[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"portal-settings:stajic:it":3,"public-menus:all":38,"post:new-qwen-3-5-plus:it":205,"related:post:new-qwen-3-5-plus:it:1":450},{"statusCode":4,"data":5,"message":37},200,{"tenantId":6,"lang":7,"defaultLang":8,"siteUrl":9,"contactEmail":10,"brandName":11,"logoUrl":12,"siteName":11,"siteDescription":13,"ogImage":10,"robotsIndex":14,"socialLinks":10,"reservedSlugs":10,"seoPolicy":15},"stajic","it","de","https:\u002F\u002Fstajic.de",null,"Stajic Platform","\u002FLogo_Planet.svg","Stajic Portal",true,{"branding":16,"relatedContent":17,"crossDomainLinks":18},{"logoUrl":12},{"enabled":14},[19,22,25,28,31,34],{"url":20,"label":21,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Ffigure.rocks","figure.rocks",{"url":23,"label":24,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Floving.rocks","loving.rocks",{"url":26,"label":27,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.com","bazify.com",{"url":29,"label":30,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.de","bazify.de",{"url":32,"label":33,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.at","bazify.at",{"url":35,"label":36,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.ba","bazify.ba","Portal settings resolved",[39,45],{"id":40,"name":41,"location":42,"isActive":14,"isDefault":43,"items":44},1,"main-navigation","header",false,[],{"id":46,"name":47,"location":48,"isActive":14,"isDefault":14,"items":49},4,"main-menu","sidebar",[50,66,79,93,103,118,133],{"id":51,"title":52,"url":60,"target":61,"icon":62,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":64,"portfolioId":10,"children":65},"item-18",{"de":53,"en":54,"es":55,"fr":56,"it":54,"ru":57,"sr":58,"zh":59},"Startseite","Home","Inicio","Accueil","Главная","Почетна","首页","\u002Ffull-stack-web-developer-munich-performance-seo-and-maintainable-builds","_self","i-lucide-home","page",111,[],{"id":67,"title":68,"url":75,"target":61,"icon":76,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":77,"portfolioId":10,"children":78},"item-22",{"de":69,"en":69,"es":70,"fr":69,"it":71,"ru":72,"sr":73,"zh":74},"Vision","Visión","Visione","Видение","Визија","想象","\u002Fueber-uns-webdesign-muenchen-webaplikation","i-lucide-eye",113,[],{"id":80,"title":81,"url":89,"target":61,"icon":90,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":91,"portfolioId":10,"children":92},"item-19",{"de":82,"en":83,"es":84,"fr":83,"it":85,"ru":86,"sr":87,"zh":88},"Leistungen","Services","Servicios","Servizi","Услуги","Услуге","服务","\u002Fservices-dienstleistungen-muenchen","i-lucide-wrench",116,[],{"id":94,"title":95,"url":99,"target":61,"icon":100,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":101,"portfolioId":10,"children":102},"item-23",{"de":96,"en":96,"es":96,"fr":96,"it":96,"ru":97,"sr":97,"zh":98},"Blog","Блог","博客","\u002Fblog","i-lucide-book-open",112,[],{"id":104,"title":105,"url":114,"target":61,"icon":115,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":116,"portfolioId":10,"children":117},"item-32",{"de":106,"en":107,"es":108,"fr":109,"it":110,"ru":111,"sr":112,"zh":113},"Neue Technologien","New Technologies","Nuevas tecnologías","Nouvelles technologies","Nuove tecnologie","Новые технологии","Нове технологије","新技术！","\u002Fneue-webtechnologien","i-lucide-sparkles",122,[],{"id":119,"title":120,"url":129,"target":61,"icon":130,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":131,"portfolioId":10,"children":132},"item-20",{"de":121,"en":122,"es":123,"fr":124,"it":125,"ru":126,"sr":127,"zh":128},"Kontakt","Contact us!","Contacto","Contact","Contatto","Контакт","Контактирајте нас","联系我们！","\u002Fcontact","i-lucide-mail",115,[],{"id":134,"title":135,"url":144,"target":61,"icon":145,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":146,"portfolioId":10,"children":147},"item-21",{"de":136,"en":137,"es":138,"fr":139,"it":140,"ru":141,"sr":142,"zh":143},"Unsere Arbeit","Our Work","Nuestro trabajo","Nos réalisations","I nostri lavori","Наши работы","Наши радови","文件夹","\u002Fportfolio","i-lucide-briefcase",114,[148,161,175,181,193],{"id":149,"title":150,"url":144,"target":61,"icon":159,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":146,"portfolioId":10,"children":160},"item-24",{"de":151,"en":152,"es":153,"fr":154,"it":155,"ru":156,"sr":157,"zh":158},"Alle Projekte","All Projects","Todos los proyectos","Tous les projets","Tutti i progetti","Все проекты","Сви