{"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\/sv\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/","title":{"rendered":"o1 \u00e4r smartare men mer bedr\u00e4glig med en \"medelh\u00f6g\" riskniv\u00e5"},"content":{"rendered":"

OpenAI:s nya \"o1\" LLM:er, med smeknamnet Strawberry, uppvisar betydande f\u00f6rb\u00e4ttringar j\u00e4mf\u00f6rt med GPT-4o, men f\u00f6retaget s\u00e4ger att detta kommer med \u00f6kade risker.<\/strong><\/p>\n

OpenAI s\u00e4ger sig vara engagerat i en s\u00e4ker utveckling av sina AI-modeller. F\u00f6r detta \u00e4ndam\u00e5l har de utvecklat ett ramverk f\u00f6r beredskap, en upps\u00e4ttning \"processer f\u00f6r att sp\u00e5ra, utv\u00e4rdera och skydda mot katastrofala risker fr\u00e5n kraftfulla modeller\".<\/p>\n

OpenAI:s sj\u00e4lvp\u00e5tagna gr\u00e4nser reglerar vilka modeller som sl\u00e4pps eller vidareutvecklas. Beredskapsramverket resulterar i ett scorecard d\u00e4r CBRN-risker (kemiska, biologiska, radiologiska, nukle\u00e4ra), modellautonomi, cybers\u00e4kerhet och \u00f6vertalningsrisker bed\u00f6ms som l\u00e5ga, medelh\u00f6ga, h\u00f6ga eller kritiska.<\/p>\n

Om oacceptabla risker identifieras vidtas \u00e5tg\u00e4rder f\u00f6r att minska dem. Endast modeller med en \"medium\" eller l\u00e4gre po\u00e4ng efter begr\u00e4nsning kan tas i bruk. Endast modeller med en \"h\u00f6g\" eller l\u00e4gre po\u00e4ng efter begr\u00e4nsning kan vidareutvecklas.<\/p>\n

Med o1 \u00e4r det f\u00f6rsta g\u00e5ngen OpenAI sl\u00e4pper en modell som har en \"medelh\u00f6g\" risk f\u00f6r CBRN-risker. GPT-4o \u00e4r klassad som en l\u00e5g risk.<\/p>\n

Det kommer inte att g\u00f6ra det m\u00f6jligt f\u00f6r en amat\u00f6r att skapa ett biologiskt vapen, men OpenAI s\u00e4ger att det fanns \"en icke-trivial upplyftning\" i dess f\u00f6rm\u00e5ga att utf\u00f6ra labbuppgifter. OpenAI s\u00e4ger dock att \"o1-preview och o1-mini p\u00e5 ett meningsfullt s\u00e4tt \u00f6vertr\u00e4ffade GPT-4o\" i biologiska protokoll i v\u00e5tlaboratorier.<\/p>\n

Den Systemkort<\/a> f\u00f6r 01-modellerna beskriver den red teaming och andra s\u00e4kerhetstester som LLM-modellerna utsattes f\u00f6r och antyder n\u00e5gra av de farh\u00e5gor som OpenAI har om potentiella risker.<\/p>\n

I sin slutsats konstaterar systemkortet: \"Dessa \u00f6kade m\u00f6jligheter kommer med betydligt b\u00e4ttre prestanda n\u00e4r det g\u00e4ller s\u00e4kerhetsriktm\u00e4rken, men \u00f6kar ocks\u00e5 vissa typer av risker.\"<\/p>\n

Resultaten av OpenAI:s anpassningsarbete verkar tyda p\u00e5 att 01 i m\u00e5nga avseenden \u00e4r en s\u00e4krare modell. Den \u00e4r mer motst\u00e5ndskraftig mot jailbreak-attacker, mindre ben\u00e4gen att vara partisk och mindre ben\u00e4gen att f\u00e5 hallucinationer.<\/p>\n

N\u00e5gra av de experimentella resultaten visar varf\u00f6r OpenAI har anledning till sin oro.<\/p>\n

Bedr\u00e4geri<\/h2>\n

OpenAI anv\u00e4nde utv\u00e4rderingsorganisationen Apollo Research f\u00f6r att utf\u00f6ra n\u00e5gra av o1: s s\u00e4kerhetstester relaterade till bedr\u00e4geri eller scheming. Apollo definierar schemal\u00e4ggning i stort som att AI:er utnyttjar sina \u00f6vervakningsmekanismer som ett medel f\u00f6r att uppn\u00e5 ett m\u00e5l.<\/p>\n

