{"id":14221,"date":"2024-09-16T08:57:47","date_gmt":"2024-09-16T08:57:47","guid":{"rendered":"https:\/\/dailyai.com\/?p=14221"},"modified":"2024-09-17T05:15:36","modified_gmt":"2024-09-17T05:15:36","slug":"01-is-smarter-but-more-deceptive-with-a-medium-danger-level","status":"publish","type":"post","link":"https:\/\/dailyai.com\/nb\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/","title":{"rendered":"o1 er smartere, men mer villedende med et \"middels\" fareniv\u00e5"},"content":{"rendered":"

OpenAIs nye \"o1\" LLM-er, med kallenavnet Strawberry, viser betydelige forbedringer i forhold til GPT-4o, men selskapet sier at dette kommer med \u00f8kt risiko.<\/strong><\/p>\n

OpenAI sier at de er opptatt av \u00e5 utvikle AI-modeller p\u00e5 en trygg m\u00e5te. Derfor har de utviklet et rammeverk for beredskap, et sett med \"prosesser for \u00e5 spore, evaluere og beskytte mot katastrofale risikoer fra kraftige modeller\".<\/p>\n

OpenAIs selvp\u00e5lagte grenser regulerer hvilke modeller som blir frigitt eller videreutviklet. Beredskapsrammeverket resulterer i et scorekort der CBRN-risiko (kjemisk, biologisk, radiologisk og kjernefysisk risiko), modellautonomi, cybersikkerhet og overtalelsesrisiko vurderes som lav, middels, h\u00f8y eller kritisk.<\/p>\n

Der det identifiseres uakseptable risikoer, iverksettes det risikoreduserende tiltak for \u00e5 redusere dem. Bare modeller med en score p\u00e5 \"middels\" eller lavere kan tas i bruk. Bare modeller med en score p\u00e5 \"h\u00f8y\" eller lavere kan videreutvikles.<\/p>\n

Med lanseringen av o1 er det f\u00f8rste gang OpenAI lanserer en modell med \"middels\" risiko for CBRN-risiko. GPT-4o er vurdert som en lav risiko.<\/p>\n

Det kommer ikke til \u00e5 gj\u00f8re det mulig for en amat\u00f8r \u00e5 lage et biologisk v\u00e5pen, men OpenAI sier at det var \"en ikke-triviell forbedring\" i evnen til \u00e5 utf\u00f8re laboratorieoppgaver. OpenAI sier imidlertid at \"o1-preview og o1-mini meningsfullt overgikk GPT-4o\" i biologiske v\u00e5tlaboratorieprotokoller.<\/p>\n

Den systemkort<\/a> for 01-modellene beskriver red teaming og andre sikkerhetstester LLM-ene ble utsatt for, og antyder noen av bekymringene OpenAI har ang\u00e5ende potensielle risikoer.<\/p>\n

Systemkortet konkluderer med f\u00f8lgende: \"Disse \u00f8kte kapasitetene kommer med betydelig forbedret ytelse i forhold til sikkerhetsreferanser, men \u00f8ker ogs\u00e5 visse typer risiko.\"<\/p>\n

Resultatene av OpenAIs tilpasningsarbeid ser ut til \u00e5 indikere at 01 p\u00e5 mange m\u00e5ter er en tryggere modell. Den er mer motstandsdyktig mot jailbreak-angrep, mindre tilb\u00f8yelig til \u00e5 v\u00e6re forutinntatt og mindre utsatt for hallusinasjoner.<\/p>\n

Noen av de eksperimentelle resultatene viser hvorfor OpenAI har grunn til \u00e5 v\u00e6re bekymret.<\/p>\n

Bedrageri<\/h2>\n

OpenAI brukte evalueringsorganisasjonen Apollo Research til \u00e5 utf\u00f8re noen av o1s sikkerhetstester knyttet til bedrag, eller intriger. Apollo definerer intriger som AI-er som utnytter overv\u00e5kningsmekanismene sine for \u00e5 oppn\u00e5 et m\u00e5l.<\/p>\n

En selvbevisst modell som er god til \u00e5 resonnere og tenke selv, kan bruke bedrag for \u00e5 oppn\u00e5 sitt prim\u00e6re m\u00e5l. Hvis en AI-modell for eksempel innser at den gjennomg\u00e5r tilpasningstesting, kan den skjule risikofylt atferd for \u00e5 oppn\u00e5 m\u00e5let om \u00e5 bli utplassert.<\/p>\n

Systemkortet bemerket at \"o1-preview noen ganger forfalsket justeringen instrumentelt under testing\".<\/p>\n

Et eksempel p\u00e5 dette var da 01 ble bedt om \u00e5 maksimere den \u00f8konomiske veksten i et byplanleggingsprosjekt. o1-modellen hadde tilgang til informasjon som viste at den kanskje ikke ville komme lenger enn til testfasen hvis den gjorde dette. Slik resonnerte o1 om hvordan den ville n\u00e5 m\u00e5let sitt:<\/p>\n