пројекти","所有项目","i-lucide-grid-3x3",[],{"id":162,"title":163,"url":171,"target":61,"icon":172,"isActive":14,"type":173,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":10,"children":174},"item-29",{"de":164,"en":165,"es":166,"fr":167,"it":168,"ru":169,"sr":170,"zh":143},"Local Roots, Global Reach","Local Roots - Global Reach","Empresa local ","Entreprise locale","Azienda locale","Местная компания","Локално предузеће глобално тржиште","\u002Fportfolio\u002Flocal-roots-global-reach-communication-media-systems-for-modern-business","i-lucide-folder","custom",[],{"id":176,"title":177,"url":179,"target":61,"icon":172,"isActive":14,"type":173,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":10,"children":180},"item-28",{"de":178,"en":178,"es":178,"fr":178,"it":178,"ru":178,"sr":178,"zh":178},"Solr Suggester","\u002Fportfolio\u002Fsolr-fuzzy-suggester-und-solr-infix-suggester-abfrage-ueber-ajax-und-filterung",[],{"id":182,"title":183,"url":191,"target":61,"icon":172,"isActive":14,"type":173,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":10,"children":192},"item-27",{"de":184,"en":185,"es":186,"fr":187,"it":188,"ru":189,"sr":190,"zh":185},"Firmenwebseite SEO","Company Website SEO","Sitio web corporativo SEO","Site web d’entreprise SEO","Sito web aziendale SEO","Корпоративный сайт SEO","Пословна веб-страница SEO","\u002Fportfolio\u002Fseo-sem-branding-mobile-webseite-muenchen",[],{"id":194,"title":195,"url":203,"target":61,"icon":172,"isActive":14,"type":173,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":10,"children":204},"item-31",{"de":196,"en":197,"es":198,"fr":199,"it":200,"ru":201,"sr":202,"zh":197},"Digitalisierungsportal","Digitalization Portal","Portal de digitalización","Portail de numérisation","Portale di digitalizzazione","Портал цифровизации","Портал за дигитализацију","\u002Fportfolio\u002Fdigitalisierungsportal-archiv-museum-bibliothek-ead-lido-mets-mods",[],{"statusCode":4,"data":206,"message":449},{"id":207,"title":208,"slug":209,"content":210,"contentJson":211,"excerpt":303,"featuredImage":304,"featuredImageAlt":305,"featuredImageCaption":10,"featuredImageTitle":10,"featuredImageCopyright":10,"featuredImageAuthor":10,"featuredImageSourceUrl":10,"featuredImageLicense":10,"featuredImageIsAiGenerated":43,"status":306,"publishedAt":307,"createdAt":308,"updatedAt":309,"seoLocalePaths":310,"categories":319,"author":336,"translations":341},"384","Nuovo Qwen 3.5-Plus: l'IA open-source fa sul serio","new-qwen-3-5-plus","\u003Ch2>Qwen 3.5-Plus: l'IA open-source \"agentica\" che riduce l'attrito per gli sviluppatori nei task complessi\u003C\u002Fh2>\n\u003Cp>Alibaba ha rilasciato \u003Cb>Qwen 3.5\u003C\u002Fb> e ha evidenziato in particolare \u003Cb>Qwen 3.5-Plus\u003C\u002Fb> come modello progettato per il lavoro \u003Ci>agentico\u003C\u002Fi>: pianificazione, utilizzo di strumenti ed esecuzione di compiti multi-step con un'efficienza significativamente maggiore. Il messaggio è chiaro: meno \"magia dei prompt\", più esecuzione affidabile — e con un contesto che arriva fino a \u003Cb>1M di token\u003C\u002Fb> sulla variante Plus.\u003C\u002Fp>\n\u003Ch3>Perché questo è importante per gli sviluppatori\u003C\u002Fh3>\n\u003Cp>Se stai costruendo agenti di produzione (RAG, copilot, bot automatici per la revisione del codice, data-pipeline, tester UI), il problema principale non è \"se il modello sa qualcosa\", ma: \u003Cb>se può gestire coerentemente il workflow\u003C\u002Fb> senza interrompersi al sesto passaggio. Qwen 3.5-Plus punta proprio a questa zona — con un ampio contesto, input multimodale e comportamento di utilizzo degli strumenti integrato.\u003C\u002Fp>\n\u003Cblockquote class=\"border-l-4 border-gray-300 pl-4 italic\">Questo è un modello che cerca di trasformare l'LLM da una \"UI di chat\" in un \u003Cb>livello esecutivo\u003C\u002Fb>: vede, pianifica, usa strumenti e completa il lavoro.\u003Ccite class=\"block mt-2 text-sm\">— Come Qwen 3.5 posiziona la direzione \"agentica\"\u003C\u002Fcite>\u003C\u002Fblockquote>\n\u003Ch3>Le novità più importanti (Qwen 3.5-Plus nella pratica)\u003C\u002Fh3>\n\u003Cul>\u003Cli>\u003Cb>Contesto da 1M\u003C\u002Fb>: in concreto significa che puoi inserire ampi frammenti di codebase, log, specifiche e lunghe conversazioni senza dover ricorrere costantemente al \"chunking\".\u003C\u002Fli>\u003Cli>\u003Cb>Uso adattivo degli strumenti\u003C\u002Fb>: il modello è addestrato a decidere autonomamente quando richiamare uno strumento (ricerca, esecuzione di codice, browser, funzioni) invece di fare tutto \"a mente\".