{"id":260,"date":"2026-10-09T18:29:35","date_gmt":"2026-10-09T18:29:35","guid":{"rendered":"https:\/\/oliverng.com\/ai\/?p=260"},"modified":"2026-10-09T18:32:33","modified_gmt":"2026-10-09T18:32:33","slug":"jev-openai-decisions-api","status":"publish","type":"post","link":"https:\/\/oliverng.com\/ai\/2026\/10\/09\/jev-openai-decisions-api\/","title":{"rendered":"Jev &amp; OpenAI Decisions API"},"content":{"rendered":"\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-794e3cfa wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\">\n<p class=\"wp-block-paragraph\">I haven&#8217;t written about <a href=\"https:\/\/typesafe.ai\/blog\/introducing-system-one-models-and-jev\">Jev<\/a>. I had too much going on this month.  But the AI world was going nuts about it because it was a type safe way to leverage AI in code.  Unstructured in, structured out.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Last month, I wrote about my <a href=\"https:\/\/oliverng.com\/ai\/2026\/09\/15\/foundationmodels-and-my-news-app\/\" data-type=\"post\" data-id=\"191\">FoundationModels in iOS27<\/a> explorations where I used an on-device LLM to make decisions on code.  I was amazed at how complex algorithmic instructions could be done with a simple prompt, and then used to direct my application logic.  The problem was that comparing deterministic algorithms with LLM reasoning is no contest.  I knew it would be slow and had to restrict where I would use this type of decision making.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Jev changed all that last month where models came out that were trained to act fast and make decisions.  Suddenly integrating an LLM into code was no longer a liability.<\/p>\n\n\n\n<meta name=\"referrer\" content=\"always\">\n\n<iframe loading=\"lazy\" width=\"560\" height=\"315\" src=\"https:\/\/www.youtube.com\/embed\/FB6oCmrIj-Y?si=0Quv1zgmOGvTkICG\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen=\"\"><\/iframe>\n\n\n\n<p class=\"wp-block-paragraph\">OpenAI noticed.  And today, released <a href=\"https:\/\/developers.openai.com\/api\/docs\/guides\/decisions\">Decisions API<\/a>.  The video below shows its use in code, with the video game <a href=\"https:\/\/developers.openai.com\/api\/docs\/guides\/decisions#select-from-fixed-options\">steering demo<\/a> being most interesting to me because it highlights the quickness and accuracy of the LLM to code decision making.  But wait, this is not text, this is also multi-model as it can process images and act on it&#8230; <strong>within 150ms!  <\/strong>&#8220;ms&#8221;! <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">While it isn&#8217;t coding fast, it is way faster than your typical frontier model response of multiple seconds.  Which makes integrating LLM into code a viable option.  Coding has changed more this past 12 months than it has in 10 years.<\/p>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>I haven&#8217;t written about Jev. I had too much going on this month. But the AI world was going nuts about it because it was a type safe way to leverage AI in code. Unstructured in, structured out. Last month, I wrote about my FoundationModels in iOS27 explorations where I used an on-device LLM to [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-260","post","type-post","status-publish","format-standard","hentry","category-experimenting"],"_links":{"self":[{"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/posts\/260","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/comments?post=260"}],"version-history":[{"count":7,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/posts\/260\/revisions"}],"predecessor-version":[{"id":268,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/posts\/260\/revisions\/268"}],"wp:attachment":[{"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/media?parent=260"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/categories?post=260"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/tags?post=260"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}