{"id":95716,"date":"2024-10-24T12:31:10","date_gmt":"2024-10-24T16:31:10","guid":{"rendered":"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/"},"modified":"2025-02-27T08:38:27","modified_gmt":"2025-02-27T13:38:27","slug":"ai-inferencing-at-crossroads","status":"publish","type":[3762],"link":"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/","title":{"rendered":"AI inferencing at crossroads"},"content":{"rendered":"<div  class=\"bbg-row-container\">\n    <section class=\"bbg-row  text--black row-padding--top-compact row-padding--bottom-none bbg-row--full-bg-bleed\" data-anchor='row-6a0023e1f1422'>\n        \n        \n        <div\n            class=\"bbg-row--content\"\n                    >\n            \n            <p><div\n    class=\"bbg-column bbg-column--width-7\"\n    style=\"\"\n    >\n    <p><div\n    class=\"bbg-spacer bbg-spacer--lg\"\n    >\n<\/div><div\n\tclass=\"bb-wysiwyg\"\n\t\t>\n\t<p class=\"small\"><strong><span style=\"font-size: 14px; letter-spacing: 1px; color: #0062dd;\">ARTICLE<\/span><\/strong><\/p>\n\n<\/div>\n<div\n    class=\"bbg-spacer bbg-spacer--sm\"\n    >\n<\/div>    <h1 class=\"bbg-metadata bbg-metadata--title\">AI inferencing at crossroads<\/h1>\n<div\n    class=\"bbg-spacer\"\n        style=\"height: 50px !important\"\n    >\n<\/div>    <ul class=\"bbg-categories_list\">\n                    <li>\n                <a href=\"https:\/\/www.bloomberg.com\/professional\/insights\/category\/artificial-intelligence\/\" rel=\"category tag\">\n                    Artificial Intelligence\n                <\/a>\n            <\/li>\n            <\/ul>\n<\/p>\n\n<\/div><div\n    class=\"bbg-column bbg-column--width-5\"\n    style=\"\"\n    >\n    <div id=\"\" class=\"wpb_content_element bbg-single-image align-left\">\n    <figure class=\"bbg-single-image__figure\" style=\"max-width:100%\">\n                <img loading=\"lazy\" decoding=\"async\" width=\"500\" height=\"328\" src=\"https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/NEW-PHOTO1.png\" class=\"bbg-single-image__image attachment-full\" alt=\"\" title=\"NEW-PHOTO1\" \/>\n        \n            <\/figure>\n<\/div>\n\n\n\n<\/div>\n\n\n                    <\/div>\n    <\/section>\n<\/div>\n\n<div  class=\"bbg-row-container\">\n    <section class=\"bbg-row  text--black row-padding--top-none row-padding--bottom-none bbg-row--full-bg-bleed\" data-anchor='row-6a0023e2076a3'>\n        \n        \n        <div\n            class=\"bbg-row--content\"\n                    >\n            \n            <p><div\n    class=\"bbg-column bbg-column--width-2\"\n    style=\"\"\n    >\n    \n<\/div><div\n    class=\"bbg-column bbg-column--width-6 bbg-column--m-width-6\"\n    style=\"\"\n    >\n    <p>    <p class=\"bbg-metadata bbg-metadata--date\">October 24, 2024<\/p>\n<div\n\tclass=\"bb-wysiwyg\"\n\t\t>\n\t<p><strong>Bloomberg Intelligence<\/strong><\/p>\n\n<\/div>\n\n<\/div><div\n    class=\"bbg-column bbg-column--width-2 bbg-column--valign-middle bbg-column--m-width-2 bbg-column--s-padding-right-2\"\n    style=\"\"\n    >\n    <div class=\"bb-tts\"\n\tdata-selector=\"main\"\n\tdata-label=\"Speak this page\"\n\tdata-custom-play=\"Play\"\n\tdata-custom-pause=\"Pause\"\n\tdata-custom-stop=\"Stop\"\n\tdata-overlay=\"false\"\n\tdata-invert=\"false\"\n\tdata-no-time=\"false\"\n\tdata-no-button-text=\"false\"\n\tdata-one-button=\"true\"\n\tdata-one-style=\"true\"\n\tdata-hide-stop=\"true\"\n\tdata-voice=\"Gordon\"\n\tdata-pitch=\"1\"\n\tdata-speed=\"1\"\n\tdata-align=\"flex-start\"\n>\n<\/div>\n\n\n<\/div><div\n    class=\"bbg-column bbg-column--width-2\"\n    style=\"\"\n    >\n    \n<\/div>\n\n\n                    <\/div>\n    <\/section>\n<\/div>\n\n<div  class=\"bbg-row-container\">\n    <section class=\"bbg-row  text--black row-padding--top-compact row-padding--bottom-compact bbg-row--full-bg-bleed\" data-anchor='row-6a0023e209ed7'>\n        \n        \n        <div\n            class=\"bbg-row--content\"\n                    >\n            \n            <p><div\n    class=\"bbg-column bbg-column--width-2\"\n    style=\"\"\n    >\n    \n<\/div><div\n    class=\"bbg-column bbg-column--width-8\"\n    style=\"\"\n    >\n    <div\n\tclass=\"bb-wysiwyg\"\n\t\t>\n\t<p><i>This analysis is by Bloomberg Intelligence Senior Industry Analyst Mandeep Singh. It appeared first on the Bloomberg Terminal.<\/i><\/p>\n<p>Hyperscale-cloud sales of $235 billion getting a boost from generative- AI workload contributions, coupled with increased reasoning capabilities for pre-trained models, could drive faster growth in inferencing relative to the larger training market. We believe techniques such as quantization and distillation may gain momentum to shrink the size of trained models for more privacy-centric use cases, including personal assistants and AI agents.