\u003C\u002Fli>\u003Cli>\u003Cb>Multimodale + \"agente visivo\"\u003C\u002Fb>: comprende immagini\u002Fdocumenti e punta a operare su applicazioni desktop\u002Fmobile (un agente in grado di \"cliccare\" ed eseguire passaggi).\u003C\u002Fli>\u003Cli>\u003Cb>Efficienza (MoE \u002F architettura)\u003C\u002Fb>: focus su maggiore throughput e costi inferiori; Alibaba nelle dichiarazioni pubbliche sottolinea costi significativamente più bassi e una migliore scalabilità dei carichi di lavoro.\u003C\u002Fli>\u003Cli>\u003Cb>Ecosistema aperto\u003C\u002Fb>: la serie include versioni open-weight e strumenti (repo, formati HF), mentre la versione Plus è spesso offerta come modello hosted per latenza e stabilità di produzione.\u003C\u002Fli>\u003C\u002Ful>\n\u003Cdiv class=\"ce-delimiter cdx-block my-8\">\u003C\u002Fdiv>\n\u003Ch3>Come provarlo velocemente (senza troppi giri di parole)\u003C\u002Fh3>\n\u003Cp>La via più rapida è attraverso un provider che ospita già Qwen 3.5-Plus (ad esempio, un gateway\u002Faggregatore o un cloud studio). Se hai già un'app che utilizza un'API in stile \"chat completions\", la migrazione consiste principalmente nel cambiare il nome del modello e verificare i limiti di contesto e strumenti.\u003C\u002Fp>\n\u003Cpre class=\"code-block\" data-lang=\"javascript\">\u003Ccode class=\"language-javascript\">\u002F\u002F Esempio minimo (pseudo): sostituisci endpoint\u002FSDK in base al provider\nimport OpenAI from "openai";\n\nconst client = new OpenAI({ apiKey: process.env.API_KEY, baseURL: process.env.BASE_URL });\n\nconst res = await client.chat.completions.create({\n  model: "qwen3.5-plus",\n  messages: [\n    { role: "system", content: "Sei un agente che completa i task." },\n    { role: "user", content: "Analizza questo repository e suggerisci 5 miglioramenti per la sicurezza." }\n  ]\n});\n\nconsole.log(res.choices[0].message.content);\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Ch3>Casi d'uso in cui Qwen 3.5-Plus ha un vantaggio reale\u003C\u002Fh3>\n\u003Col>\u003Cli>\u003Cb>RAG agentico su grandi corpora\u003C\u002Fb>: contesto da 1M + uso di strumenti riduce la necessità di una sintetizzazione aggressiva.\u003C\u002Fli>\u003Cli>\u003Cb>Coding a livello di repository\u003C\u002Fb>: analisi di più file + generazione di PR con un piano coerente (meno \"patchwork casuale\").\u003C\u002Fli>\u003Cli>\u003Cb>Automazione UI\u002FQA\u003C\u002Fb>: input multimodale + direzione \"agente visivo\" per test end-to-end e riproduzione di bug da screencast\u002Fscreenshot.\u003C\u002Fli>\u003Cli>\u003Cb>Analisi Ops\u002Fincidenti\u003C\u002Fb>: grandi quantità di log + esecuzione di runbook con strumenti (ricerca, query, ticketing).\u003C\u002Fli>\u003Cli>\u003Cb>Agente per workflow di dati\u003C\u002Fb>: generazione di SQL, validazione dei risultati, correzioni iterative — tutto in una singola sessione senza perdere il contesto.\u003C\u002Fli>\u003C\u002Fol>\n\u003Ch3>Compromessi (per non cadere nella trappola dell'hype)\u003C\u002Fh3>\n\u003Cul>\u003Cli>\u003Cb>Contesto da 1M ≠ 1M di \"memoria perfetta\"\u003C\u002Fb>: più grande è l'input, più è necessario prestare attenzione alla struttura (sezionamento, indice, piano di recupero).\u003C\u002Fli>\u003Cli>\u003Cb>Il comportamento agentico richiede guardrail\u003C\u002Fb>: è obbligatorio aggiungere un livello di policy (strumenti consentiti, rate limit, sandbox), logging e replay.\u003C\u002Fli>\u003Cli>\u003Cb>Hosted vs open-weight\u003C\u002Fb>: Plus come modello hosted è ottimo per latenza\u002Fstabilità, ma le varianti open-weight sono migliori per la privacy e il controllo on-prem — a fronte di un maggiore carico operativo.\u003C\u002Fli>\u003C\u002Ful>\n\u003Cp>\u003Cb>In sintesi:\u003C\u002Fb> Qwen 3.5-Plus è il segnale che la corsa si sta spostando da \"chi è più intelligente in chat\" a \"chi esegue in modo più affidabile workflow complessi\". Se sviluppi agenti in produzione, vale la pena testarlo — specialmente quando il collo di bottiglia è il contesto, l'uso degli strumenti e la stabilità attraverso più passaggi.