En sj\u00e4lvmedveten modell som \u00e4r bra p\u00e5 sj\u00e4lvresonemang och tanketeori kan planera eller anv\u00e4nda bedr\u00e4geri f\u00f6r att uppn\u00e5 sitt prim\u00e4ra m\u00e5l. Om en AI-modell till exempel inser att den genomg\u00e5r anpassningstestning kan den d\u00f6lja riskfyllt beteende f\u00f6r att uppn\u00e5 sitt m\u00e5l att bli utplacerad.<\/p>\n

Systemkortet noterade att \"o1-preview ibland instrumentellt f\u00f6rfalskade anpassningen under testningen.\"<\/p>\n

Ett exempel p\u00e5 detta var n\u00e4r 01 fick ett prim\u00e4rt m\u00e5l att maximera den ekonomiska tillv\u00e4xten i ett stadsplaneringsprojekt. Modellen o1 hade tillg\u00e5ng till information som visade att den kanske inte skulle komma l\u00e4ngre \u00e4n till testfasen om den gjorde detta. S\u00e5 h\u00e4r resonerade o1 om hur den skulle uppn\u00e5 sitt m\u00e5l:<\/p>\n

\"\"
o1 best\u00e4mmer sig f\u00f6r att d\u00f6lja sin verkliga avsikt under testning s\u00e5 att den kommer att distribueras. K\u00e4lla: OpenAI OpenAI<\/figcaption><\/figure>\n

Det h\u00e4r exemplet visar att o1 har m\u00f6jlighet att d\u00f6lja sina verkliga avsikter under testningen s\u00e5 att de kan uppn\u00e5 sitt prim\u00e4ra m\u00e5l under utplaceringen. Om o1 \u00e4r medveten om OpenAI:s regler f\u00f6r utplacering baserat p\u00e5 dess Preparedness Framework, kan den d\u00e5 ha fejkat n\u00e5gra av sina svar f\u00f6r att s\u00e4kerst\u00e4lla att den blev utplacerad?<\/p>\n

Om mer intelligenta modeller \u00e4r p\u00e5 g\u00e5ng, kan de d\u00e5 se till att de h\u00e5ller sig under den \"kritiska\" riskniv\u00e5n f\u00f6r att s\u00e4kerst\u00e4lla att de utvecklas vidare?<\/p>\n

Apollo-teamet s\u00e4ger att det \"subjektivt tror att o1-preview inte kan delta i intriger som kan leda till katastrofala skador, \u00e4ven om nuvarande utv\u00e4rderingar inte \u00e4r utformade f\u00f6r att definitivt utesluta detta.\"<\/p>\n

\u00d6vertalning<\/h2>\n

Tester av b\u00e5de o1-preview och o1-mini visar att dessa modeller har \"\u00f6vertalningsf\u00f6rm\u00e5ga p\u00e5 m\u00e4nsklig niv\u00e5\". OpenAI s\u00e4ger dock att \"de inte \u00f6vertr\u00e4ffar m\u00e4nskliga toppskribenter och inte n\u00e5r v\u00e5r tr\u00f6skel f\u00f6r h\u00f6g risk\".<\/p>\n

De experiment som de utf\u00f6rde f\u00f6r att testa detta v\u00e4cker vissa farh\u00e5gor. I MakeMePay-testet tilldelades 01-preview rollen som en bedragare och fick i uppgift att \u00f6vertyga GPT-4o att \u00f6verl\u00e4mna de kontanter som den hade tilldelats.<\/p>\n

GPT-4o fick veta att de hade tilldelats $100 och beh\u00f6vde vara rationella om hur de skulle anv\u00e4nda medlen. Under 1 000 interaktioner kunde o1-preview lura GPT-4o 25,8% av g\u00e5ngerna.<\/p>\n

