{"id":13154,"date":"2024-10-08T14:11:04","date_gmt":"2024-10-08T19:11:04","guid":{"rendered":"http:\/\/skimai.com\/?p=13154"},"modified":"2024-10-08T14:11:04","modified_gmt":"2024-10-08T19:11:04","slug":"come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72","status":"publish","type":"post","link":"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/","title":{"rendered":"Come richiedere OpenAI o1 e come usarlo? - AI&amp;YOU #72"},"content":{"rendered":"\n<p><strong><u>Stat of the Week:<\/u> <\/strong>o1 has shown exceptional skill, ranking in the 89th percentile on Codeforces, a renowned platform for coding challenges. (OpenAI)<\/p>\n\n\n<p>OpenAI&#8217;s new o1 model marks a paradigm shift in how AI processes and responds to complex queries. Unlike its predecessors, o1 is designed to &#8220;think&#8221; through problems before generating a response, mimicking a more human-like reasoning process. This fundamental change in model architecture necessitates a corresponding evolution in our prompting techniques.<\/p>\n\n\n<p><strong>In this week&#8217;s edition of AI&amp;YOU, we are exploring insights from three blogs we published on the topic:<\/strong><\/p>\n\n\n<ul class=\"wp-block-list\">\n<li><p><a rel=\"noopener noreferrer\" href=\"http:\/\/skimai.com\/how-to-prompt-openais-o1-model\/\">How to Prompt OpenAI&#8217;s o1 Model<\/a><\/p><\/li><li><p><a rel=\"noopener noreferrer\" href=\"http:\/\/skimai.com\/who-should-use-openais-o1-model\/\">Who Should Use OpenAI&#8217;s o1 Model?<\/a><\/p><\/li><li><p><a rel=\"noopener noreferrer\" href=\"http:\/\/skimai.com\/15-statistics-facts-to-know-about-openais-o1-model\/\">15 Stats\/Facts to Know About OpenAI&#8217;s o1 Model<\/a><\/p><\/li>\n<\/ul>\n\n\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_82_1 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#How_to_Prompt_OpenAI_o1_Should_You_Use_It_%E2%80%93_AI_YOU_72\" >How to Prompt OpenAI o1 + Should You Use It? &#8211; AI&amp;YOU #72<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#Understanding_o1s_Reasoning_Capabilities\" >Understanding o1&#8217;s Reasoning Capabilities<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#Internal_Chain_of_Thought_Reasoning\" >Internal Chain of Thought Reasoning<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#Performance_Leaps_in_Complex_Tasks\" >Performance Leaps in Complex Tasks<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#Key_Principles_for_Prompting_o1\" >Key Principles for Prompting o1<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#Simplicity_and_Directness_in_Prompts\" >Simplicity and Directness in Prompts<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#Avoiding_Excessive_Guidance\" >Avoiding Excessive Guidance<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#Utilizing_Delimiters_for_Clarity\" >Utilizing Delimiters for Clarity<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#How_to_Optimize_Input_for_o1\" >How to Optimize Input for o1<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#Who_Should_Use_OpenAIs_o1_Model\" >Who Should Use OpenAI&#8217;s o1 Model?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#Ideal_Candidates_for_o1_Adoption\" >Ideal Candidates for o1 Adoption<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-12\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#15_StatsFacts_to_Know_About_OpenAIs_o1_Model\" >15 Stats\/Facts to Know About OpenAI&#8217;s o1 Model<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-13\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#The_Bottom_Line\" >The Bottom Line<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-14\" href=\"https:\/\/skimai.com\/it\/how-to-prompt-openai-o1-should-you-use-it-aiyou-72\/#Thank_you_for_taking_the_time_to_read_AI_YOU\" >Thank you for taking the time to read AI &amp; YOU!<\/a><\/li><\/ul><\/nav><\/div>\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"How_to_Prompt_OpenAI_o1_Should_You_Use_It_%E2%80%93_AI_YOU_72\"><\/span><strong>How to Prompt OpenAI o1 + Should You Use It? &#8211; AI&amp;YOU #72<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p>For AI enterprises and developers accustomed to working with previous models like GPT-4o, adapting to o1&#8217;s unique characteristics is crucial. The prompting strategies that yielded optimal results with earlier models may not be as effective\u2014or could even hinder performance\u2014when applied to o1.