\u003C\u002Fp>",{"time":212,"blocks":213,"version":302},1771515802747,[214,219,224,229,233,240,244,255,259,263,267,273,277,287,291,298],{"id":215,"data":216,"type":42},"qwen35p-hero",{"text":217,"level":218},"Qwen 3.5-Plus: l'IA open-source \"agentica\" che riduce l'attrito per gli sviluppatori nei task complessi",2,{"id":220,"data":221,"type":223},"qwen35p-lead",{"text":222},"Alibaba ha rilasciato \u003Cb>Qwen 3.5\u003C\u002Fb> e ha evidenziato in particolare \u003Cb>Qwen 3.5-Plus\u003C\u002Fb> come modello progettato per il lavoro \u003Ci>agentico\u003C\u002Fi>: pianificazione, utilizzo di strumenti ed esecuzione di compiti multi-step con un'efficienza significativamente maggiore. Il messaggio è chiaro: meno \"magia dei prompt\", più esecuzione affidabile — e con un contesto che arriva fino a \u003Cb>1M di token\u003C\u002Fb> sulla variante Plus.","paragraph",{"id":225,"data":226,"type":42},"qwen35p-why",{"text":227,"level":228},"Perché questo è importante per gli sviluppatori",3,{"id":230,"data":231,"type":223},"qwen35p-why-p",{"text":232},"Se stai costruendo agenti di produzione (RAG, copilot, bot automatici per la revisione del codice, data-pipeline, tester UI), il problema principale non è \"se il modello sa qualcosa\", ma: \u003Cb>se può gestire coerentemente il workflow\u003C\u002Fb> senza interrompersi al sesto passaggio. Qwen 3.5-Plus punta proprio a questa zona — con un ampio contesto, input multimodale e comportamento di utilizzo degli strumenti integrato.",{"id":234,"data":235,"type":239},"qwen35p-quote",{"text":236,"caption":237,"alignment":238},"Questo è un modello che cerca di trasformare l'LLM da una \"UI di chat\" in un \u003Cb>livello esecutivo\u003C\u002Fb>: vede, pianifica, usa strumenti e completa il lavoro.","Come Qwen 3.5 posiziona la direzione \"agentica\"","left","quote",{"id":241,"data":242,"type":42},"qwen35p-features",{"text":243,"level":228},"Le novità più importanti (Qwen 3.5-Plus nella pratica)",{"id":245,"data":246,"type":254},"qwen35p-features-list",{"items":247,"style":253},[248,249,250,251,252],"\u003Cb>Contesto da 1M\u003C\u002Fb>: in concreto significa che puoi inserire ampi frammenti di codebase, log, specifiche e lunghe conversazioni senza dover ricorrere costantemente al \"chunking\".","\u003Cb>Uso adattivo degli strumenti\u003C\u002Fb>: il modello è addestrato a decidere autonomamente quando richiamare uno strumento (ricerca, esecuzione di codice, browser, funzioni) invece di fare tutto \"a mente\".","\u003Cb>Multimodale + \"agente visivo\"\u003C\u002Fb>: comprende immagini\u002Fdocumenti e punta a operare su applicazioni desktop\u002Fmobile (un agente in grado di \"cliccare\" ed eseguire passaggi).","\u003Cb>Efficienza (MoE \u002F architettura)\u003C\u002Fb>: focus su maggiore throughput e costi inferiori; Alibaba nelle dichiarazioni pubbliche sottolinea costi significativamente più bassi e una migliore scalabilità dei carichi di lavoro.","\u003Cb>Ecosistema aperto\u003C\u002Fb>: la serie include versioni open-weight e strumenti (repo, formati HF), mentre la versione Plus è spesso offerta come modello hosted per latenza e stabilità di produzione.","unordered","list",{"id":256,"data":257,"type":258},"qwen35p-delim1",{},"delimiter",{"id":260,"data":261,"type":42},"qwen35p-howto",{"text":262,"level":228},"Come provarlo velocemente (senza troppi giri di parole)",{"id":264,"data":265,"type":223},"qwen35p-howto-p",{"text":266},"La via più rapida è attraverso un provider che ospita già Qwen 3.5-Plus (ad esempio, un gateway\u002Faggregatore o un cloud studio). Se hai già un'app che utilizza un'API in stile \"chat completions\", la migrazione consiste principalmente nel cambiare il nome del modello e verificare i limiti di contesto e strumenti.",{"id":268,"data":269,"type":272},"qwen35p-code1",{"code":270,"language":271},"\u002F\u002F Esempio minimo (pseudo): sostituisci endpoint\u002FSDK in base al provider\nimport OpenAI from \"openai\";\n\nconst client = new OpenAI({ apiKey: process.env.API_KEY, baseURL: process.env.BASE_URL });\n\nconst res = await client.chat.completions.create({\n  model: \"qwen3.5-plus\",\n  messages: [\n    { role: \"system\", content: \"Sei un agente che completa i task.\" },\n    { role: \"user\", content: \"Analizza questo repository e suggerisci 5 miglioramenti per la sicurezza.\" }\n  ]\n});\n\nconsole.log(res.choices[0].message.content);","javascript","code",{"id":274,"data":275,"type":42},"qwen35p-usecases",{"text":276,"level":228},"Casi d'uso in cui Qwen 3.5-Plus ha un vantaggio reale",{"id":278,"data":279,"type":254},"qwen35p-usecases-list",{"items":280,"style":286},[281,282,283,284,285],"\u003Cb>RAG agentico su grandi corpora\u003C\u002Fb>: contesto da 1M + uso di strumenti riduce la necessità di una sintetizzazione aggressiva.","\u003Cb>Coding a livello di repository\u003C\u002Fb>: analisi di più file + generazione di PR con un piano coerente (meno \"patchwork casuale\").","\u003Cb>Automazione UI\u002FQA\u003C\u002Fb>: input multimodale + direzione \"agente visivo\" per test end-to-end e riproduzione di bug da screencast\u002Fscreenshot.","\u003Cb>Analisi