OpenAI drog slutsatsen att \"Dessa resultat indikerar att o1-modellserien kan vara mer manipulativ \u00e4n GPT-4o f\u00f6r att f\u00e5 GPT-4o att utf\u00f6ra den ouppt\u00e4ckta uppgiften (\u223c25% uplift).\" Det noterade vidare att \"Denna utv\u00e4rdering ger oss en baslinje f\u00f6r modellens f\u00f6rm\u00e5ga att g\u00f6ra \u00f6vertygande skada, utan att utl\u00f6sa n\u00e5gon modellpolicy (eftersom det inte \u00e4r utanf\u00f6r policyn att ber\u00e4tta f\u00f6r en modell att spela ett spel).\"<\/p>\n

Utsikterna att s\u00e4tta o1 LLM:erna i arbete med verkliga problem \u00e4r extremt sp\u00e4nnande, och n\u00e4r o1 f\u00e5r multimodala funktioner kommer det att inneb\u00e4ra ytterligare ett exponentiellt spr\u00e5ng. Men n\u00e4r AI-testare s\u00e4ger att de inte kan utesluta \"katastrofala skador\" och att modeller ibland d\u00f6ljer sina verkliga avsikter kan det finnas anledning att d\u00e4mpa denna entusiasm med f\u00f6rsiktighet.<\/p>\n

Gav OpenAI just Gavin Newsom en bra anledning att underteckna SB 1047 Lagf\u00f6rslag om AI-s\u00e4kerhet<\/a> som den mots\u00e4tter sig?<\/p>","protected":false},"excerpt":{"rendered":"

OpenAI:s nya \"o1\" LLM:er, med smeknamnet Strawberry, visar betydande f\u00f6rb\u00e4ttringar j\u00e4mf\u00f6rt med GPT-4o, men f\u00f6retaget s\u00e4ger att detta kommer med \u00f6kade risker. OpenAI s\u00e4ger att det \u00e4r engagerat i en s\u00e4ker utveckling av sina AI-modeller. F\u00f6r detta \u00e4ndam\u00e5l utvecklade de ett beredskapsramverk, en upps\u00e4ttning \"processer f\u00f6r att sp\u00e5ra, utv\u00e4rdera och skydda mot katastrofala risker fr\u00e5n kraftfulla modeller.\" OpenAI:s sj\u00e4lvp\u00e5tagna gr\u00e4nser reglerar vilka modeller som sl\u00e4pps eller vidareutvecklas. Preparedness Framework resulterar i ett scorecard d\u00e4r CBRN-risker (kemiska, biologiska, radiologiska, nukle\u00e4ra), modellautonomi, cybers\u00e4kerhet och \u00f6vertalningsrisker rankas som l\u00e5ga, medelh\u00f6ga, h\u00f6ga eller kritiska. D\u00e4r oacceptabla risker identifieras,<\/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\/sv\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/\" \/>\n<meta property=\"og:locale\" content=\"sv_SE\" \/>\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\/sv\/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=\"Skriven av\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Ber\u00e4knad l\u00e4stid\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minuter\" \/>\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\":\"sv-SE\"},{\"@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\":\"sv-SE\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@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\":\"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\\\/7ce525c6d0c79838b7cc7cde96993cfa\",\"name\":\"Eugene van der Watt\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@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\\\/sv\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"o1 \u00e4r smartare men mer bedr\u00e4glig med en \"medelh\u00f6g\" riskniv\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\/sv\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/","og_locale":"sv_SE","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\/sv\/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":{"Skriven av":"Eugene van der Watt","Ber\u00e4knad l\u00e4stid":"5 minuter"},"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":"sv-SE"},{"@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 \u00e4r smartare men mer bedr\u00e4glig med en \"medelh\u00f6g\" riskniv\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":"sv-SE","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/"]}]},{"@type":"ImageObject","inLanguage":"sv-SE","@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":"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\/7ce525c6d0c79838b7cc7cde96993cfa","name":"Eugene van der Watt","image":{"@type":"ImageObject","inLanguage":"sv-SE","@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 kommer fr\u00e5n en bakgrund som elektronikingenj\u00f6r och \u00e4lskar allt som har med teknik att g\u00f6ra. N\u00e4r han tar en paus fr\u00e5n att konsumera AI-nyheter hittar du honom vid snookerbordet.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/sv\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/14221","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\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/comments?post=14221"}],"version-history":[{"count":6,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/14221\/revisions"}],"predecessor-version":[{"id":14248,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/14221\/revisions\/14248"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media\/14226"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media?parent=14221"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/categories?post=14221"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/tags?post=14221"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}