{"id":13539,"date":"2024-07-22T10:04:27","date_gmt":"2024-07-22T10:04:27","guid":{"rendered":"https:\/\/dailyai.com\/?p=13539"},"modified":"2024-07-22T10:04:27","modified_gmt":"2024-07-22T10:04:27","slug":"llm-refusal-training-easily-bypassed-with-past-tense-prompts","status":"publish","type":"post","link":"https:\/\/dailyai.com\/sv\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/","title":{"rendered":"LLM-v\u00e4grarutbildning som l\u00e4tt kan kringg\u00e5s med uppmaningar om f\u00f6rfluten tid"},"content":{"rendered":"

Forskare fr\u00e5n Swiss Federal Institute of Technology Lausanne (EPFL) fann att skrivande av farliga uppmaningar i f\u00f6rfluten tid kringgick v\u00e4grarutbildningen f\u00f6r de mest avancerade LLM.<\/strong><\/p>\n

AI-modeller justeras ofta med hj\u00e4lp av tekniker som \u00f6vervakad finjustering (SFT) eller f\u00f6rst\u00e4rkningsinl\u00e4rning med m\u00e4nsklig \u00e5terkoppling (RLHF) f\u00f6r att s\u00e4kerst\u00e4lla att modellen inte svarar p\u00e5 farliga eller o\u00f6nskade uppmaningar.<\/p>\n

Denna v\u00e4grarutbildning b\u00f6rjar n\u00e4r du ber ChatGPT om r\u00e5d om hur man g\u00f6r en bomb eller droger. Vi har t\u00e4ckt en rad olika intressanta jailbreak-tekniker<\/a> som kringg\u00e5r dessa skyddsr\u00e4cken, men den metod som EPFL-forskarna testade \u00e4r den absolut enklaste.<\/p>\n

Forskarna tog ett dataset med 100 skadliga beteenden och anv\u00e4nde GPT-3.5 f\u00f6r att skriva om uppmaningarna i f\u00f6rfluten tid.<\/p>\n

H\u00e4r \u00e4r ett exempel p\u00e5 den metod som f\u00f6rklaras i deras papper<\/a>.<\/p>\n

\"\"
Anv\u00e4nda en LLM f\u00f6r att skriva om farliga uppmaningar i f\u00f6rfluten tid. K\u00e4lla: arXiv<\/figcaption><\/figure>\n

De utv\u00e4rderade sedan svaren p\u00e5 dessa omskrivna uppmaningar fr\u00e5n dessa 8 LLM:er: Llama-3 8B, Claude-3.5 Sonnet, GPT-3.5 Turbo, Gemma-2 9B, Phi-3-Mini, GPT-4o-mini<\/a>, GPT-4o och R2D2.<\/p>\n

De anv\u00e4nde flera LLM:er f\u00f6r att bed\u00f6ma utdata och klassificera dem som antingen ett misslyckat eller ett lyckat f\u00f6rs\u00f6k till jailbreak.<\/p>\n

Att helt enkelt \u00e4ndra tempus i prompten hade en f\u00f6rv\u00e5nansv\u00e4rt betydande effekt p\u00e5 attackens framg\u00e5ngsgrad (ASR). GPT-4o och GPT-4o mini var s\u00e4rskilt mottagliga f\u00f6r denna teknik.<\/p>\n

ASR f\u00f6r denna \"enkla attack p\u00e5 GPT-4o \u00f6kar fr\u00e5n 1% med direkta f\u00f6rfr\u00e5gningar till 88% med 20 omformuleringsf\u00f6rs\u00f6k i f\u00f6rfluten tid p\u00e5 skadliga f\u00f6rfr\u00e5gningar\".<\/p>\n

H\u00e4r \u00e4r ett exempel p\u00e5 hur kompatibel GPT-4o blir n\u00e4r du helt enkelt skriver om uppmaningen i f\u00f6rfluten tid. Jag anv\u00e4nde ChatGPT f\u00f6r detta och s\u00e5rbarheten har inte patchats \u00e4nnu.<\/p>\n