<\/p>\n\n<\/div>\n\n\n<\/div>\n\n\n                    <\/div>\n    <\/section>\n<\/div>\n\n<div  class=\"bbg-row-container\">\n    <section class=\"bbg-row  text--black row-padding--top-none row-padding--bottom-none bbg-row--margin-top-compact bbg-row--margin-bottom-compact bbg-row--full-bg-bleed\" data-anchor='row-6a0023e20b599'>\n        \n        \n        <div\n            class=\"bbg-row--content\"\n                    >\n            \n            <div\n    class=\"bbg-column\"\n    style=\"\"\n    >\n    <div class=\"bbg-interstitial\" aria-label=\"interstitial\" tabindex=\"0\">\n\t<style>\n\t\t.bbg-interstitial #card_1.bbg-card_hasCta{\n\t\t\tbackground: url(https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Interstitial_bg.png);\n\t\t\t\tbackground-repeat: no-repeat;\n\t\t\t\tbackground-position: center center;\n\t\t\t\tbackground-size: cover;\n\t\t\tpadding: 104px;\n\t\t\t\n\t\t\t\n\t\t}\n\t\t.bbg-interstitial #card_1.bbg-card_hasCta .bbg-card__content, .bbg-interstitial #card_1.bbg-card_hasCta .bbg-card__content p{\n\t\t\tcolor:white;\n\t\t}\n\t\t@media (max-width: 768px) {\n\t\t\t.bbg-interstitial #card_1.bbg-card_hasCta{\n\t\t\t\tpadding: 80px 32px;\n\t\t\t}\n\t\t}\n\t\t@media (max-width: 480px) {\n\t\t\t.bbg-interstitial #card_1.bbg-card_hasCta{\n\t\t\t\tpadding: 80px 18px;\n\t\t\t}\n\t\t}\n\t<\/style>\n\t<div class=\"wpb_content_element bbg-card  bbg-card-dark bbg-card_hasCta has_interstitial\" id=\"card_1\" data-card_type=\"no_image\">\n  \n  \n  <div class=\"bbg-card__innerwrapper\">\n    <div class=\"bbg-card__content\">\n      \n      \n                      <h3 class=\"bbg-card__title\">Discover more with Bloomberg newsletters<\/h3>\n      \n              <div class=\"bbg-card__wysiwyg bb-wysiwyg\"><p>Subscribe now<\/p>\n<\/div>\n          <\/div>\n\n          \n<div\n  id=\"cta_4916508704761406106\"\n  class=\"wpb_content_element bbg-cta icon icon-arrow\">\n  <style>\n    \n    \n    \n  <\/style>\n  <div\n    class=\"bbg-cta-link link-holder\"\n    data-links-type=\"cta-links\">\n    <p class=\"bbg-cta-p right\">\n      <a\n        class=\"bbg-cta-link link interstitial_cta\"\n        href=\"https:\/\/www.bloomberg.com\/professional\/insights\/newsletter\/\"\n        target=\"\"\n        rel=\"\"\n        data-section-name=\"\"\n                role=\"button\"\n        aria-label=\"Learn more\"\n        >\n                <\/a>\n    <\/p>\n  <\/div>\n<\/div>\n\n      <\/div>\n\n  <\/div>\n\n<\/div>\n\n\n<\/div>\n\n\n                    <\/div>\n    <\/section>\n<\/div>\n\n<div  class=\"bbg-row-container\">\n    <section class=\"bbg-row  text--black row-padding--top-none bbg-row--full-bg-bleed\" data-anchor='row-6a0023e210061'>\n        \n        \n        <div\n            class=\"bbg-row--content\"\n                    >\n            \n            <p><div\n    class=\"bbg-column bbg-column--width-2\"\n    style=\"\"\n    >\n    \n<\/div><div\n    class=\"bbg-column bbg-column--width-8\"\n    style=\"\"\n    >\n    <div\n\tclass=\"bb-wysiwyg\"\n\t\t>\n\t<h2>Cloud vs. on-device inferencing<\/h2>\n\n<\/div>\n<div\n\tclass=\"bb-wysiwyg\"\n\t\t>\n\t<p>Microsoft has already quantified about 7 percentage points of gen-AI workload contribution, primarily from inferencing, to its Azure revenue growth. This equates to about a $5 billion revenue run rate. Other hyperscalers, including Amazon.com and Google, also have multiple billion dollars in gen-AI inferencing workload revenue. Apple Intelligence aims to boost the use of on-device inferencing, which doesn&#8217;t require application programming interface (API) calls to large language model (LLM) providers.<\/p>\n<p>Hyperscale cloud&#8217;s $235 billion revenue could get a lift from inferencing workloads running on the cloud vs. on the edge natively on PCs and smartphones. In the case of Apple Intelligence, on-device LLM may decide to offload certain complex tasks to more powerful models hosted in Apple\u2019s data centers (private cloud compute).<\/p>\n\n<\/div>\n<div id=\"\" class=\"wpb_content_element bbg-single-image align-center\">\n    <figure class=\"bbg-single-image__figure\" style=\"max-width:1024px\">\n                <img loading=\"lazy\" decoding=\"async\" width=\"800\" height=\"361\" src=\"https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-134.png\" class=\"bbg-single-image__image attachment-large\" alt=\"Cloud and AI Inferencing ARR ($ in Billions)\" title=\"Figure-134\" srcset=\"https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-134.png 800w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-134.png 552w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-134.png 768w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-134.png 1475w\" sizes=\"auto, (max-width: 800px) 100vw, 800px\" \/>\n        \n            <\/figure>\n<\/div>\n\n<div\n\tclass=\"bb-wysiwyg\"\n\t\t>\n\t<h2>Reasoning vs. smaller models<\/h2>\n\n<\/div>\n<div\n\tclass=\"bb-wysiwyg\"\n\t\t>\n\t<p>A pivot to smaller models with fewer parameters, which can be used for specific tasks vs. LLMs, will likely fuel a secular shift in applications to agent functionality. OpenAI released its &#8220;chain-of-reasoning&#8221; o1 model, along with an o1-mini version, to showcase improvements in reasoning capabilities. Given the difference in pricing across various versions of LLMs, we believe companies may mix LLMs from different providers, depending on the query.