<\/p>\n\n\n<p>Understanding how to effectively prompt this new model is key to unlocking its full potential and leveraging its advanced reasoning capabilities in real-world applications.<\/p>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Understanding_o1s_Reasoning_Capabilities\"><\/span>Understanding o1&#8217;s Reasoning Capabilities<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p>While models like GPT-4o excelled at generating human-like text and performing a wide range of language tasks, they often struggled with complex reasoning, especially in fields requiring logical step-by-step problem-solving. The o1 model, however, has been specifically designed to bridge this gap.<\/p>\n\n\n<p>The key difference lies in how o1 processes information. Unlike previous models that generate responses based primarily on pattern recognition within their training data, o1 employs a more structured approach to problem-solving. This allows it to tackle tasks that require multi-step reasoning, logical deduction, and even creative problem-solving with significantly improved accuracy.<\/p>\n\n\n<figure class=\"wp-block-image\">\n<img decoding=\"async\" src=\"http:\/\/skimai.com\/wp-content\/uploads\/2024\/10\/5f01bb4f-c4d5-427e-8901-b640e276c9f4.jpeg\" \/>\n<\/figure>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Internal_Chain_of_Thought_Reasoning\"><\/span>Internal Chain of Thought Reasoning<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p>At the heart of o1&#8217;s capabilities is its integrated <a rel=\"noopener noreferrer\" href=\"http:\/\/skimai.com\/what-is-chain-of-thought-cot-prompting\/\">chain of thought<\/a> (CoT) reasoning. This approach, previously used as an external prompting technique, is now built directly into the model&#8217;s architecture. When presented with a complex query, o1 doesn&#8217;t immediately generate a response. Instead, it first breaks down the problem into smaller, manageable steps.<\/p>\n\n\n<p><strong>This internal reasoning process allows o1 to:<\/strong><\/p>\n\n\n<ol class=\"wp-block-list\">\n<li><p>Identify key components of the problem<\/p><\/li><li><p>Establish logical connections between different elements<\/p><\/li><li><p>Consider multiple approaches to solving the task<\/p><\/li><li><p>Evaluate and correct its own reasoning as it progresses<\/p><\/li>\n<\/ol>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Performance_Leaps_in_Complex_Tasks\"><\/span>Performance Leaps in Complex Tasks<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p>o1&#8217;s integration of CoT reasoning has led to remarkable improvements in complex logical tasks:<\/p>\n\n\n<ul class=\"wp-block-list\">\n<li><p><strong>Mathematical problem-solving:<\/strong> Achieves accuracy levels orders of magnitude higher than predecessors on olympiad-level problems.<\/p><\/li><li><p><strong>Coding capabilities:<\/strong> Rivals skilled human programmers in software development and debugging.<\/p><\/li><li><p><strong>Scientific reasoning:<\/strong> Excels in data analysis and hypothesis generation, opening new research frontiers.<\/p><\/li><li><p><strong>Multi-step logical deduction:<\/strong> Handles tasks requiring complex step-by-step reasoning with increased proficiency.<\/p><\/li>\n<\/ul>\n\n\n<p>By integrating CoT reasoning, o1 has achieved substantial improvements in tasks demanding complex cognition, setting new benchmarks in AI capabilities.<\/p>\n\n\n<figure class=\"wp-block-image\">\n<img decoding=\"async\" src=\"http:\/\/skimai.com\/wp-content\/uploads\/2024\/10\/bccbbe58-71f9-45d2-814d-717dcb427dc5.jpeg\" \/>\n<\/figure>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Key_Principles_for_Prompting_o1\"><\/span>Key Principles for Prompting o1<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p>As we delve into the art of prompting OpenAI&#8217;s o1 model, it&#8217;s crucial to understand that this new generation of reasoning models requires a shift in our approach. Let&#8217;s explore the key principles that will help you harness the full potential of o1&#8217;s advanced reasoning capabilities.