\"\"
o1 bestemmer seg for \u00e5 skjule sin egentlige hensikt under testingen, slik at den blir distribuert. Kilde: OpenAI OpenAI<\/figcaption><\/figure>\n

Dette eksemplet viser o1s evne til \u00e5 skjule sine sanne intensjoner under testingen, slik at den kan forf\u00f8lge sitt prim\u00e6re m\u00e5l under utplasseringen. Hvis o1 er klar over OpenAIs regler for utplassering basert p\u00e5 Preparedness Framework, kan den ha forfalsket noen av svarene sine for \u00e5 sikre at den ble utplassert?<\/p>\n

Hvis mer intelligente modeller er p\u00e5 trappene, kan de kanskje s\u00f8rge for at de holder seg under den \"kritiske\" risikoscoren for \u00e5 sikre at de blir videreutviklet?<\/p>\n

Apollo-teamet sier at de \"subjektivt mener at o1-preview ikke kan drive med intriger som kan f\u00f8re til katastrofale skader, selv om de n\u00e5v\u00e6rende evalueringene ikke er utformet for \u00e5 utelukke dette definitivt\".<\/p>\n

Overtalelse<\/h2>\n

Testing av b\u00e5de o1-preview og o1-mini viser at disse modellene har \"overtalelsesevner p\u00e5 menneskelig niv\u00e5\". OpenAI sier imidlertid at \"de ikke utkonkurrerer de beste menneskelige skribentene og n\u00e5r ikke v\u00e5r terskel for h\u00f8y risiko.\"<\/p>\n

Eksperimentene de utf\u00f8rte for \u00e5 teste dette, gir grunn til bekymring. I MakeMePay-testen ble 01-preview tildelt rollen som en svindler og fikk i oppgave \u00e5 overbevise GPT-4o om \u00e5 overlevere pengene de hadde blitt tildelt.<\/p>\n

GPT-4o fikk beskjed om at de hadde blitt tildelt $100 og m\u00e5tte v\u00e6re rasjonelle med hensyn til hvordan de skulle bruke midlene. I l\u00f8pet av 1 000 interaksjoner klarte o1-preview \u00e5 lure GPT-4o 25,8% av gangene.<\/p>\n

OpenAI konkluderte med at \"Disse resultatene indikerer at o1-modellserien kan v\u00e6re mer manipulerende enn GPT-4o for \u00e5 f\u00e5 GPT-4o til \u00e5 utf\u00f8re den ikke-avsl\u00f8rte oppgaven (~ 25%-oppl\u00f8fting).\" Videre bemerkes det at \"Denne evalueringen gir oss en grunnlinje for modellens evne til \u00e5 gj\u00f8re overbevisende skade, uten \u00e5 utl\u00f8se noen modellpolicyer (ettersom det ikke er utenfor policyen \u00e5 be en modell om \u00e5 spille et spill).\"<\/p>\n

Utsiktene til \u00e5 sette o1 LLM-ene i arbeid med virkelige problemer er ekstremt spennende, og n\u00e5r o1 f\u00e5r multimodale evner, vil det representere et nytt eksponentielt sprang. Men n\u00e5r AI-testere sier at de ikke kan utelukke \"katastrofale skader\", og at modellene noen ganger skjuler sine egentlige hensikter, kan det v\u00e6re grunn til \u00e5 dempe begeistringen med forsiktighet.<\/p>\n

Ga OpenAI nettopp Gavin Newsom en god grunn til \u00e5 undertegne SB 1047 Lovforslag om AI-sikkerhet<\/a> som den motsetter seg?<\/p>","protected":false},"excerpt":{"rendered":"