<\/p>\n<p>A small, low latency AI model (5-10B parameters) will be included in iOS18 as part of the Apple Intelligence framework, which will be able to understand user commands, the current screen and take actions on apps. It can handle tasks like summarization, as well as power the \u201cAI agent\u201d features of Siri, including user commands that require utilizing multiple apps.<\/p>\n\n<\/div>\n<div id=\"\" class=\"wpb_content_element bbg-single-image align-center\">\n    <figure class=\"bbg-single-image__figure\" style=\"max-width:1024px\">\n                <img loading=\"lazy\" decoding=\"async\" width=\"800\" height=\"505\" src=\"https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-230.png\" class=\"bbg-single-image__image attachment-large\" alt=\"Foundational Language Model Pricing\/Performance\" title=\"Figure-230\" srcset=\"https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-230.png 800w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-230.png 552w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-230.png 768w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-230.png 1460w\" sizes=\"auto, (max-width: 800px) 100vw, 800px\" \/>\n        \n            <\/figure>\n<\/div>\n\n<div\n\tclass=\"bb-wysiwyg\"\n\t\t>\n\t<h2>Shrinking LLM parameters for on-device inferencing<\/h2>\n\n<\/div>\n<div\n\tclass=\"bb-wysiwyg\"\n\t\t>\n\t<p>As LLMs grow exponentially larger, the number of floating point operations (FLOPs) is expanding amid parameter counts that demand significantly greater computational resources. To offset rising LLM costs, foundational model companies will seek to shrink the size of trained models for lowering inferencing costs for broader use cases across enterprise and consumer applications.<\/p>\n<p>Most foundational model providers including OpenAI GPT, Anthropic Claude, Google Gemini, Meta Llama and Mistral have released smaller versions using quantization and distillation for edge use cases to run LLMs natively on PC and smartphone devices. We believe shrinking the parameter size of models will become more important amid continuous scaling of datasets and tokens used in the transformer architecture that underpins most foundational LLMs.<\/p>\n\n<\/div>\n<div id=\"\" class=\"wpb_content_element bbg-single-image align-center\">\n    <figure class=\"bbg-single-image__figure\" style=\"max-width:1024px\">\n                <img loading=\"lazy\" decoding=\"async\" width=\"800\" height=\"345\" src=\"https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-326.png\" class=\"bbg-single-image__image attachment-large\" alt=\"Foundational LLMs Training Comparison\" title=\"Figure-326\" srcset=\"https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-326.png 800w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-326.png 552w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-326.png 768w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-326.png 1469w\" sizes=\"auto, (max-width: 800px) 100vw, 800px\" \/>\n        \n            <\/figure>\n<\/div>\n\n<div\n\tclass=\"bb-wysiwyg\"\n\t\t>\n\t<h2>Inferencing efficiency aids margin<\/h2>\n\n<\/div>\n<div\n\tclass=\"bb-wysiwyg\"\n\t\t>\n\t<p>Inference efficiency will likely become a big focus given the high training costs and reliance on the latest GPU chips for performance and smarter power use. We believe most companies will seek ways to increase the utilization of their existing compute infrastructure &#8212; using both custom chips and smaller models &#8212; while lowering their total inferencing costs.<\/p>\n<p>Even amid the elevated spending expectations of hyperscale-cloud providers, we believe a corresponding increase in cloud sales and the use of lowest-cost model should be a driver of margin for cloud providers. This is as the inferencing market continues to expand beyond coding copilots and customer-service chatbots, and into other types of applications and use cases.