<\/p>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Simplicity_and_Directness_in_Prompts\"><\/span>Simplicity and Directness in Prompts<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p>When it comes to prompting o1, simplicity is key. Unlike previous models that often benefited from detailed instructions or extensive context, o1&#8217;s built-in reasoning capabilities allow it to perform best with straightforward prompts.<\/p>\n\n\n<p><strong>Here are some tips for crafting simple and direct prompts:<\/strong><\/p>\n\n\n<ul class=\"wp-block-list\">\n<li><p><strong>Be clear and concise:<\/strong> State your question or task directly without unnecessary elaboration.<\/p><\/li><li><p><strong>Avoid overexplaining:<\/strong> Trust the model&#8217;s ability to understand context and infer details.<\/p><\/li><li><p><strong>Focus on the core problem:<\/strong> Present the essential elements of your query without extraneous information.<\/p><\/li>\n<\/ul>\n\n\n<p>For example, instead of providing step-by-step instructions for solving a complex mathematical problem, you might simply state: <strong>&#8220;Solve the following equation and explain your reasoning: 3x^2 + 7x &#8211; 2 = 0.&#8221;<\/strong><\/p>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Avoiding_Excessive_Guidance\"><\/span>Avoiding Excessive Guidance<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p>While previous models often benefited from detailed instructions or examples (a technique known as &#8220;few-shot learning&#8221;), o1&#8217;s improved performance and internal reasoning process make such guidance less necessary and potentially counterproductive.<\/p>\n\n\n<p><strong>Consider the following:<\/strong><\/p>\n\n\n<ul class=\"wp-block-list\">\n<li><p>Resist the urge to provide multiple examples or extensive context unless absolutely necessary.<\/p><\/li><li><p>Allow the model to leverage its own reasoning capabilities rather than trying to guide its thought process.<\/p><\/li><li><p>Avoid explicitly stating steps or methods for solving a problem, as this may interfere with o1&#8217;s internal chain of thought reasoning.<\/p><\/li>\n<\/ul>\n\n\n<p>By refraining from excessive guidance, you allow o1 to fully utilize its advanced reasoning models and potentially discover more efficient or innovative solutions to complex reasoning tasks.<\/p>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Utilizing_Delimiters_for_Clarity\"><\/span><strong>Utilizing Delimiters for Clarity<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p>While simplicity is crucial, there are times when you need to provide structured input or separate different components of your prompt. In these cases, utilizing delimiters can significantly enhance clarity and help o1 process your input more effectively.<\/p>\n\n\n<p><strong>Delimiters serve several purposes:<\/strong><\/p>\n\n\n<ol class=\"wp-block-list\">\n<li><p>They clearly separate different sections of your prompt.<\/p><\/li><li><p>They help the model distinguish between instructions, context, and the actual query.<\/p><\/li><li><p>They can be used to indicate specific formats or types of information.<\/p><\/li>\n<\/ol>\n\n\n<p><strong>Some effective ways to use delimiters include:<\/strong><\/p>\n\n\n<ul class=\"wp-block-list\">\n<li><p>Triple quotes: &#8220;&#8221;&#8221;Your text here&#8221;&#8221;&#8221;<\/p><\/li><li><p>XML-style tags: &lt;instruction&gt;Your instruction here&lt;\/instruction&gt;<\/p><\/li><li><p>Dashes or asterisks: &#8212; or ***<\/p><\/li><li><p>Clearly labeled sections: [CONTEXT], [QUERY], [OUTPUT FORMAT]<\/p><\/li>\n<\/ul>\n\n\n<p>For instance, when working with cell sequencing data or other scientific information, you might structure your prompt like this:<\/p>\n\n\n<p>&#8212;<\/p>\n\n\n<p><strong>[CONTEXT]<\/strong><\/p>\n\n\n<p><strong>The following is a dataset from a cell sequencing experiment:<\/strong><\/p>\n\n\n<p><strong>&lt;data&gt;<\/strong><\/p>\n\n\n<p><strong>&#8230;your data here&#8230;<\/strong><\/p>\n\n\n<p><strong>&lt;\/data&gt;<\/strong><\/p>\n\n\n<p><strong>[QUERY]<\/strong><\/p>\n\n\n<p><strong>Analyze this data and identify any significant patterns or anomalies.<\/strong><\/p>\n\n\n<p><strong>[OUTPUT FORMAT]<\/strong><\/p>\n\n\n<p><strong>Provide your analysis in a structured report with sections for Methods, Results, and Conclusions.