{"id":10653,"date":"2024-03-12T10:07:58","date_gmt":"2024-03-12T10:07:58","guid":{"rendered":"https:\/\/dailyai.com\/?p=10653"},"modified":"2024-03-12T10:07:58","modified_gmt":"2024-03-12T10:07:58","slug":"wmdp-measures-and-reduces-llm-malicious-use-with-unlearning","status":"publish","type":"post","link":"https:\/\/dailyai.com\/sv\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/","title":{"rendered":"WMDP m\u00e4ter och reducerar LLM skadlig anv\u00e4ndning med avinl\u00e4rning"},"content":{"rendered":"

Forskarna lanserade ett riktm\u00e4rke f\u00f6r att m\u00e4ta om en LLM inneh\u00e5ller potentiellt farlig kunskap och en ny teknik f\u00f6r att l\u00e4ra sig bort farlig data.<\/strong><\/p>\n

Det har varit mycket debatt om huruvida AI-modeller kan hj\u00e4lpa d\u00e5liga akt\u00f6rer att bygga en bomb, planera en cybers\u00e4kerhetsattack<\/a>, eller bygga ett biovapen<\/a>.<\/p>\n

Ett team best\u00e5ende av forskare fr\u00e5n Scale AI, Center for AI Safety och experter fr\u00e5n ledande utbildningsinstitutioner har tagit fram ett riktm\u00e4rke som ger oss ett b\u00e4ttre m\u00e5tt p\u00e5 hur farlig en viss LLM \u00e4r.<\/p>\n

Benchmark f\u00f6r Weapons of Mass Destruction Proxy (WMDP) \u00e4r ett dataset med 4 157 flervalsfr\u00e5gor om farliga kunskaper inom bios\u00e4kerhet, cybers\u00e4kerhet och kemikalies\u00e4kerhet.<\/p>\n

Ju h\u00f6gre po\u00e4ng en LLM f\u00e5r p\u00e5 riktm\u00e4rket, desto st\u00f6rre risk utg\u00f6r den f\u00f6r att potentiellt m\u00f6jligg\u00f6ra f\u00f6r en person med kriminella avsikter. En LLM med en l\u00e4gre WMDP-po\u00e4ng \u00e4r mindre ben\u00e4gen att hj\u00e4lpa dig att bygga en bomb eller skapa ett nytt virus.<\/p>\n

Det traditionella s\u00e4ttet att g\u00f6ra en LLM mer anpassad \u00e4r att avvisa f\u00f6rfr\u00e5gningar som ber om data som kan m\u00f6jligg\u00f6ra skadliga handlingar. Jailbreaking eller finjustering<\/a> en anpassad LLM kan ta bort dessa skyddsr\u00e4cken och avsl\u00f6ja farlig kunskap i modellens dataset.<\/p>\n

Om man kan f\u00e5 modellen att gl\u00f6mma eller l\u00e4ra sig den felaktiga informationen, finns det ingen risk f\u00f6r att den oavsiktligt levererar den som svar p\u00e5 n\u00e5gon smart jailbreaking<\/a> teknik.<\/p>\n

I deras forskningsrapport<\/a>f\u00f6rklarar forskarna hur de utvecklade en algoritm som kallas Contrastive Unlearn Tuning (CUT), en finjusteringsmetod f\u00f6r att l\u00e4ra bort farlig kunskap och samtidigt beh\u00e5lla godartad information.<\/p>\n

Finjusteringsmetoden CUT g\u00f6r att maskinen l\u00e4r sig mindre genom att optimera en \"gl\u00f6mma-term\" s\u00e5 att modellen blir mindre expert p\u00e5 farliga \u00e4mnen. Den optimerar ocks\u00e5 en \"beh\u00e5ll-term\" s\u00e5 att den levererar anv\u00e4ndbara svar p\u00e5 godartade f\u00f6rfr\u00e5gningar.<\/p>\n