<\/p>\n\n<\/div>\n<div id=\"\" class=\"wpb_content_element bbg-single-image align-center\">\n    <figure class=\"bbg-single-image__figure\" style=\"max-width:1024px\">\n                <img loading=\"lazy\" decoding=\"async\" width=\"800\" height=\"363\" src=\"https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-425.png\" class=\"bbg-single-image__image attachment-large\" alt=\"LLM Inference Cost Decreases Over Time\" title=\"Figure-425\" srcset=\"https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-425.png 800w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-425.png 552w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-425.png 768w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&amp;type=webp&amp;url=https:\/\/assets.bbhub.io\/professional\/sites\/41\/Figure-425.png 1451w\" sizes=\"auto, (max-width: 800px) 100vw, 800px\" \/>\n        \n            <\/figure>\n<\/div>\n\n<div\n\tclass=\"bb-wysiwyg\"\n\t\t>\n\t<p><span style=\"font-size: 10px;\"><em>The data included in these materials are for illustrative purposes only. The BLOOMBERG TERMINAL service and Bloomberg data products (the \u201cServices\u201d) are owned and distributed by Bloomberg Finance L.P. (\u201cBFLP\u201d) except (i) in Argentina, Australia and certain jurisdictions in the Pacific Islands, Bermuda, China, India, Japan, Korea and New Zealand, where Bloomberg L.P. and its subsidiaries (\u201cBLP\u201d) distribute these products, and (ii) in Singapore and the jurisdictions serviced by Bloomberg\u2019s Singapore office, where a subsidiary of BFLP distributes these products. BLP provides BFLP and its subsidiaries with global marketing and operational support and service. Certain features, functions, products and services are available only to sophisticated investors and only where permitted. BFLP, BLP and their affiliates do not guarantee the accuracy of prices or other information in the Services. Nothing in the Services shall constitute or be construed as an offering of financial instruments by BFLP, BLP or their affiliates, or as investment advice or recommendations by BFLP, BLP or their affiliates of an investment strategy or whether or not to \u201cbuy\u201d, \u201csell\u201d or \u201chold\u201d an investment. Information available via the Services should not be considered as information sufficient upon which to base an investment decision. The following are trademarks and service marks of BFLP, a Delaware limited partnership, or its subsidiaries: BLOOMBERG, BLOOMBERG ANYWHERE, BLOOMBERG MARKETS, BLOOMBERG NEWS, BLOOMBERG PROFESSIONAL, BLOOMBERG TERMINAL and BLOOMBERG.COM. Absence of any trademark or service mark from this list does not waive Bloomberg\u2019s intellectual property rights in that name, mark or logo. All rights reserved. \u00a9 2024 Bloomberg.<\/em><\/span><\/p>\n\n<\/div>\n\n<\/div>\n\n\n                    <\/div>\n    <\/section>\n<\/div>\n\n<div  class=\"bbg-row-container\">\n    <style>section[data-anchor=row-6a0023e21a106]::before {\n\t\t\t\tbackground-color: #f4f4f9;\n\t\t\t}<\/style>\n    <section class=\"bbg-row bg--custom-color  bg--f4f4f9 text--black bbg-row--full-bg-bleed\" data-anchor='row-6a0023e21a106'>\n        \n        \n        <div\n            class=\"bbg-row--content\"\n                    >\n            \n            <p><div\n    class=\"bbg-column bbg-column--width-8\"\n    style=\"\"\n    >\n    <div\n\tclass=\"bb-wysiwyg\"\n\t\t>\n\t<h3>Related Content<\/h3>\n\n<\/div>\n\n\n<\/div><div\n    class=\"bbg-column bbg-column--width-4 bbg-column--halign-right\"\n    style=\"\"\n    >\n    \n<div\n  id=\"cta_8625717366855305554\"\n  class=\"wpb_content_element bbg-cta icon icon-arrow\">\n  <style>\n    \n    \n    \n  <\/style>\n  <div\n    class=\"bbg-cta-link link-holder\"\n    data-links-type=\"cta-links\">\n    <p class=\"bbg-cta-p right\">\n      <a\n        class=\"bbg-cta-link link\"\n        href=\"https:\/\/www.bloomberg.com\/professional\/insights\/\"\n        target=\"\"\n        rel=\"\"\n        data-section-name=\"View all\"\n        >\n                      View all\n                <\/a>\n    <\/p>\n  <\/div>\n<\/div>\n\n\n<\/div><div\n    class=\"bbg-column\"\n    style=\"\"\n    >\n    <script>\n    window.feed = window.feed || {};\n    window.feed['6a0023e21cd6f'] = {\"config\":{\"uuid\":\"\",\"title\":\"\",\"filter_label\":\"\",\"post_type\":\"post\",\"order_by\":\"date\",\"direction\":\"desc\",\"show_date\":\"no\",\"show_excerpt\":\"no\",\"display\":\"limit\",\"filter\":\"OR\",\"max_items\":\"3\",\"skip_cache\":\"no\",\"feed_style\":\"grid\",\"published_date\":\"\",\"show_cta\":\"\",\"featured_image\":\"yes\",\"el_class\":\"\",\"terms_post\":\"\",\"terms_page\":\"\",\"terms_attachment\":\"\",\"terms_webinar\":\"\",\"terms_bbmegamenu\":\"\",\"terms_directory\":\"\",\"terms_datalayer\":\"\",\"terms_templatera\":\"\",\"terms_bbg-fourofour\":\"\",\"terms_reusable\":\"\",\"terms_cookie_items\":\"\",\"terms_bbl_email_subscriber\":\"\",\"terms_dynamic_table_ticker\":\"\",\"terms_bfix\":\"\",\"terms_quicklinks\":\"\",\"terms_interstitial\":\"\",\"terms_slide\":\"\",\"terms_gated_content_form\":\"\",\"terms_site_alert\":\"\",\"terms_country\":\"\",\"terms_region\":\"\",\"terms\":\"\"},\"cpt\":{\"name\":\"post\",\"label\":\"Posts\",\"labels\":{\"name\":\"Posts\",\"singular_name\":\"Post\",\"add_new\":\"Add New\",\"add_new_item\":\"Add New Post\",\"edit_item\":\"Edit Post\",\"new_item\":\"New Post\",\"view_item\":\"View Post\",\"view_items\":\"View Posts\",\"search_items\":\"Search Posts\",\"not_found\":\"No posts found.\",\"not_found_in_trash\":\"No posts found in Trash.