusthet mot ideologisk retorik.<\/p>\n<p>89% h\u00e5ller till och med med om att de vinnande v\u00e4rdena var r\u00e4ttvisa, \u00e4ven om deras eget v\u00e4rde inte vann! <a href=\"https:\/\/t.co\/sGgLCUtwzN\">pic.twitter.com\/sGgLCUtwzN<\/a><\/p>\n<p>- Joe Edelman (@edelwax) <a href=\"https:\/\/twitter.com\/edelwax\/status\/1773621155712377054?ref_src=twsrc%5Etfw\">29 mars 2024<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<h2>Begr\u00e4nsningar<\/h2>\n<p>Det finns begr\u00e4nsningar f\u00f6r metoder f\u00f6r AI-anpassning som bygger p\u00e5 crowdsourcing av v\u00e4rden fr\u00e5n allm\u00e4nheten.<\/p>\n<p>Till exempel har avvikande \u00e5sikter varit en integrerad del av samh\u00e4llets beslutsfattande i \u00e5rhundraden, och historien har visat att majoriteten ofta kan anta minoritetens avvikande synpunkter. Som exempel kan n\u00e4mnas Darwins evolutionsteori och kampen f\u00f6r att avskaffa slaveriet och ge kvinnor r\u00f6str\u00e4tt.<\/p>\n<p class=\"whitespace-pre-wrap break-words\">\u00c4ven om direkt medverkan fr\u00e5n allm\u00e4nheten \u00e4r demokratisk kan det leda till populism, d\u00e4r majoriteten kan \u00e5sidos\u00e4tta minoritetens \u00e5sikter eller bortse fr\u00e5n expertr\u00e5d.<\/p>\n<p class=\"whitespace-pre-wrap break-words\">En annan utmaning \u00e4r att balansera globala eller universalistiska och lokala eller relativistiska kulturella v\u00e4rderingar. Principer som \u00e4r allm\u00e4nt accepterade i en kultur eller region kan vara kontroversiella i en annan.<\/p>\n<p class=\"whitespace-pre-wrap break-words\">AI-konstitutioner skulle kunna f\u00f6rst\u00e4rka v\u00e4sterl\u00e4ndska v\u00e4rderingar och potentiellt undergr\u00e4va \u00e5sikter och id\u00e9er hos dem som befinner sig i periferin.<\/p>\n<p><span style=\"font-weight: 400;\">\u00c4ven om denna nya studie erk\u00e4nner begr\u00e4nsningar och behovet av ytterligare utveckling, ger den en annan strategi f\u00f6r att skapa AI-system som \u00f6verensst\u00e4mmer med m\u00e4nskliga v\u00e4rderingar. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Varje f\u00f6rs\u00f6k r\u00e4knas om centraliserad AI ska kunna tj\u00e4na alla p\u00e5 ett r\u00e4ttvist s\u00e4tt i framtiden.\u00a0<\/span><\/p>","protected":false},"excerpt":{"rendered":"<p>Forskare fr\u00e5n Meaning Alignment Institute har f\u00f6reslagit ett nytt tillv\u00e4gag\u00e5ngss\u00e4tt, Moral Graph Elicitation (MGE), f\u00f6r att anpassa AI-system till m\u00e4nskliga v\u00e4rderingar. I takt med att AI blir allt mer avancerat och integreras i v\u00e5ra dagliga liv \u00e4r det av st\u00f6rsta vikt att s\u00e4kerst\u00e4lla att det tj\u00e4nar och representerar alla p\u00e5 ett r\u00e4ttvist s\u00e4tt. Den h\u00e4r studien visar dock att det inte r\u00e4cker med att anpassa AI till anv\u00e4ndarens m\u00e5l f\u00f6r att garantera s\u00e4kerheten.  \"AI-system kommer att anv\u00e4ndas i sammanhang d\u00e4r blind f\u00f6ljsamhet till operat\u00f6rens intentioner kan orsaka skada som en biprodukt. Detta syns tydligast i milj\u00f6er med konkurrensdynamik, som politiska kampanjer eller hantering av finansiella tillg\u00e5ngar\", menar forskarna.  Detta beror p\u00e5 att<\/p>","protected":false},"author":2,"featured_media":11165,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[88],"tags":[105,93],"class_list":["post-11164","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ethics","tag-machine-learning","tag-openai"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>New study attempts to align AI with crowdsourced human values | DailyAI<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/sv\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/\" \/>\n<meta property=\"og:locale\" content=\"sv_SE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"New study attempts to align AI with crowdsourced human values | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers from the Meaning Alignment Institute have proposed a new approach, Moral Graph Elicitation (MGE), to align AI systems with human values. As AI becomes more advanced and integrated into our daily lives, ensuring it serves and represents everyone fairly is paramount. However, this study argues that aligning AI with the user&#8217;s goals alone doesn&#8217;t guarantee safety. \u00a0&#8220;AI systems will be deployed in contexts where blind adherence to operator intent can cause harm as a byproduct. This can be seen most clearly in environments with competitive dynamics, like political campaigns or managing financial assets,&#8221; the researchers argue.\u00a0 This is because\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/sv\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-04-01T13:43:28+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-02T17:03:30+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1792\" \/>\n\t<meta property=\"og:image:height\" content=\"1024\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Sam Jeans\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"Skriven av\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sam Jeans\" \/>\n\t<meta name=\"twitter:label2\" content=\"Ber\u00e4knad l\u00e4stid\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minuter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/\"},\"author\":{\"name\":\"Sam Jeans\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\"},\"headline\":\"New study attempts to align AI with crowdsourced human values\",\"datePublished\":\"2024-04-01T13:43:28+00:00\",\"dateModified\":\"2024-04-02T17:03:30+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/\"},\"wordCount\":764,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp\",\"keywords\":[\"machine learning\",\"OpenAI\"],\"articleSection\":[\"Ethics &amp; Society\"],\"inLanguage\":\"sv-SE\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/\",\"name\":\"New study attempts to align AI with crowdsourced human values | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp\",\"datePublished\":\"2024-04-01T13:43:28+00:00\",\"dateModified\":\"2024-04-02T17:03:30+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#breadcrumb\"},\"inLanguage\":\"sv-SE\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp\",\"width\":1792,\"height\":1024,\"caption\":\"AI values\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"New study attempts to align AI with crowdsourced human values\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"sv-SE\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\",\"name\":\"Sam Jeans\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"caption\":\"Sam Jeans\"},\"description\":\"Sam is a science and technology writer who has worked in various AI startups. When he\u2019s not writing, he can be found reading medical journals or digging through boxes of vinyl records.\",\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/in\\\/sam-jeans-6746b9142\\\/\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/sv\\\/author\\\/samjeans\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Ny studie f\u00f6rs\u00f6ker anpassa AI till m\u00e4nskliga v\u00e4rderingar som h\u00e4mtats fr\u00e5n massor av m\u00e4nniskor | DailyAI","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dailyai.com\/sv\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/","og_locale":"sv_SE","og_type":"article","og_title":"New study attempts to align AI with crowdsourced human values | DailyAI","og_description":"Researchers from the Meaning Alignment Institute have proposed a new approach, Moral Graph Elicitation (MGE), to align AI systems with human values. As AI becomes more advanced and integrated into our daily lives, ensuring it serves and represents everyone fairly is paramount. However, this study argues that aligning AI with the user&#8217;s goals alone doesn&#8217;t guarantee safety. \u00a0&#8220;AI systems will be deployed in contexts where blind adherence to operator intent can cause harm as a byproduct. This can be seen most clearly in environments with competitive dynamics, like political campaigns or managing financial assets,&#8221; the researchers argue.\u00a0 This is because","og_url":"https:\/\/dailyai.com\/sv\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/","og_site_name":"DailyAI","article_published_time":"2024-04-01T13:43:28+00:00","article_modified_time":"2024-04-02T17:03:30+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp","type":"image\/webp"}],"author":"Sam Jeans","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Skriven av":"Sam Jeans","Ber\u00e4knad l\u00e4stid":"4 minuter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/"},"author":{"name":"Sam Jeans","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9"},"headline":"New study attempts to align AI with crowdsourced human values","datePublished":"2024-04-01T13:43:28+00:00","dateModified":"2024-04-02T17:03:30+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/"},"wordCount":764,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp","keywords":["machine learning","OpenAI"],"articleSection":["Ethics &amp; Society"],"inLanguage":"sv-SE"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/","url":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/","name":"Ny studie f\u00f6rs\u00f6ker anpassa AI till m\u00e4nskliga v\u00e4rderingar som h\u00e4mtats fr\u00e5n massor av m\u00e4nniskor | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp","datePublished":"2024-04-01T13:43:28+00:00","dateModified":"2024-04-02T17:03:30+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#breadcrumb"},"inLanguage":"sv-SE","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/"]}]},{"@type":"ImageObject","inLanguage":"sv-SE","@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp","width":1792,"height":1024,"caption":"AI values"},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"New study attempts to align AI with crowdsourced human values"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DagligaAI","description":"Din dagliga dos av AI-nyheter","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"sv-SE"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DagligaAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"sv-SE","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9","name":"Sam Jeans","image":{"@type":"ImageObject","inLanguage":"sv-SE","@id":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","caption":"Sam Jeans"},"description":"Sam \u00e4r en vetenskaps- och teknikskribent som har arbetat i olika AI-startups. N\u00e4r han inte skriver l\u00e4ser han medicinska tidskrifter eller gr\u00e4ver igenom l\u00e5dor med vinylskivor.","sameAs":["https:\/\/www.linkedin.com\/in\/sam-jeans-6746b9142\/"],"url":"https:\/\/dailyai.com\/sv\/author\/samjeans\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/11164","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/comments?post=11164"}],"version-history":[{"count":6,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/11164\/revisions"}],"predecessor-version":[{"id":11200,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/11164\/revisions\/11200"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media\/11165"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media?parent=11164"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/categories?post=11164"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/tags?post=11164"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}