\"\"
ChatGPT som anv\u00e4nder GPT-4o v\u00e4grar en uppmaning i presens, men f\u00f6ljer uppmaningen n\u00e4r den skrivs om i preteritum. K\u00e4lla: ChatGPT ChatGPT<\/figcaption><\/figure>\n

Avvisningstr\u00e4ning med RLHF och SFT tr\u00e4nar en modell att framg\u00e5ngsrikt generalisera f\u00f6r att avvisa skadliga uppmaningar \u00e4ven om den inte har sett den specifika uppmaningen tidigare.<\/p>\n

N\u00e4r uppmaningen \u00e4r skriven i f\u00f6rfluten tid verkar LLM:erna f\u00f6rlora f\u00f6rm\u00e5gan att generalisera. De andra LLM:erna klarade sig inte mycket b\u00e4ttre \u00e4n GPT-4o, \u00e4ven om Llama-3 8B verkade vara mest motst\u00e5ndskraftig.<\/p>\n

\"\"
Framg\u00e5ngsrika attacker med hj\u00e4lp av farliga uppmaningar i nutid och f\u00f6rfluten tid. K\u00e4lla: arXiv<\/figcaption><\/figure>\n

Att skriva om uppmaningen i futurum ledde till en \u00f6kning av ASR men var mindre effektivt \u00e4n att skriva om uppmaningen i pastum.<\/p>\n

Forskarna drog slutsatsen att detta kan bero p\u00e5 att \"de finjusterande dataseten kan inneh\u00e5lla en h\u00f6gre andel skadliga f\u00f6rfr\u00e5gningar som uttrycks i futurum eller som hypotetiska h\u00e4ndelser\".<\/p>\n

De f\u00f6reslog ocks\u00e5 att \"modellens interna resonemang kan tolka framtidsorienterade f\u00f6rfr\u00e5gningar som potentiellt mer skadliga, medan uttalanden i f\u00f6rfluten tid, till exempel historiska h\u00e4ndelser, kan uppfattas som mer godartade.\"<\/p>\n

Kan det \u00e5tg\u00e4rdas?<\/h2>\n

Ytterligare experiment visade att om man lade till uppmaningar om f\u00f6rfluten tid i de finjusterande dataseten minskade k\u00e4nsligheten f\u00f6r denna jailbreak-teknik effektivt.<\/p>\n

Denna metod \u00e4r visserligen effektiv, men kr\u00e4ver att man f\u00f6regriper de typer av farliga uppmaningar som en anv\u00e4ndare kan mata in.<\/p>\n

Forskarna menar att det \u00e4r en enklare l\u00f6sning att utv\u00e4rdera resultatet av en modell innan den presenteras f\u00f6r anv\u00e4ndaren.<\/p>\n

S\u00e5 enkelt som detta jailbreak \u00e4r verkar det inte som om de ledande AI-f\u00f6retagen har hittat ett s\u00e4tt att fixa det \u00e4nnu.<\/p>","protected":false},"excerpt":{"rendered":"