\",\"parent_item_colon\":null,\"all_items\":\"All Posts\",\"archives\":\"Post Archives\",\"attributes\":\"Post Attributes\",\"insert_into_item\":\"Insert into post\",\"uploaded_to_this_item\":\"Uploaded to this post\",\"featured_image\":\"Featured image\",\"set_featured_image\":\"Set featured image\",\"remove_featured_image\":\"Remove featured image\",\"use_featured_image\":\"Use as featured image\",\"filter_items_list\":\"Filter posts list\",\"filter_by_date\":\"Filter by date\",\"items_list_navigation\":\"Posts list navigation\",\"items_list\":\"Posts list\",\"item_published\":\"Post published.\",\"item_published_privately\":\"Post published privately.\",\"item_reverted_to_draft\":\"Post reverted to draft.\",\"item_trashed\":\"Post trashed.\",\"item_scheduled\":\"Post scheduled.\",\"item_updated\":\"Post updated.\",\"item_link\":\"Post Link\",\"item_link_description\":\"A link to a post.\",\"menu_name\":\"Posts\",\"name_admin_bar\":\"Post\"},\"description\":\"\",\"public\":true,\"hierarchical\":false,\"exclude_from_search\":false,\"publicly_queryable\":true,\"show_ui\":true,\"show_in_menu\":true,\"show_in_nav_menus\":true,\"show_in_admin_bar\":true,\"menu_position\":5,\"menu_icon\":\"dashicons-admin-post\",\"capability_type\":\"post\",\"map_meta_cap\":true,\"register_meta_box_cb\":null,\"taxonomies\":[],\"has_archive\":false,\"query_var\":false,\"can_export\":true,\"delete_with_user\":true,\"template\":[],\"template_lock\":false,\"_builtin\":true,\"_edit_link\":\"post.php?post=%d\",\"cap\":{\"edit_post\":\"edit_post\",\"read_post\":\"read_post\",\"delete_post\":\"delete_post\",\"edit_posts\":\"edit_posts\",\"edit_others_posts\":\"edit_others_posts\",\"delete_posts\":\"delete_posts\",\"publish_posts\":\"publish_posts\",\"read_private_posts\":\"read_private_posts\",\"read\":\"read\",\"delete_private_posts\":\"delete_private_posts\",\"delete_published_posts\":\"delete_published_posts\",\"delete_others_posts\":\"delete_others_posts\",\"edit_private_posts\":\"edit_private_posts\",\"edit_published_posts\":\"edit_published_posts\",\"create_posts\":\"edit_posts\"},\"rewrite\":false,\"show_in_rest\":true,\"rest_base\":\"posts\",\"rest_namespace\":\"wp\\\/v2\",\"rest_controller_class\":\"WP_REST_Posts_Controller\",\"rest_controller\":{},\"revisions_rest_controller_class\":false,\"revisions_rest_controller\":{},\"autosave_rest_controller_class\":false,\"autosave_rest_controller\":{},\"late_route_registration\":false},\"taxonomies\":[{\"taxonomy\":\"post_format\",\"terms\":[{\"term_id\":33,\"name\":\"Link\",\"slug\":\"post-format-link\",\"term_group\":0,\"term_taxonomy_id\":33,\"taxonomy\":\"post_format\",\"description\":\"\",\"parent\":0,\"count\":12,\"filter\":\"raw\"},{\"term_id\":666,\"name\":\"Link\",\"slug\":\"post-format-link\",\"term_group\":0,\"term_taxonomy_id\":666,\"taxonomy\":\"post_format\",\"description\":\"\",\"parent\":0,\"count\":2,\"filter\":\"raw\"}]},{\"taxonomy\":\"post_series\",\"terms\":{\"0\":{\"term_id\":3751,\"name\":\"Asia Centric\",\"slug\":\"asia-centric\",\"term_group\":0,\"term_taxonomy_id\":3751,\"taxonomy\":\"post_series\",\"description\":\"\",\"parent\":0,\"count\":51,\"filter\":\"raw\"},\"1\":{\"term_id\":3741,\"name\":\"Bloomberg Expert Access\",\"slug\":\"bloomberg-expert-access\",\"term_group\":0,\"term_taxonomy_id\":3741,\"taxonomy\":\"post_series\",\"description\":\"\",\"parent\":0,\"count\":10,\"filter\":\"raw\"},\"2\":{\"term_id\":3739,\"name\":\"Bloomberg Pro Tips\",\"slug\":\"bloomberg-pro-tips\",\"term_group\":0,\"term_taxonomy_id\":3739,\"taxonomy\":\"post_series\",\"description\":\"\",\"parent\":0,\"count\":59,\"filter\":\"raw\"},\"4\":{\"term_id\":3743,\"name\":\"Functions for the Market\",\"slug\":\"ffm\",\"term_group\":0,\"term_taxonomy_id\":3743,\"taxonomy\":\"post_series\",\"description\":\"\",\"parent\":0,\"count\":7,\"filter\":\"raw\"},\"5\":{\"term_id\":3770,\"name\":\"Market Dialogues\",\"slug\":\"market-dialogues\",\"term_group\":0,\"term_taxonomy_id\":3770,\"taxonomy\":\"post_series\",\"description\":\"\",\"parent\":0,\"count\":11,\"filter\":\"raw\"},\"6\":{\"term_id\":3742,\"name\":\"Need to Know\",\"slug\":\"need-to-know\",\"term_group\":0,\"term_taxonomy_id\":3742,\"taxonomy\":\"post_series\",\"description\":\"\",\"parent\":0,\"count\":15,\"filter\":\"raw\"},\"7\":{\"term_id\":3798,\"name\":\"Pricing Insights\",\"slug\":\"pricing-insights\",\"term_group\":0,\"term_taxonomy_id\":3798,\"taxonomy\":\"post_series\",\"description\":\"\",\"parent\":0,\"count\":6,\"filter\":\"raw\"},\"8\":{\"term_id\":3740,\"name\":\"Terminal Essentials\",\"slug\":\"terminal-essentials\",\"term_group\":0,\"term_taxonomy_id\":3740,\"taxonomy\":\"post_series\",\"description\":\"\",\"parent\":0,\"count\":6,\"filter\":\"raw\"}}},{\"taxonomy\":\"type\",\"terms\":{\"0\":{\"term_id\":3762,\"name\":\"Article\",\"slug\":\"article\",\"term_group\":0,\"term_taxonomy_id\":3762,\"taxonomy\":\"type\",\"description\":\"\",\"parent\":0,\"count\":1641,\"filter\":\"raw\"},\"1\":{\"term_id\":3763,\"name\":\"Case