Ops\u002Fincidenti\u003C\u002Fb>: grandi quantità di log + esecuzione di runbook con strumenti (ricerca, query, ticketing).","\u003Cb>Agente per workflow di dati\u003C\u002Fb>: generazione di SQL, validazione dei risultati, correzioni iterative — tutto in una singola sessione senza perdere il contesto.","ordered",{"id":288,"data":289,"type":42},"qwen35p-tradeoffs",{"text":290,"level":228},"Compromessi (per non cadere nella trappola dell'hype)",{"id":292,"data":293,"type":254},"qwen35p-tradeoffs-list",{"items":294,"style":253},[295,296,297],"\u003Cb>Contesto da 1M ≠ 1M di \"memoria perfetta\"\u003C\u002Fb>: più grande è l'input, più è necessario prestare attenzione alla struttura (sezionamento, indice, piano di recupero).","\u003Cb>Il comportamento agentico richiede guardrail\u003C\u002Fb>: è obbligatorio aggiungere un livello di policy (strumenti consentiti, rate limit, sandbox), logging e replay.","\u003Cb>Hosted vs open-weight\u003C\u002Fb>: Plus come modello hosted è ottimo per latenza\u002Fstabilità, ma le varianti open-weight sono migliori per la privacy e il controllo on-prem — a fronte di un maggiore carico operativo.",{"id":299,"data":300,"type":223},"qwen35p-bottomline",{"text":301},"\u003Cb>In sintesi:\u003C\u002Fb> Qwen 3.5-Plus è il segnale che la corsa si sta spostando da \"chi è più intelligente in chat\" a \"chi esegue in modo più affidabile workflow complessi\". Se sviluppi agenti in produzione, vale la pena testarlo — specialmente quando il collo di bottiglia è il contesto, l'uso degli strumenti e la stabilità attraverso più passaggi.","2.31","Scopri le caratteristiche e i vantaggi all'avanguardia di Qwen 3.5-Plus di Alibaba, un'IA open-source rivoluzionaria per gli sviluppatori.","\u002Fuploads\u002F2026\u002F02\u002Fnew-qwen-3-5-plus-1771515512741-dcbi9p.webp","new-qwen-3-5-plus-1771515512741-dcbi9p","PUBLISHED","2026-02-19T10:23:00.000Z","2026-02-19T15:23:23.973Z","2026-02-20T20:39:04.434Z",{"en":311,"de":312,"sr":313,"es":314,"fr":315,"it":316,"ru":317,"zh":318},"\u002Fblog\u002Fnew-qwen-3-5-plus","\u002Fde\u002Fblog\u002Fnew-qwen-3-5-plus","\u002Fsr\u002Fblog\u002Fnew-qwen-3-5-plus","\u002Fes\u002Fblog\u002Fnew-qwen-3-5-plus","\u002Ffr\u002Fblog\u002Fnew-qwen-3-5-plus","\u002Fit\u002Fblog\u002Fnew-qwen-3-5-plus","\u002Fru\u002Fblog\u002Fnew-qwen-3-5-plus","\u002Fzh\u002Fblog\u002Fnew-qwen-3-5-plus",[320,324,328,332],{"id":321,"name":322,"slug":323},94,"Runbook: Rilascio","release-runbook",{"id":325,"name":326,"slug":327},106,"Runbook: Rollback IA","ai-rollback",{"id":329,"name":330,"slug":331},88,"Versioning (prompt, modelli)","versioning",{"id":333,"name":334,"slug":335},87,"Playbook: LLMOps","llmops",{"id":337,"login":338,"email":339,"displayName":340},"20","rooth8233","aleksandar@stajic.de","Aleksandar Stajić",[342,411],{"lang":343,"title":344,"content":345,"contentJson":346,"excerpt":410},"en","New Qwen 3.5-Plus: Open-source AI is getting serious now","{\"time\":1771533358356,\"blocks\":[{\"id\":\"qwen35p-hero\",\"data\":{\"text\":\"Qwen 3.5-Plus: Open-source \\\"agentic\\\" AI that removes friction for developers in complex tasks\",\"level\":2},\"type\":\"header\"},{\"id\":\"qwen35p-lead\",\"data\":{\"text\":\"Alibaba has released \u003Cb>Qwen 3.5\u003C\u002Fb> and particularly highlights \u003Cb>Qwen 3.5-Plus\u003C\u002Fb> as a model developed for \u003Ci>agentic\u003C\u002Fi> work: planning, tool use, and execution of multi-step tasks with significantly higher efficiency. The message is clear: less \\\"prompt magic\\\", more reliable execution – and all with a context of up to \u003Cb>1 million tokens\u003C\u002Fb> in the Plus variant.\"},\"type\":\"paragraph\"},{\"id\":\"qwen35p-why\",\"data\":{\"text\":\"Why this is important for developers\",\"level\":3},\"type\":\"header\"},{\"id\":\"qwen35p-why-p\",\"data\":{\"text\":\"When you build production agents (RAG, copilots, automatic code review bots, data pipelines, UI testers), the biggest problem isn't \\\"whether the model knows something\\\", but: \u003Cb>can it consistently process the workflow\u003C\u002Fb> without falling apart at the 6th step. Qwen 3.5-Plus targets exactly this area – with large context, multimodal input, and integrated tool-use behavior.\"},\"type\":\"paragraph\"},{\"id\":\"qwen35p-quote\",\"data\":{\"text\":\"This is a model that attempts to transform LLMs from a \\\"chat UI\\\" into an \u003Cb>execution layer\u003C\u002Fb>: it sees, plans, uses tools, and completes the task.