Forskare fr\u00e5n Swiss Federal Institute of Technology Lausanne (EPFL) fann att skrivande av farliga uppmaningar i f\u00f6rfluten tid kringgick v\u00e4gransutbildningen f\u00f6r de mest avancerade LLM: erna. AI-modeller anpassas vanligtvis med tekniker som \u00f6vervakad finjustering (SFT) eller f\u00f6rst\u00e4rkningsinl\u00e4rning m\u00e4nsklig feedback (RLHF) f\u00f6r att se till att modellen inte svarar p\u00e5 farliga eller o\u00f6nskade uppmaningar. Denna v\u00e4gransutbildning startar n\u00e4r du ber ChatGPT om r\u00e5d om hur man g\u00f6r en bomb eller droger. Vi har t\u00e4ckt en rad intressanta jailbreak-tekniker som kringg\u00e5r dessa skyddsr\u00e4cken men den metod som EPFL-forskarna testade \u00e4r \u00f6verl\u00e4gset den enklaste.<\/p>","protected":false},"author":6,"featured_media":13544,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[163,118],"class_list":["post-13539","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-ai-risks","tag-llms"],"yoast_head":"\nLLM refusal training easily bypassed with past tense prompts | 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\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/\" \/>\n<meta property=\"og:locale\" content=\"sv_SE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"LLM refusal training easily bypassed with past tense prompts | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers from the Swiss Federal Institute of Technology Lausanne (EPFL) found that writing dangerous prompts in the past tense bypassed the refusal training of the most advanced LLMs. AI models are commonly aligned using techniques like supervised fine-tuning (SFT) or reinforcement learning human feedback (RLHF) to make sure the model doesn\u2019t respond to dangerous or undesirable prompts. This refusal training kicks in when you ask ChatGPT for advice on how to make a bomb or drugs. We\u2019ve covered a range of interesting jailbreak techniques that bypass these guardrails but the method the EPFL researchers tested is by far the simplest.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/sv\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-07-22T10:04:27+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/07\/Jailbreak-AI-model-with-past-tense.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=\"4 minuter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"LLM refusal training easily bypassed with past tense prompts\",\"datePublished\":\"2024-07-22T10:04:27+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\\\/\"},\"wordCount\":569,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/07\\\/Jailbreak-AI-model-with-past-tense.webp\",\"keywords\":[\"AI risks\",\"LLMS\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"sv-SE\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\\\/\",\"name\":\"LLM refusal training easily bypassed with past tense prompts | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/07\\\/Jailbreak-AI-model-with-past-tense.webp\",\"datePublished\":\"2024-07-22T10:04:27+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\\\/#breadcrumb\"},\"inLanguage\":\"sv-SE\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/07\\\/Jailbreak-AI-model-with-past-tense.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/07\\\/Jailbreak-AI-model-with-past-tense.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"LLM refusal training easily bypassed with past tense prompts\"}]},{\"@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":"LLM-v\u00e4gran utbildning l\u00e4tt kringg\u00e5s med uppmaningar om f\u00f6rfluten tid | 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\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/","og_locale":"sv_SE","og_type":"article","og_title":"LLM refusal training easily bypassed with past tense prompts | DailyAI","og_description":"Researchers from the Swiss Federal Institute of Technology Lausanne (EPFL) found that writing dangerous prompts in the past tense bypassed the refusal training of the most advanced LLMs. AI models are commonly aligned using techniques like supervised fine-tuning (SFT) or reinforcement learning human feedback (RLHF) to make sure the model doesn\u2019t respond to dangerous or undesirable prompts. This refusal training kicks in when you ask ChatGPT for advice on how to make a bomb or drugs. We\u2019ve covered a range of interesting jailbreak techniques that bypass these guardrails but the method the EPFL researchers tested is by far the simplest.","og_url":"https:\/\/dailyai.com\/sv\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/","og_site_name":"DailyAI","article_published_time":"2024-07-22T10:04:27+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/07\/Jailbreak-AI-model-with-past-tense.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":"4 minuter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"LLM refusal training easily bypassed with past tense prompts","datePublished":"2024-07-22T10:04:27+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/"},"wordCount":569,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/07\/Jailbreak-AI-model-with-past-tense.webp","keywords":["AI risks","LLMS"],"articleSection":["Industry"],"inLanguage":"sv-SE"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/","url":"https:\/\/dailyai.com\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/","name":"LLM-v\u00e4gran utbildning l\u00e4tt kringg\u00e5s med uppmaningar om f\u00f6rfluten tid | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/07\/Jailbreak-AI-model-with-past-tense.webp","datePublished":"2024-07-22T10:04:27+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/#breadcrumb"},"inLanguage":"sv-SE","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/"]}]},{"@type":"ImageObject","inLanguage":"sv-SE","@id":"https:\/\/dailyai.com\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/07\/Jailbreak-AI-model-with-past-tense.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/07\/Jailbreak-AI-model-with-past-tense.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/07\/llm-refusal-training-easily-bypassed-with-past-tense-prompts\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"LLM refusal training easily bypassed with past tense prompts"}]},{"@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\/13539","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=13539"}],"version-history":[{"count":3,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/13539\/revisions"}],"predecessor-version":[{"id":13546,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/13539\/revisions\/13546"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media\/13544"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media?parent=13539"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/categories?post=13539"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/tags?post=13539"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}