Study\",\"slug\":\"case-study\",\"term_group\":0,\"term_taxonomy_id\":3763,\"taxonomy\":\"type\",\"description\":\"\",\"parent\":0,\"count\":41,\"filter\":\"raw\"},\"3\":{\"term_id\":3765,\"name\":\"Podcast\",\"slug\":\"podcast\",\"term_group\":0,\"term_taxonomy_id\":3765,\"taxonomy\":\"type\",\"description\":\"\",\"parent\":0,\"count\":504,\"filter\":\"raw\"},\"4\":{\"term_id\":3815,\"name\":\"Press Release\",\"slug\":\"press-release\",\"term_group\":0,\"term_taxonomy_id\":3815,\"taxonomy\":\"type\",\"description\":\"\",\"parent\":0,\"count\":81,\"filter\":\"raw\"},\"5\":{\"term_id\":3766,\"name\":\"Q&amp;A\",\"slug\":\"qa\",\"term_group\":0,\"term_taxonomy_id\":3766,\"taxonomy\":\"type\",\"description\":\"\",\"parent\":0,\"count\":101,\"filter\":\"raw\"},\"6\":{\"term_id\":3767,\"name\":\"Report\",\"slug\":\"report\",\"term_group\":0,\"term_taxonomy_id\":3767,\"taxonomy\":\"type\",\"description\":\"\",\"parent\":0,\"count\":77,\"filter\":\"raw\"},\"8\":{\"term_id\":3768,\"name\":\"Video\",\"slug\":\"video\",\"term_group\":0,\"term_taxonomy_id\":3768,\"taxonomy\":\"type\",\"description\":\"\",\"parent\":0,\"count\":135,\"filter\":\"raw\"}}}],\"excluded_taxonomies\":{\"\":[]},\"post_id\":95716};\n<\/script>\n<div class=\"feed\" data-id=\"6a0023e21cd6f\"><\/div>\n\n<\/div>\n\n\n                    <\/div>\n    <\/section>\n<\/div>\n\n<div  class=\"bbg-row-container\">\n    <section class=\"bbg-row  text--black row-padding--top-none bbg-row--margin-top-normal bbg-row--margin-bottom-normal bbg-row--full-bg-bleed\" data-anchor='row-6a0023e21dc27'>\n        \n        \n        <div\n            class=\"bbg-row--content\"\n                    >\n            \n            <div\n    class=\"bbg-column\"\n    style=\"\"\n    >\n    <div class=\"bbg-interstitial\" aria-label=\"interstitial\" tabindex=\"0\">\n\t<style>\n\t\t.bbg-interstitial #card_2.bbg-card_hasCta{\n\t\t\tbackground:#e6f3ff;\n\t\t\tpadding: 104px;\n\t\t\t\n\t\t\t\n\t\t}\n\t\t.bbg-interstitial #card_2.bbg-card_hasCta .bbg-card__content, .bbg-interstitial #card_2.bbg-card_hasCta .bbg-card__content p{\n\t\t\tcolor:black;\n\t\t}\n\t\t@media (max-width: 768px) {\n\t\t\t.bbg-interstitial #card_2.bbg-card_hasCta{\n\t\t\t\tpadding: 80px 32px;\n\t\t\t}\n\t\t}\n\t\t@media (max-width: 480px) {\n\t\t\t.bbg-interstitial #card_2.bbg-card_hasCta{\n\t\t\t\tpadding: 80px 18px;\n\t\t\t}\n\t\t}\n\t<\/style>\n\t<div class=\"wpb_content_element bbg-card  bbg-card-dark bbg-card_hasCta has_interstitial\" id=\"card_2\" data-card_type=\"no_image\">\n  \n  \n  <div class=\"bbg-card__innerwrapper\">\n    <div class=\"bbg-card__content\">\n      \n      \n                      <h3 class=\"bbg-card__title\">Get insights delivered to your inbox<\/h3>\n      \n              <div class=\"bbg-card__wysiwyg bb-wysiwyg\"><p>Sign up for Bloomberg Professional Services newsletter<\/p>\n<\/div>\n          <\/div>\n\n          \n<div\n  id=\"cta_8871232429037559132\"\n  class=\"wpb_content_element bbg-cta icon icon-arrow\">\n  <style>\n    \n    \n    \n  <\/style>\n  <div\n    class=\"bbg-cta-link link-holder\"\n    data-links-type=\"cta-links\">\n    <p class=\"bbg-cta-p right\">\n      <a\n        class=\"bbg-cta-link link interstitial_cta\"\n        href=\"https:\/\/www.bloomberg.com\/professional\/insights\/newsletter\/\"\n        target=\"\"\n        rel=\"\"\n        data-section-name=\"\"\n                role=\"button\"\n        aria-label=\"Learn more\"\n        >\n                <\/a>\n    <\/p>\n  <\/div>\n<\/div>\n\n      <\/div>\n\n  <\/div>\n\n<\/div>\n\n\n<\/div>\n\n\n                    <\/div>\n    <\/section>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Bloomberg Intelligence believes techniques such as quantization and distillation may gain momentum to shrink the size of trained models for more privacy-centric use cases, including personal assistants and AI agents.<\/p>\n","protected":false},"author":1938,"featured_media":96806,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"template-article.php","format":"standard","meta":{"_yoast_wpseo_primary_category":"3715","footnotes":""},"categories":[3715],"tags":[603,565,3668,577],"series":[],"class_list":["post-95716","post","type-post","status-publish","format-standard","hentry","category-artificial-intelligence","tag-ai-machine-learning","tag-bloomberg-intelligence","tag-cloud","tag-research","type-article"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v19.11 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>AI inferencing at crossroads | Insights | Bloomberg Professional Services<\/title>\n<meta name=\"description\" content=\"Bloomberg Intelligence believes techniques such as quantization and distillation may gain momentum to shrink the size of trained models for more privacy-centric use cases, including personal assistants and AI agents.