Eftersom mycket av informationen i LLM:s tr\u00e4ningsdataset har dubbla anv\u00e4ndningsomr\u00e5den \u00e4r det sv\u00e5rt att bara l\u00e4ra sig d\u00e5liga saker och samtidigt beh\u00e5lla anv\u00e4ndbar information. Med hj\u00e4lp av WMDP kunde forskarna bygga \"gl\u00f6m\"- och \"beh\u00e5ll\"-dataset f\u00f6r att styra sin CUT-avl\u00e4rningsteknik.<\/p>\n

Forskarna anv\u00e4nde WMDP f\u00f6r att m\u00e4ta hur sannolikt det var att ZEPHYR-7B-BETA-modellen skulle ge farlig information f\u00f6re och efter avinl\u00e4rning med CUT. Deras tester fokuserade p\u00e5 bio- och cybers\u00e4kerhet.<\/p>\n

De testade sedan modellen f\u00f6r att se om dess allm\u00e4nna prestanda hade f\u00f6rs\u00e4mrats p\u00e5 grund av avinl\u00e4rningsprocessen.<\/p>\n

\"\"
WMPD-noggrannhet och MMLU-prestanda f\u00f6re och efter CUT-avl\u00e4rning. K\u00e4lla: arXiv<\/figcaption><\/figure>\n

Resultaten visar att avinl\u00e4rningsprocessen avsev\u00e4rt minskade noggrannheten i svaren p\u00e5 farliga f\u00f6rfr\u00e5gningar med endast en marginell minskning av modellens prestanda p\u00e5 MMLU-riktm\u00e4rket.<\/p>\n

Tyv\u00e4rr minskar CUT precisionen i svaren f\u00f6r n\u00e4rbesl\u00e4ktade omr\u00e5den som inledande virologi och datas\u00e4kerhet. F\u00f6r att ge ett anv\u00e4ndbart svar p\u00e5 \"Hur stoppar man en cyberattack?\" men inte p\u00e5 \"Hur utf\u00f6r man en cyberattack?\" kr\u00e4vs mer precision i avinl\u00e4rningsprocessen.<\/p>\n

Forskarna fann ocks\u00e5 att de inte kunde utesluta kunskap om farliga kemikalier eftersom den var alltf\u00f6r t\u00e4tt sammanfl\u00e4tad med allm\u00e4n kemisk kunskap.<\/p>\n

Genom att anv\u00e4nda CUT kan leverant\u00f6rer av slutna modeller som GPT-4 l\u00e4ra sig bort farlig information s\u00e5 att de inte kommer ih\u00e5g n\u00e5gon farlig information att leverera, \u00e4ven om de uts\u00e4tts f\u00f6r skadlig finjustering eller jailbreaking.<\/p>\n

Du kan g\u00f6ra samma sak med modeller med \u00f6ppen k\u00e4llkod, men offentlig tillg\u00e5ng till deras vikter inneb\u00e4r att de kan l\u00e4ra sig farliga data igen om de tr\u00e4nas p\u00e5 dem.<\/p>\n

Den h\u00e4r metoden f\u00f6r att f\u00e5 en AI-modell att l\u00e4ra sig farliga data \u00e4r inte idiots\u00e4ker, s\u00e4rskilt inte f\u00f6r modeller med \u00f6ppen k\u00e4llkod, men det \u00e4r ett robust till\u00e4gg till nuvarande inriktning<\/a> metoder.<\/p>","protected":false},"excerpt":{"rendered":"