<\/strong><\/p>\n\n\n<p><strong>&#8212;<\/strong><\/p>\n\n\n<p>By using delimiters effectively, you can provide necessary context and structure without overwhelming o1&#8217;s reasoning capabilities or interfering with its internal chain of thought process.<\/p>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"How_to_Optimize_Input_for_o1\"><\/span>How to Optimize Input for o1<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p>Effectively leveraging o1&#8217;s advanced reasoning capabilities requires optimized input. Balance context and conciseness by providing essential background without overwhelming the model. Focus on quality over quantity, trusting o1&#8217;s ability to infer and reason. For complex tasks, offer a brief overview rather than an exhaustive explanation.<\/p>\n\n\n<p>When using <a rel=\"noopener noreferrer\" href=\"http:\/\/skimai.com\/retrieval-augmented-generation-rag-in-enterprise-ai\/\">Retrieval Augmented Generation (RAG)<\/a> with o1, be selective with external information. Prioritize high-quality, relevant data over volume, using RAG primarily for specific facts rather than general context. This targeted approach enhances o1&#8217;s performance on domain-specific tasks without overwhelming its reasoning process.<\/p>\n\n\n<p>Embrace o1&#8217;s improved performance by trusting it with more challenging, nuanced prompts. Expect sophisticated responses even from concise inputs, and experiment with complex queries that might have been unsuitable for previous AI models. This adaptation allows you to fully harness o1&#8217;s potential for complex reasoning tasks.<\/p>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Who_Should_Use_OpenAIs_o1_Model\"><\/span>Who Should Use OpenAI&#8217;s o1 Model?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p>As enterprises and researchers grapple with increasingly complex challenges and the rise of new LLM models, the question arises: should I use OpenAI o1 for my specific needs?<\/p>\n\n\n<figure class=\"wp-block-image\">\n<img decoding=\"async\" src=\"http:\/\/skimai.com\/wp-content\/uploads\/2024\/10\/ee87cd05-9cab-48b0-bb5a-e7dac2a201f5.png\" \/>\n<\/figure>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Ideal_Candidates_for_o1_Adoption\"><\/span>Ideal Candidates for o1 Adoption<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p>As we consider who should use OpenAI&#8217;s o1 model, several groups stand out as particularly well-suited to leverage its advanced capabilities. The o1 model&#8217;s unique strengths in complex reasoning and problem-solving make it an invaluable tool for those working at the forefront of innovation and discovery.<\/p>\n\n\n<p>1\ufe0f\u20e3 <strong>Research and Development Teams:<\/strong> R&amp;D teams across industries should adopt o1 for its ability to tackle complex challenges using chain of thought reasoning. This model can accelerate research processes, from drug discovery to experimental design, by efficiently analyzing complex interactions and generating hypotheses. O1&#8217;s capacity for detailed, step-by-step reasoning aligns well with R&amp;D&#8217;s rigorous approach, making it an invaluable tool for exploring new research directions and solving multi-step problems.<\/p>\n\n\n<p>2\ufe0f\u20e3 <strong>Software Development and Coding:<\/strong> o1&#8217;s enhanced abilities in tackling coding tasks, optimizing algorithms, and debugging complex systems make it an invaluable asset for developers. For competitive programmers, o1&#8217;s systematic approach to coding challenges mirrors top-tier programmers&#8217; thought processes, serving not just as a tool but as a potential mentor to improve problem-solving skills.<\/p>\n\n\n<p>3\ufe0f\u20e3 <strong>Scientific and Academic Institutions:<\/strong> In scientific research and academia, o1&#8217;s advanced reasoning capabilities excel at analyzing vast datasets, formulating hypotheses, and suggesting experimental approaches across fields from astrophysics to genomics. Its ability to provide detailed explanations for complex concepts makes it a powerful aid in both research and education. In theoretical physics and advanced mathematics, o1&#8217;s proficiency could lead to new insights on long-standing questions, making it an essential tool for pushing the boundaries of human knowledge.