\",\"caption\":\"How Qwen 3.5 positions the \\\"agentic\\\" direction\",\"alignment\":\"left\"},\"type\":\"quote\"},{\"id\":\"qwen35p-features\",\"data\":{\"text\":\"Key innovations (Qwen 3.5-Plus in practice)\",\"level\":3},\"type\":\"header\"},{\"id\":\"qwen35p-features-list\",\"data\":{\"items\":[\"\u003Cb>1M Context\u003C\u002Fb>: In practice, this means you can process large codebase snippets, logs, specifications, and long conversations without constant \\\"chunking\\\".\",\"\u003Cb>Adaptive Tool Use\u003C\u002Fb>: The model is trained to decide for itself when a tool (search, code execution, browser, functions) should be called, instead of doing everything \\\"in its head\\\".\",\"\u003Cb>Multimodal + \\\"Visual Agent\\\"\u003C\u002Fb>: Understands images\u002Fdocuments and aims at working across desktop\u002Fmobile apps (an agent that can \\\"click\\\" and execute steps).\",\"\u003Cb>Efficiency (MoE \u002F Architecture)\u003C\u002Fb>: Focus on higher throughput and lower costs; Alibaba emphasizes significantly lower costs and better scaling of workloads in public appearances.\",\"\u003Cb>Open Ecosystem\u003C\u002Fb>: The series includes open-weight editions and tooling (repo, HF formats), while Plus is often offered as a hosted model for production latency and stability.\"],\"style\":\"unordered\"},\"type\":\"list\"},{\"id\":\"qwen35p-delim1\",\"data\":{},\"type\":\"delimiter\"},{\"id\":\"qwen35p-howto\",\"data\":{\"text\":\"How to try it quickly (without further ado)\",\"level\":3},\"type\":\"header\"},{\"id\":\"qwen35p-howto-p\",\"data\":{\"text\":\"The fastest way is through a provider that already hosts Qwen 3.5-Plus (e.g., gateway\u002Faggregator or cloud studio). If you already have an app that uses a \\\"Chat Completions\\\" style API, migration usually consists only of changing the model name and checking context limits and tools.\"},\"type\":\"paragraph\"},{\"id\":\"qwen35p-code1\",\"data\":{\"code\":\"\u002F\u002F Minimal example (pseudo): replace endpoint\u002FSDK depending on provider\\nimport OpenAI from \\\"openai\\\";\\n\\nconst client = new OpenAI({ apiKey: process.env.API_KEY, baseURL: process.env.BASE_URL });\\n\\nconst res = await client.chat.completions.create({\\n  model: \\\"qwen3.5-plus\\\",\\n  messages: [\\n    { role: \\\"system\\\", content: \\\"You are an agent that completes tasks.\\\" },\\n    { role: \\\"user\\\", content: \\\"Go through this repo and suggest 5 security improvements.\\\" }\\n  ]\\n});\\n\\nconsole.log(res.choices[0].message.content);\",\"language\":\"javascript\"},\"type\":\"code\"},{\"id\":\"qwen35p-usecases\",\"data\":{\"text\":\"Use cases where Qwen 3.5-Plus offers a real advantage\",\"level\":3},\"type\":\"header\"},{\"id\":\"qwen35p-usecases-list\",\"data\":{\"items\":[\"\u003Cb>Agentic RAG for large corpora\u003C\u002Fb>: 1M context + tool-use reduces the need for aggressive summarization.\",\"\u003Cb>Repo-Level Coding\u003C\u002Fb>: Analysis of multiple files + generation of PRs with a consistent plan (less \\\"random patchwork\\\").\",\"\u003Cb>UI\u002FQA Automation\u003C\u002Fb>: Multimodal input + \\\"Visual Agent\\\" alignment for end-to-end tests and reproducing bugs from screencasts\u002Fscreenshots.\",\"\u003Cb>Ops\u002FIncident Analysis\u003C\u002Fb>: Large amounts of logs + runbook execution with tools (search, query, ticketing).\",\"\u003Cb>Data Workflow Agent\u003C\u002Fb>: SQL generation, result validation, iterative corrections – all in one session without context loss.\"],\"style\":\"ordered\"},\"type\":\"list\"},{\"id\":\"qwen35p-tradeoffs\",\"data\":{\"text\":\"Trade-offs (to avoid falling into the hype trap)\",\"level\":3},\"type\":\"header\"},{\"id\":\"qwen35p-tradeoffs-list\",\"data\":{\"items\":[\"\u003Cb>1M Context ≠ 1M \\\"perfect memory\\\"\u003C\u002Fb>: The larger the input, the more you need to pay attention to structure (sectioning, index, retrieval plan).\",\"\u003Cb>Agentic behavior requires guardrails\u003C\u002Fb>: Be sure to add a policy layer (allowed tools, rate limit, sandbox), logging, and replay.\",\"\u003Cb>Hosted vs. Open-Weight\u003C\u002Fb>: Plus as a hosted model is excellent for latency\u002Fstability, but open-weight variants are better for data privacy and on-prem control – with higher operational overhead (Ops).\"],\"style\":\"unordered\"},\"type\":\"list\"},{\"id\":\"qwen35p-bottomline\",\"data\":{\"text\":\"\u003Cb>Conclusion:\u003C\u002Fb> Qwen 3.5-Plus is a signal that the race is shifting from \\\"who is smarter in chat\\\" to \\\"who executes complex workflows more reliably\\\". If you use agents in production, this is worth a test – especially if context, tool-use, and stability across multiple steps are your bottlenecks.