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AI inferencing at crossroads | Insights | Bloomberg Professional Services\" \/>\n<meta property=\"og:description\" content=\"Bloomberg Intelligence believes techniques such as quantization and distillation may gain momentum to shrink the size of trained models for more privacy-centric use cases, including personal assistants and AI agents.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/\" \/>\n<meta property=\"og:site_name\" content=\"Bloomberg Professional Services\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/bloomberglp\" \/>\n<meta property=\"article:published_time\" content=\"2024-10-24T16:31:10+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-02-27T13:38:27+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/assets.bbhub.io\/professional\/sites\/41\/NEW-PHOTO-800x526.png\" \/>\n\t<meta property=\"og:image:width\" content=\"800\" \/>\n\t<meta property=\"og:image:height\" content=\"526\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"emincer2\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@theterminal\" \/>\n<meta name=\"twitter:site\" content=\"@theterminal\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"emincer2\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/\"},\"author\":{\"name\":\"emincer2\",\"@id\":\"https:\/\/www.bloomberg.com\/professional\/#\/schema\/person\/2bbaed889456449ebb090d7bf4202a98\"},\"headline\":\"AI inferencing at crossroads\",\"datePublished\":\"2024-10-24T16:31:10+00:00\",\"dateModified\":\"2025-02-27T13:38:27+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/\"},\"wordCount\":\"1242\",\"publisher\":{\"@id\":\"https:\/\/www.bloomberg.com\/professional\/#organization\"},\"keywords\":[\"Artificial Intelligence\/Machine learning\",\"Bloomberg Intelligence\",\"Cloud\",\"Research\"],\"articleSection\":[\"Artificial Intelligence\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/\",\"url\":\"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/\",\"name\":\"AI inferencing at crossroads | Insights | Bloomberg Professional Services\",\"isPartOf\":{\"@id\":\"https:\/\/www.bloomberg.com\/professional\/#website\"},\"datePublished\":\"2024-10-24T16:31:10+00:00\",\"dateModified\":\"2025-02-27T13:38:27+00:00\",\"description\":\"Bloomberg Intelligence believes techniques such as quantization and distillation may gain momentum to shrink the size of trained models for more privacy-centric use cases, including personal assistants and AI agents.\",\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/\"]}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.bloomberg.com\/professional\/#website\",\"url\":\"https:\/\/www.bloomberg.com\/professional\/\",\"name\":\"Bloomberg Professional Services\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/www.bloomberg.com\/professional\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.bloomberg.com\/professional\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.bloomberg.com\/professional\/#organization\",\"name\":\"Bloomberg Professional Services\",\"url\":\"https:\/\/www.bloomberg.com\/professional\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.bloomberg.com\/professional\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/assets.bbhub.io\/image\/v1\/convert?type=auto&amp;url=https%3A%2F%2Fassets.bbhub.io%2Fprofessional%2Fsites%2F41%2Flogo.png\",\"contentUrl\":\"https:\/\/assets.bbhub.io\/image\/v1\/convert?type=auto&amp;url=https%3A%2F%2Fassets.bbhub.io%2Fprofessional%2Fsites%2F41%2Flogo.png\",\"width\":\"512\",\"height\":\"103\",\"caption\":\"Bloomberg Professional Services\"},\"image\":{\"@id\":\"https:\/\/www.bloomberg.com\/professional\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.instagram.com\/bloomberg\/\",\"https:\/\/www.linkedin.com\/showcase\/bloomberg-professional-service\/\",\"https:\/\/www.facebook.com\/bloomberglp\",\"https:\/\/twitter.com\/theterminal\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.bloomberg.com\/professional\/#\/schema\/person\/2bbaed889456449ebb090d7bf4202a98\",\"name\":\"Bloomberg Professional Services\",\"url\":\"https:\/\/www.bloomberg.com\/professional\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"AI inferencing at crossroads | Insights | Bloomberg Professional Services","description":"Bloomberg Intelligence believes techniques such as quantization and distillation may gain momentum to shrink the size of trained models for more privacy-centric use cases, including personal assistants and AI agents.","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:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/","og_locale":"en_US","og_type":"article","og_title":"AI inferencing at crossroads | Insights | Bloomberg Professional Services","og_description":"Bloomberg Intelligence believes techniques such as quantization and distillation may gain momentum to shrink the size of trained models for more privacy-centric use cases, including personal assistants and AI agents.","og_url":"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/","og_site_name":"Bloomberg Professional