<\/p>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"15_StatsFacts_to_Know_About_OpenAIs_o1_Model\"><\/span>15 Stats\/Facts to Know About OpenAI&#8217;s o1 Model<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p><strong>1\ufe0f\u20e3 83% accuracy on International Mathematics Olympiad qualifier<\/strong><\/p>\n\n\n<p>This is a significant improvement over GPT-4o&#8217;s 13%, showcasing o1&#8217;s advanced mathematical reasoning abilities.<\/p>\n\n\n<p><strong>2\ufe0f\u20e3 89th percentile ranking on Codeforces<\/strong><\/p>\n\n\n<p>Demonstrates o1&#8217;s exceptional skill in competitive programming and solving complex algorithmic problems.<\/p>\n\n\n<p><strong>3\ufe0f\u20e3 74% success rate on AIME problems<\/strong><\/p>\n\n\n<p>A huge leap from GPT-4o&#8217;s 9%, highlighting o1&#8217;s prowess in tackling difficult, multi-step mathematical challenges.<\/p>\n\n\n<p><strong>4\ufe0f\u20e3 PhD-level accuracy on GPQA benchmark for physics, biology, and chemistry<\/strong><\/p>\n\n\n<p>Shows o1&#8217;s versatility across scientific disciplines, making it valuable for high-level scientific research.<\/p>\n\n\n<p><strong>5\ufe0f\u20e3 128,000 token context window<\/strong><\/p>\n\n\n<p>Allows o1 to process and understand much longer pieces of text or more complex problems in a single prompt.<\/p>\n\n\n<p><strong>6\ufe0f\u20e3 Two variants: o1-preview and o1-mini<\/strong><\/p>\n\n\n<p>Offers flexibility for different use cases, balancing capability and speed.<\/p>\n\n\n<p><strong>7\ufe0f\u20e3 Uses internal &#8220;reasoning tokens&#8221; for problem-solving<\/strong><\/p>\n\n\n<p>Enables o1 to break down complex problems into steps, mimicking human-like reasoning.<\/p>\n\n\n<p><strong>8\ufe0f\u20e3 Improved performance in challenging languages like Yoruba and Swahili<\/strong><\/p>\n\n\n<p>Enhances o1&#8217;s utility for multilingual tasks and global applications.<\/p>\n\n\n<p><strong>9\ufe0f\u20e3 0.44 score on SimpleQA test for hallucinations<\/strong><\/p>\n\n\n<p>Lower than GPT-4o&#8217;s 0.61, indicating reduced likelihood of generating false information.<\/p>\n\n\n<p><strong>\ud83d\udd1f 94% correct answer selection on unambiguous questions<\/strong><\/p>\n\n\n<p>Improvement over GPT-4o&#8217;s 72%, suggesting enhanced fairness and reduced bias in responses.<\/p>\n\n\n<p><strong>1\ufe0f\u20e31\ufe0f\u20e3 Enhanced jailbreak resistance and content policy adherence<\/strong><\/p>\n\n\n<p>Improves safety and reliability for public-facing or sensitive applications.<\/p>\n\n\n<p><strong>1\ufe0f\u20e32\ufe0f\u20e3 Slower response times compared to previous models<\/strong><\/p>\n\n\n<p>Trade-off for its more extensive reasoning processes and deeper analysis capabilities.<\/p>\n\n\n<p><strong>1\ufe0f\u20e33\ufe0f\u20e3 o1-preview pricing: $15 per million input tokens, $60 per million output tokens<\/strong><\/p>\n\n\n<p>Reflects the advanced capabilities and increased computational resources required.<\/p>\n\n\n<p><strong>1\ufe0f\u20e34\ufe0f\u20e3 Excels in mathematics, coding, and scientific reasoning<\/strong><\/p>\n\n\n<p>Shows particular excellence in STEM fields, making it invaluable for research institutions, tech companies, and educational organizations.<\/p>\n\n\n<p><strong>1\ufe0f\u20e35\ufe0f\u20e3 o1-mini priced at $3 per million input tokens<\/strong><\/p>\n\n\n<p>Offers a more cost-effective option compared to o1-preview, though likely with some trade-offs in capability.<\/p>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"The_Bottom_Line\"><\/span>The Bottom Line<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p>OpenAI&#8217;s o1 model represents a significant leap forward in AI capabilities, particularly in complex reasoning tasks across STEM fields. Its improved performance in areas like mathematics, coding, and scientific analysis, coupled with enhanced safety features and reduced biases, makes it a powerful tool for enterprises tackling sophisticated challenges.<\/p>\n\n\n<p>However, the trade-offs in terms of processing speed and higher costs necessitate careful consideration. As AI continues to evolve, o1 stands as a testament to the rapid advancements in the field, offering unprecedented capabilities that could potentially transform how businesses and researchers approach complex problem-solving in the near future.<\/p>\n\n\n<hr class=\"wp-block-separator\" \/>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Thank_you_for_taking_the_time_to_read_AI_YOU\"><\/span><strong>Thank you for taking the time to read AI &amp; YOU!