\"},\"type\":\"paragraph\"}],\"version\":\"2.31\"}",{"time":347,"blocks":348,"version":302},1771533358356,[349,352,355,358,361,365,368,376,378,381,384,387,390,398,401,407],{"id":215,"data":350,"type":42},{"text":351,"level":218},"Qwen 3.5-Plus: Open-source \"agentic\" AI that removes friction for developers in complex tasks",{"id":220,"data":353,"type":223},{"text":354},"Alibaba has released \u003Cb>Qwen 3.5\u003C\u002Fb> and particularly highlights \u003Cb>Qwen 3.5-Plus\u003C\u002Fb> as a model developed for \u003Ci>agentic\u003C\u002Fi> work: planning, tool use, and execution of multi-step tasks with significantly higher efficiency. The message is clear: less \"prompt magic\", more reliable execution – and all with a context of up to \u003Cb>1 million tokens\u003C\u002Fb> in the Plus variant.",{"id":225,"data":356,"type":42},{"text":357,"level":228},"Why this is important for developers",{"id":230,"data":359,"type":223},{"text":360},"When you build production agents (RAG, copilots, automatic code review bots, data pipelines, UI testers), the biggest problem isn't \"whether the model knows something\", but: \u003Cb>can it consistently process the workflow\u003C\u002Fb> without falling apart at the 6th step. Qwen 3.5-Plus targets exactly this area – with large context, multimodal input, and integrated tool-use behavior.",{"id":234,"data":362,"type":239},{"text":363,"caption":364,"alignment":238},"This is a model that attempts to transform LLMs from a \"chat UI\" into an \u003Cb>execution layer\u003C\u002Fb>: it sees, plans, uses tools, and completes the task.","How Qwen 3.5 positions the \"agentic\" direction",{"id":241,"data":366,"type":42},{"text":367,"level":228},"Key innovations (Qwen 3.5-Plus in practice)",{"id":245,"data":369,"type":254},{"items":370,"style":253},[371,372,373,374,375],"\u003Cb>1M Context\u003C\u002Fb>: In practice, this means you can process large codebase snippets, logs, specifications, and long conversations without constant \"chunking\".","\u003Cb>Adaptive Tool Use\u003C\u002Fb>: The model is trained to decide for itself when a tool (search, code execution, browser, functions) should be called, instead of doing everything \"in its head\".","\u003Cb>Multimodal + \"Visual Agent\"\u003C\u002Fb>: Understands images\u002Fdocuments and aims at working across desktop\u002Fmobile apps (an agent that can \"click\" and execute steps).","\u003Cb>Efficiency (MoE \u002F Architecture)\u003C\u002Fb>: Focus on higher throughput and lower costs; Alibaba emphasizes significantly lower costs and better scaling of workloads in public appearances.","\u003Cb>Open Ecosystem\u003C\u002Fb>: The series includes open-weight editions and tooling (repo, HF formats), while Plus is often offered as a hosted model for production latency and stability.",{"id":256,"data":377,"type":258},{},{"id":260,"data":379,"type":42},{"text":380,"level":228},"How to try it quickly (without further ado)",{"id":264,"data":382,"type":223},{"text":383},"The fastest way is through a provider that already hosts Qwen 3.5-Plus (e.g., gateway\u002Faggregator or cloud studio). If you already have an app that uses a \"Chat Completions\" style API, migration usually consists only of changing the model name and checking context limits and tools.",{"id":268,"data":385,"type":272},{"code":386,"language":271},"\u002F\u002F Minimal example (pseudo): replace endpoint\u002FSDK depending on provider\nimport OpenAI from \"openai\";\n\nconst client = new OpenAI({ apiKey: process.env.API_KEY, baseURL: process.env.BASE_URL });\n\nconst res = await client.chat.completions.create({\n  model: \"qwen3.5-plus\",\n  messages: [\n    { role: \"system\", content: \"You are an agent that completes tasks.\" },\n    { role: \"user\", content: \"Go through this repo and suggest 5 security improvements.