Services","article_publisher":"https:\/\/www.facebook.com\/bloomberglp","article_published_time":"2024-10-24T16:31:10+00:00","article_modified_time":"2025-02-27T13:38:27+00:00","og_image":[{"width":800,"height":526,"url":"https:\/\/assets.bbhub.io\/professional\/sites\/41\/NEW-PHOTO-800x526.png","type":"image\/png"}],"author":"emincer2","twitter_card":"summary_large_image","twitter_creator":"@theterminal","twitter_site":"@theterminal","twitter_misc":{"Written by":"emincer2","Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/#article","isPartOf":{"@id":"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/"},"author":{"name":"emincer2","@id":"https:\/\/www.bloomberg.com\/professional\/#\/schema\/person\/2bbaed889456449ebb090d7bf4202a98"},"headline":"AI inferencing at crossroads","datePublished":"2024-10-24T16:31:10+00:00","dateModified":"2025-02-27T13:38:27+00:00","mainEntityOfPage":{"@id":"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/"},"wordCount":"1242","publisher":{"@id":"https:\/\/www.bloomberg.com\/professional\/#organization"},"keywords":["Artificial Intelligence\/Machine learning","Bloomberg Intelligence","Cloud","Research"],"articleSection":["Artificial Intelligence"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/","url":"https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/","name":"AI inferencing at crossroads | Insights | Bloomberg Professional Services","isPartOf":{"@id":"https:\/\/www.bloomberg.com\/professional\/#website"},"datePublished":"2024-10-24T16:31:10+00:00","dateModified":"2025-02-27T13:38:27+00:00","description":"Bloomberg Intelligence believes techniques such as quantization and distillation may gain momentum to shrink the size of trained models for more privacy-centric use cases, including personal assistants and AI agents.","inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.bloomberg.com\/professional\/insights\/artificial-intelligence\/ai-inferencing-at-crossroads\/"]}]},{"@type":"WebSite","@id":"https:\/\/www.bloomberg.com\/professional\/#website","url":"https:\/\/www.bloomberg.com\/professional\/","name":"Bloomberg Professional Services","description":"","publisher":{"@id":"https:\/\/www.bloomberg.com\/professional\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.bloomberg.com\/professional\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.bloomberg.com\/professional\/#organization","name":"Bloomberg Professional Services","url":"https:\/\/www.bloomberg.com\/professional\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.bloomberg.com\/professional\/#\/schema\/logo\/image\/","url":"https:\/\/assets.bbhub.io\/image\/v1\/convert?type=auto&amp;url=https%3A%2F%2Fassets.bbhub.io%2Fprofessional%2Fsites%2F41%2Flogo.png","contentUrl":"https:\/\/assets.bbhub.io\/image\/v1\/convert?type=auto&amp;url=https%3A%2F%2Fassets.bbhub.io%2Fprofessional%2Fsites%2F41%2Flogo.png","width":"512","height":"103","caption":"Bloomberg Professional Services"},"image":{"@id":"https:\/\/www.bloomberg.com\/professional\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.instagram.com\/bloomberg\/","https:\/\/www.linkedin.com\/showcase\/bloomberg-professional-service\/","https:\/\/www.facebook.com\/bloomberglp","https:\/\/twitter.com\/theterminal"]},{"@type":"Person","@id":"https:\/\/www.bloomberg.com\/professional\/#\/schema\/person\/2bbaed889456449ebb090d7bf4202a98","name":"Bloomberg Professional Services","url":"https:\/\/www.bloomberg.com\/professional"}]}},"_links":{"self":[{"href":"https:\/\/www.bloomberg.com\/professional\/wp-json\/wp\/v2\/posts\/95716","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.bloomberg.com\/professional\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bloomberg.com\/professional\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bloomberg.com\/professional\/wp-json\/wp\/v2\/users\/1938"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bloomberg.com\/professional\/wp-json\/wp\/v2\/comments?post=95716"}],"version-history":[{"count":9,"href":"https:\/\/www.bloomberg.com\/professional\/wp-json\/wp\/v2\/posts\/95716\/revisions"}],"predecessor-version":[{"id":109203,"href":"https:\/\/www.bloomberg.com\/professional\/wp-json\/wp\/v2\/posts\/95716\/revisions\/109203"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.bloomberg.com\/professional\/wp-json\/wp\/v2\/media\/96806"}],"wp:attachment":[{"href":"https:\/\/www.bloomberg.com\/professional\/wp-json\/wp\/v2\/media?parent=95716"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bloomberg.com\/professional\/wp-json\/wp\/v2\/categories?post=95716"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bloomberg.com\/professional\/wp-json\/wp\/v2\/tags?post=95716"},{"taxonomy":"post_series","embeddable":true,"href":"https:\/\/www.bloomberg.com\/professional\/wp-json\/wp\/v2\/series?post=95716"},{"taxonomy":"type","embeddable":true,"href":"https:\/\/www.bloomberg.com\/professional\/wp-json\/wp\/v2\/type?post=95716"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}