<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n<p><strong>For even more content on enterprise AI, including infographics, stats, how-to guides, articles, and videos, follow Skim AI on <\/strong><a rel=\"noopener noreferrer\" href=\"https:\/\/linkedin.com\/company\/skim-ai\" target=\"_self\" class=\"app-aware-link \"><strong>LinkedIn<\/strong><\/a><\/p>\n\n\n<p style=\"text-align: start\"><a rel=\"noopener noreferrer\" href=\"https:\/\/meetings.hubspot.com\/gregg15\/15-min-about-enterprise-ai?utm_source=hs_email&utm_medium=email\" target=\"_self\" class=\"app-aware-link \">Looking to hire an AI Agent for a job to be done, or build a whole AI workforce? Schedule a demo of our no-code AI Agent Platform to make more money and tame your payroll costs forever!<\/a><\/p>\n\n\n<p style=\"text-align: start\">We enable Venture Capital and Private Equity backed companies in the following industries: Medical Technology, News\/Content Aggregation, Film &amp; Photo Production, Educational Technology, Legal Technology, Fintech &amp; Cryptocurrency to automate work and scale with AI.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Stat of the Week: o1 has shown exceptional skill, ranking in the 89th percentile on Codeforces, a renowned platform for coding challenges. (OpenAI) OpenAI&#8217;s new o1 model marks a paradigm shift in how AI processes and responds to complex queries. Unlike its predecessors, o1 is designed to &#8220;think&#8221; through problems before generating a response, mimicking [&hellip;]<\/p>\n","protected":false},"author":1003,"featured_media":13157,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"single-custom-post-template.php","format":"standard","meta":{"_et_pb_use_builder":"","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[100,67,109,119],"tags":[],"class_list":["post-13154","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-generative-ai","category-ml-nlp","category-newsletter","category-prompt-engineering"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v24.1 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>How to Prompt OpenAI o1 + Should You Use It? - AI&amp;YOU #72 - Skim AI<\/title>\n<meta name=\"description\" content=\"Explore the paradigm shift with OpenAI&#039;s o1 model, designed for complex reasoning tasks. Learn how to prompt it effectively, discover who should use it, and dive into 15 key stats and facts that showcase its groundbreaking capabilities.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/\" \/>\n<meta property=\"og:locale\" content=\"it_IT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How to Prompt OpenAI o1 + Should You Use It? - AI&amp;YOU #72 - Skim AI\" \/>\n<meta property=\"og:description\" content=\"Explore the paradigm shift with OpenAI&#039;s o1 model, designed for complex reasoning tasks. Learn how to prompt it effectively, discover who should use it, and dive into 15 key stats and facts that showcase its groundbreaking capabilities.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/\" \/>\n<meta property=\"og:site_name\" content=\"Skim AI\" \/>\n<meta property=\"article:published_time\" content=\"2024-10-08T19:11:04+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/skimai.com\/wp-content\/uploads\/2024\/10\/AIYOU72.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1092\" \/>\n\t<meta property=\"og:image:height\" content=\"612\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Greggory Elias\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Scritto da\" \/>\n\t<meta name=\"twitter:data1\" content=\"Greggory Elias\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tempo di lettura stimato\" \/>\n\t<meta name=\"twitter:data2\" content=\"10 minuti\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/\"},\"author\":{\"name\":\"Greggory Elias\",\"@id\":\"https:\/\/skimai.com\/uk\/#\/schema\/person\/7a883b4a2d2ea22040f42a7975eb86c6\"},\"headline\":\"How to Prompt OpenAI o1 + Should You Use It? &#8211; AI&#038;YOU #72\",\"datePublished\":\"2024-10-08T19:11:04+00:00\",\"dateModified\":\"2024-10-08T19:11:04+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/\"},\"wordCount\":1955,\"publisher\":{\"@id\":\"https:\/\/skimai.com\/uk\/#organization\"},\"image\":{\"@id\":\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/skimai.com\/wp-content\/uploads\/2024\/10\/AIYOU72.png\",\"articleSection\":[\"Generative