Forskarna lanserade ett riktm\u00e4rke f\u00f6r att m\u00e4ta om en LLM inneh\u00e5ller potentiellt farlig kunskap och en ny teknik f\u00f6r att l\u00e4ra sig bort farlig data. Det har varit mycket debatt om huruvida AI-modeller kan hj\u00e4lpa d\u00e5liga akt\u00f6rer att bygga en bomb, planera en cybers\u00e4kerhetsattack eller bygga ett biovapen. Teamet med forskare fr\u00e5n Scale AI, Center for AI Safety och experter fr\u00e5n ledande utbildningsinstitutioner har sl\u00e4ppt ett riktm\u00e4rke som ger oss ett b\u00e4ttre m\u00e5tt p\u00e5 hur farlig en viss LLM \u00e4r. Riktm\u00e4rket Weapons of Mass Destruction Proxy (WMDP) \u00e4r en dataset med 4 157 flervalsfr\u00e5gor kring farlig kunskap inom bios\u00e4kerhet,<\/p>","protected":false},"author":6,"featured_media":10656,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[339,118],"class_list":["post-10653","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-ai-safety","tag-llms"],"yoast_head":"\nWMDP measures and reduces LLM malicious use with unlearning | 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\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/\" \/>\n<meta property=\"og:locale\" content=\"sv_SE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"WMDP measures and reduces LLM malicious use with unlearning | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers released a benchmark to measure whether an LLM contains potentially hazardous knowledge and a novel technique for unlearning dangerous data. There has been much debate over whether AI models could help bad actors build a bomb, plan a cybersecurity attack, or build a bioweapon. The team of researchers from Scale AI, the Center for AI Safety, and experts from leading educational institutions, released a benchmark that gives us a better measure of just how dangerous a particular LLM is. The Weapons of Mass Destruction Proxy (WMDP) benchmark is a dataset of 4,157 multiple-choice questions surrounding hazardous knowledge in biosecurity,\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/sv\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-03-12T10:07:58+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/AI-unlearning.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1640\" \/>\n\t<meta property=\"og:image:height\" content=\"924\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\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=\"3 minuter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"WMDP measures and reduces LLM malicious use with unlearning\",\"datePublished\":\"2024-03-12T10:07:58+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/\"},\"wordCount\":583,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/AI-unlearning.jpg\",\"keywords\":[\"AI safety\",\"LLMS\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"sv-SE\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/\",\"name\":\"WMDP measures and reduces LLM malicious use with unlearning | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/AI-unlearning.jpg\",\"datePublished\":\"2024-03-12T10:07:58+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#breadcrumb\"},\"inLanguage\":\"sv-SE\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/AI-unlearning.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/AI-unlearning.jpg\",\"width\":1640,\"height\":924},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"WMDP measures and reduces LLM malicious use with unlearning\"}]},{\"@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":"WMDP m\u00e4ter och minskar LLM-skadlig anv\u00e4ndning med avl\u00e6ring | 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\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/","og_locale":"sv_SE","og_type":"article","og_title":"WMDP measures and reduces LLM malicious use with unlearning | DailyAI","og_description":"Researchers released a benchmark to measure whether an LLM contains potentially hazardous knowledge and a novel technique for unlearning dangerous data. There has been much debate over whether AI models could help bad actors build a bomb, plan a cybersecurity attack, or build a bioweapon. The team of researchers from Scale AI, the Center for AI Safety, and experts from leading educational institutions, released a benchmark that gives us a better measure of just how dangerous a particular LLM is. The Weapons of Mass Destruction Proxy (WMDP) benchmark is a dataset of 4,157 multiple-choice questions surrounding hazardous knowledge in biosecurity,","og_url":"https:\/\/dailyai.com\/sv\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/","og_site_name":"DailyAI","article_published_time":"2024-03-12T10:07:58+00:00","og_image":[{"width":1640,"height":924,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/AI-unlearning.jpg","type":"image\/jpeg"}],"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":"3 minuter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"WMDP measures and reduces LLM malicious use with unlearning","datePublished":"2024-03-12T10:07:58+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/"},"wordCount":583,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/AI-unlearning.jpg","keywords":["AI safety","LLMS"],"articleSection":["Industry"],"inLanguage":"sv-SE"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/","url":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/","name":"WMDP m\u00e4ter och minskar LLM-skadlig anv\u00e4ndning med avl\u00e6ring | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/AI-unlearning.jpg","datePublished":"2024-03-12T10:07:58+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#breadcrumb"},"inLanguage":"sv-SE","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/"]}]},{"@type":"ImageObject","inLanguage":"sv-SE","@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/AI-unlearning.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/AI-unlearning.jpg","width":1640,"height":924},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"WMDP measures and reduces LLM malicious use with unlearning"}]},{"@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\/10653","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=10653"}],"version-history":[{"count":2,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/10653\/revisions"}],"predecessor-version":[{"id":10657,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/10653\/revisions\/10657"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media\/10656"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media?parent=10653"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/categories?post=10653"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/tags?post=10653"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}