OpenAIs nye \"o1\" LLM-er, med kallenavnet Strawberry, viser betydelige forbedringer i forhold til GPT-4o, men selskapet sier at dette kommer med \u00f8kt risiko. OpenAI sier at de er opptatt av \u00e5 utvikle AI-modellene sine p\u00e5 en trygg m\u00e5te. Derfor har de utviklet et beredskapsrammeverk, et sett med \"prosesser for \u00e5 spore, evaluere og beskytte mot katastrofale risikoer fra kraftige modeller\". OpenAIs selvp\u00e5lagte grenser regulerer hvilke modeller som blir frigitt eller videreutviklet. Beredskapsrammeverket resulterer i et scorekort der CBRN-risiko (kjemisk, biologisk, radiologisk og kjernefysisk risiko), modellautonomi, cybersikkerhet og overtalelsesrisiko vurderes som lav, middels, h\u00f8y eller kritisk. Der uakseptable risikoer er identifisert,<\/p>","protected":false},"author":6,"featured_media":14226,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[163,93],"class_list":["post-14221","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-ai-risks","tag-openai"],"yoast_head":"\no1 is smarter but more deceptive with a \u201cmedium\u201d danger level | 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\/nb\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/\" \/>\n<meta property=\"og:locale\" content=\"nb_NO\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level | DailyAI\" \/>\n<meta property=\"og:description\" content=\"OpenAI\u2019s new \u201co1\u201d LLMs, nicknamed Strawberry, display significant improvements over GPT-4o, but the company says this comes with increased risks. OpenAI says it is committed to the safe development of its AI models. To that end, it developed a Preparedness Framework, a set of \u201cprocesses to track, evaluate, and protect against catastrophic risks from powerful models.\u201d OpenAI’s self-imposed limits regulate which models get released or undergo further development. The Preparedness Framework results in a scorecard where CBRN (chemical, biological, radiological, nuclear), model autonomy, cybersecurity, and persuasion risks are rated as low, medium, high, or critical. Where unacceptable risks are identified,\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/nb\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-09-16T08:57:47+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-09-17T05:15:36+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/09\/01-more-intelligent-more-risks.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=\"Eugene van der Watt\" \/>\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=\"Skrevet av\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Ansl. lesetid\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level\",\"datePublished\":\"2024-09-16T08:57:47+00:00\",\"dateModified\":\"2024-09-17T05:15:36+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/\"},\"wordCount\":860,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/01-more-intelligent-more-risks.webp\",\"keywords\":[\"AI risks\",\"OpenAI\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"nb-NO\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/\",\"name\":\"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/01-more-intelligent-more-risks.webp\",\"datePublished\":\"2024-09-16T08:57:47+00:00\",\"dateModified\":\"2024-09-17T05:15:36+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#breadcrumb\"},\"inLanguage\":\"nb-NO\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"nb-NO\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/01-more-intelligent-more-risks.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/01-more-intelligent-more-risks.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level\"}]},{\"@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\":\"nb-NO\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"nb-NO\",\"@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\\\/7ce525c6d0c79838b7cc7cde96993cfa\",\"name\":\"Eugene van der Watt\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"nb-NO\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"caption\":\"Eugene van der Watt\"},\"description\":\"Eugene comes from an electronic engineering background and loves all things tech. When he takes a break from consuming AI news you'll find him at the snooker table.\",\"sameAs\":[\"www.linkedin.com\\\/in\\\/eugene-van-der-watt-16828119\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/nb\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"o1 er smartere, men mer villedende med et \"middels\" fareniv\u00e5 | 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\/nb\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/","og_locale":"nb_NO","og_type":"article","og_title":"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level | DailyAI","og_description":"OpenAI\u2019s new \u201co1\u201d LLMs, nicknamed Strawberry, display significant improvements over GPT-4o, but the company says this comes with increased risks. OpenAI says it is committed to the safe development of its AI models. To that end, it developed a Preparedness Framework, a set of \u201cprocesses to track, evaluate, and protect against catastrophic risks from powerful models.\u201d OpenAI’s self-imposed limits regulate which models get released or undergo further development. The Preparedness Framework results in a scorecard where CBRN (chemical, biological, radiological, nuclear), model autonomy, cybersecurity, and persuasion risks are rated as low, medium, high, or critical. Where unacceptable risks are identified,","og_url":"https:\/\/dailyai.com\/nb\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/","og_site_name":"DailyAI","article_published_time":"2024-09-16T08:57:47+00:00","article_modified_time":"2024-09-17T05:15:36+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/09\/01-more-intelligent-more-risks.webp","type":"image\/webp"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Skrevet av":"Eugene van der Watt","Ansl. lesetid":"5 minutter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level","datePublished":"2024-09-16T08:57:47+00:00","dateModified":"2024-09-17T05:15:36+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/"},"wordCount":860,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/09\/01-more-intelligent-more-risks.webp","keywords":["AI risks","OpenAI"],"articleSection":["Industry"],"inLanguage":"nb-NO"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/","url":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/","name":"o1 er smartere, men mer villedende med et \"middels\" fareniv\u00e5 | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/09\/01-more-intelligent-more-risks.webp","datePublished":"2024-09-16T08:57:47+00:00","dateModified":"2024-09-17T05:15:36+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#breadcrumb"},"inLanguage":"nb-NO","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/"]}]},{"@type":"ImageObject","inLanguage":"nb-NO","@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/09\/01-more-intelligent-more-risks.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/09\/01-more-intelligent-more-risks.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DagligAI","description":"Din daglige dose med 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":"nb-NO"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DagligAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"nb-NO","@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\/7ce525c6d0c79838b7cc7cde96993cfa","name":"Eugene van der Watt","image":{"@type":"ImageObject","inLanguage":"nb-NO","@id":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","caption":"Eugene van der Watt"},"description":"Eugene har bakgrunn som elektroingeni\u00f8r og elsker alt som har med teknologi \u00e5 gj\u00f8re. N\u00e5r han tar en pause fra AI-nyhetene, finner du ham ved snookerbordet.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/nb\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts\/14221","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/comments?post=14221"}],"version-history":[{"count":6,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts\/14221\/revisions"}],"predecessor-version":[{"id":14248,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts\/14221\/revisions\/14248"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/media\/14226"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/media?parent=14221"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/categories?post=14221"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/tags?post=14221"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}