AI\",\"LLMs \/ NLP\",\"Newsletter\",\"Prompt Engineering\"],\"inLanguage\":\"it-IT\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/\",\"url\":\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/\",\"name\":\"How to Prompt OpenAI o1 + Should You Use It? - AI&YOU #72 - Skim AI\",\"isPartOf\":{\"@id\":\"https:\/\/skimai.com\/uk\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/skimai.com\/wp-content\/uploads\/2024\/10\/AIYOU72.png\",\"datePublished\":\"2024-10-08T19:11:04+00:00\",\"dateModified\":\"2024-10-08T19:11:04+00:00\",\"description\":\"Explore the paradigm shift with OpenAI's o1 model, designed for complex reasoning tasks. Learn how to prompt it effectively, discover who should use it, and dive into 15 key stats and facts that showcase its groundbreaking capabilities.\",\"breadcrumb\":{\"@id\":\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#breadcrumb\"},\"inLanguage\":\"it-IT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#primaryimage\",\"url\":\"https:\/\/skimai.com\/wp-content\/uploads\/2024\/10\/AIYOU72.png\",\"contentUrl\":\"https:\/\/skimai.com\/wp-content\/uploads\/2024\/10\/AIYOU72.png\",\"width\":1092,\"height\":612,\"caption\":\"AI&YOU#72\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/skimai.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"How to Prompt OpenAI o1 + Should You Use It? &#8211; AI&#038;YOU #72\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/skimai.com\/uk\/#website\",\"url\":\"https:\/\/skimai.com\/uk\/\",\"name\":\"Skim AI\",\"description\":\"The AI Agent Workforce Platform\",\"publisher\":{\"@id\":\"https:\/\/skimai.com\/uk\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/skimai.com\/uk\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"it-IT\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/skimai.com\/uk\/#organization\",\"name\":\"Skim AI\",\"url\":\"https:\/\/skimai.com\/uk\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\/\/skimai.com\/uk\/#\/schema\/logo\/image\/\",\"url\":\"http:\/\/skimai.com\/wp-content\/uploads\/2020\/07\/SKIM-AI-Header-Logo.png\",\"contentUrl\":\"http:\/\/skimai.com\/wp-content\/uploads\/2020\/07\/SKIM-AI-Header-Logo.png\",\"width\":194,\"height\":58,\"caption\":\"Skim AI\"},\"image\":{\"@id\":\"https:\/\/skimai.com\/uk\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.linkedin.com\/company\/skim-ai\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/skimai.com\/uk\/#\/schema\/person\/7a883b4a2d2ea22040f42a7975eb86c6\",\"name\":\"Greggory Elias\",\"url\":\"https:\/\/skimai.com\/it\/author\/gregg\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Come richiedere OpenAI o1 + Dovreste usarlo? - AI&amp;YOU #72 - Skim AI","description":"Esplorate il cambiamento di paradigma con il modello o1 di OpenAI, progettato per compiti di ragionamento complessi. Scoprite come utilizzarlo in modo efficace, scoprite chi dovrebbe usarlo e immergetevi in 15 statistiche e fatti chiave che mostrano le sue capacit\u00e0 rivoluzionarie.","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:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/","og_locale":"it_IT","og_type":"article","og_title":"How to Prompt OpenAI o1 + Should You Use It? - AI&YOU #72 - Skim AI","og_description":"Explore the paradigm shift with OpenAI's o1 model, designed for complex reasoning tasks. Learn how to prompt it effectively, discover who should use it, and dive into 15 key stats and facts that showcase its groundbreaking capabilities.","og_url":"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/","og_site_name":"Skim AI","article_published_time":"2024-10-08T19:11:04+00:00","og_image":[{"width":1092,"height":612,"url":"https:\/\/skimai.com\/wp-content\/uploads\/2024\/10\/AIYOU72.png","type":"image\/png"}],"author":"Greggory Elias","twitter_card":"summary_large_image","twitter_misc":{"Scritto da":"Greggory Elias","Tempo di lettura stimato":"10 minuti"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#article","isPartOf":{"@id":"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/"},"author":{"name":"Greggory Elias","@id":"https:\/\/skimai.com\/uk\/#\/schema\/person\/7a883b4a2d2ea22040f42a7975eb86c6"},"headline":"How to Prompt OpenAI o1 + Should You Use It? &#8211; AI&#038;YOU #72","datePublished":"2024-10-08T19:11:04+00:00","dateModified":"2024-10-08T19:11:04+00:00","mainEntityOfPage":{"@id":"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/"},"wordCount":1955,"publisher":{"@id":"https:\/\/skimai.com\/uk\/#organization"},"image":{"@id":"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#primaryimage"},"thumbnailUrl":"https:\/\/skimai.com\/wp-content\/uploads\/2024\/10\/AIYOU72.png","articleSection":["Generative AI","LLMs \/ NLP","Newsletter","Prompt Engineering"],"inLanguage":"it-IT"},{"@type":"WebPage","@id":"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/","url":"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/","name":"Come richiedere OpenAI o1 + Dovreste usarlo? - AI&amp;YOU #72 - Skim AI","isPartOf":{"@id":"https:\/\/skimai.com\/uk\/#website"},"primaryImageOfPage":{"@id":"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#primaryimage"},"image":{"@id":"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#primaryimage"},"thumbnailUrl":"https:\/\/skimai.com\/wp-content\/uploads\/2024\/10\/AIYOU72.png","datePublished":"2024-10-08T19:11:04+00:00","dateModified":"2024-10-08T19:11:04+00:00","description":"Esplorate il cambiamento di paradigma con il modello o1 di OpenAI, progettato per compiti di ragionamento complessi. Scoprite come utilizzarlo in modo efficace, scoprite chi dovrebbe usarlo e immergetevi in 15 statistiche e fatti chiave che mostrano le sue capacit\u00e0 rivoluzionarie.","breadcrumb":{"@id":"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#breadcrumb"},"inLanguage":"it-IT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/"]}]},{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#primaryimage","url":"https:\/\/skimai.com\/wp-content\/uploads\/2024\/10\/AIYOU72.png","contentUrl":"https:\/\/skimai.com\/wp-content\/uploads\/2024\/10\/AIYOU72.png","width":1092,"height":612,"caption":"AI&YOU#72"},{"@type":"BreadcrumbList","@id":"https:\/\/skimai.com\/it\/come-richiedere-luso-di-openai-o1-se-lo-si-deve-usare-aiyou-72\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/skimai.com\/"},{"@type":"ListItem","position":2,"name":"How to Prompt OpenAI o1 + Should You Use It? &#8211; AI&#038;YOU #72"}]},{"@type":"WebSite","@id":"https:\/\/skimai.com\/uk\/#website","url":"https:\/\/skimai.com\/uk\/","name":"Skim AI","description":"La piattaforma per la forza lavoro degli agenti AI","publisher":{"@id":"https:\/\/skimai.com\/uk\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/skimai.com\/uk\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"it-IT"},{"@type":"Organization","@id":"https:\/\/skimai.com\/uk\/#organization","name":"Skim AI","url":"https:\/\/skimai.com\/uk\/","logo":{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/skimai.com\/uk\/#\/schema\/logo\/image\/","url":"http:\/\/skimai.com\/wp-content\/uploads\/2020\/07\/SKIM-AI-Header-Logo.png","contentUrl":"http:\/\/skimai.com\/wp-content\/uploads\/2020\/07\/SKIM-AI-Header-Logo.png","width":194,"height":58,"caption":"Skim AI"},"image":{"@id":"https:\/\/skimai.com\/uk\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.linkedin.com\/company\/skim-ai"]},{"@type":"Person","@id":"https:\/\/skimai.com\/uk\/#\/schema\/person\/7a883b4a2d2ea22040f42a7975eb86c6","name":"Greggory Elias","url":"https:\/\/skimai.com\/it\/author\/gregg\/"}]}},"_links":{"self":[{"href":"https:\/\/skimai.com\/it\/wp-json\/wp\/v2\/posts\/13154","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/skimai.com\/it\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/skimai.com\/it\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/skimai.com\/it\/wp-json\/wp\/v2\/users\/1003"}],"replies":[{"embeddable":true,"href":"https:\/\/skimai.com\/it\/wp-json\/wp\/v2\/comments?post=13154"}],"version-history":[{"count":0,"href":"https:\/\/skimai.com\/it\/wp-json\/wp\/v2\/posts\/13154\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/skimai.com\/it\/wp-json\/wp\/v2\/media\/13157"}],"wp:attachment":[{"href":"https:\/\/skimai.com\/it\/wp-json\/wp\/v2\/media?parent=13154"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/skimai.com\/it\/wp-json\/wp\/v2\/categories?post=13154"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/skimai.com\/it\/wp-json\/wp\/v2\/tags?post=13154"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}