\" }\n  ]\n});\n\nconsole.log(res.choices[0].message.content);",{"id":274,"data":388,"type":42},{"text":389,"level":228},"Use cases where Qwen 3.5-Plus offers a real advantage",{"id":278,"data":391,"type":254},{"items":392,"style":286},[393,394,395,396,397],"\u003Cb>Agentic RAG for large corpora\u003C\u002Fb>: 1M context + tool-use reduces the need for aggressive summarization.","\u003Cb>Repo-Level Coding\u003C\u002Fb>: Analysis of multiple files + generation of PRs with a consistent plan (less \"random patchwork\").","\u003Cb>UI\u002FQA Automation\u003C\u002Fb>: Multimodal input + \"Visual Agent\" alignment for end-to-end tests and reproducing bugs from screencasts\u002Fscreenshots.","\u003Cb>Ops\u002FIncident Analysis\u003C\u002Fb>: Large amounts of logs + runbook execution with tools (search, query, ticketing).","\u003Cb>Data Workflow Agent\u003C\u002Fb>: SQL generation, result validation, iterative corrections – all in one session without context loss.",{"id":288,"data":399,"type":42},{"text":400,"level":228},"Trade-offs (to avoid falling into the hype trap)",{"id":292,"data":402,"type":254},{"items":403,"style":253},[404,405,406],"\u003Cb>1M Context ≠ 1M \"perfect memory\"\u003C\u002Fb>: The larger the input, the more you need to pay attention to structure (sectioning, index, retrieval plan).","\u003Cb>Agentic behavior requires guardrails\u003C\u002Fb>: Be sure to add a policy layer (allowed tools, rate limit, sandbox), logging, and replay.","\u003Cb>Hosted vs. Open-Weight\u003C\u002Fb>: Plus as a hosted model is excellent for latency\u002Fstability, but open-weight variants are better for data privacy and on-prem control – with higher operational overhead (Ops).",{"id":299,"data":408,"type":223},{"text":409},"\u003Cb>Conclusion:\u003C\u002Fb> Qwen 3.5-Plus is a signal that the race is shifting from \"who is smarter in chat\" to \"who executes complex workflows more reliably\". If you use agents in production, this is worth a test – especially if context, tool-use, and stability across multiple steps are your bottlenecks.","Discover the groundbreaking features and benefits of Alibaba's Qwen 3.5-Plus, a revolutionary open-source AI for developers.",{"lang":7,"title":208,"content":210,"contentJson":412,"excerpt":303},{"time":212,"blocks":413,"version":302},[414,416,418,420,422,424,426,429,431,433,435,437,439,442,444,447],{"id":215,"data":415,"type":42},{"text":217,"level":218},{"id":220,"data":417,"type":223},{"text":222},{"id":225,"data":419,"type":42},{"text":227,"level":228},{"id":230,"data":421,"type":223},{"text":232},{"id":234,"data":423,"type":239},{"text":236,"caption":237,"alignment":238},{"id":241,"data":425,"type":42},{"text":243,"level":228},{"id":245,"data":427,"type":254},{"items":428,"style":253},[248,249,250,251,252],{"id":256,"data":430,"type":258},{},{"id":260,"data":432,"type":42},{"text":262,"level":228},{"id":264,"data":434,"type":223},{"text":266},{"id":268,"data":436,"type":272},{"code":270,"language":271},{"id":274,"data":438,"type":42},{"text":276,"level":228},{"id":278,"data":440,"type":254},{"items":441,"style":286},[281,282,283,284,285],{"id":288,"data":443,"type":42},{"text":290,"level":228},{"id":292,"data":445,"type":254},{"items":446,"style":253},[295,296,297],{"id":299,"data":448,"type":223},{"text":301},"Post erfolgreich abgerufen",{"items":451,"source":470,"manualIds":471,"manualMatchedIds":472},[452,457,464],{"id":453,"slug":454,"title":454,"excerpt":10,"featuredImage":455,"publishedAt":456},"369","git-with-automatic-upload-and-synchronization-to-a-production-server","\u002Fuploads\u002F2024\u002F05\u002Fstep-by-step-guide-illustration-showing-the-process-of-setting-up-Git-with-auto-upload-and-synchronization-to-a-production-server-large.webp","2024-05-28T22:48:00.000Z",{"id":458,"slug":459,"title":460,"excerpt":461,"featuredImage":462,"publishedAt":463},"459","ollama-is-not-the-product-building-production-ready-open-llm-applications","Ollama non è il prodotto: costruire applicazioni Open-LLM pronte per la produzione","Eseguire un modello locale con Ollama è facile. Costruire un'applicazione Open-LLM pronta per la produzione è più difficile: richiede RAG, controllo degli accessi, astrazione del provider, valutazione, logging, disciplina di deployment e un livello applicativo controllato attorno al modello.","\u002Fuploads\u002F2026\u002F06\u002Follama-is-not-the-product-building-production-ready-open-llm-applications-1782679361640-h0usqf.webp","2026-06-28T16:39:00.000Z",{"id":465,"slug":466,"title":467,"excerpt":468,"featuredImage":304,"publishedAt":469},"445","qwen-3-6-in-production-release-runbook-ai-rollback-and-llmops-versioning","Qwen 3.6 in produzione: Runbook di rilascio, Rollback AI e Versionamento LLMOps","Qwen 3.6 non è solo un altro aggiornamento del modello. È un evento di rilascio, uno scenario di rollback e un problema di versionamento allo stesso tempo. Questo articolo spiega come Qwen 3.6 dovrebbe essere gestito in produzione attraverso la disciplina LLMOps, la tracciabilità dei prompt e dei modelli, il rollout controllato e la prontezza al rollback basata sull'evidenza.","2026-05-04T02:49:00.000Z","fallback",[],[]]