{"id":23529,"date":"2026-08-26T17:54:35","date_gmt":"2026-08-26T17:54:35","guid":{"rendered":"https:\/\/scannn.com\/some-recent-applications-of-ai-nate-meyvis\/"},"modified":"2026-08-26T17:54:35","modified_gmt":"2026-08-26T17:54:35","slug":"some-recent-applications-of-ai-nate-meyvis","status":"publish","type":"post","link":"https:\/\/scannn.com\/lv\/some-recent-applications-of-ai-nate-meyvis\/","title":{"rendered":"Some recent applications of AI \u2013 Nate Meyvis"},"content":{"rendered":"\n<div>\n<p><!-- Powered by Bear Blog --><\/p>\n<p><head><\/p>\n<p>  <meta charset=\"utf-8\"\/><br \/>\n  <meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0, maximum-scale=5\"\/><\/p>\n<p>  <title>Some recent applications of AI \u2013 Nate Meyvis<\/title>\n  <link rel=\"canonical\" href=\"https:\/\/www.natemeyvis.com\/some-recent-applications-of-ai\/\"\/>\n<p>    <meta name=\"nwm\" content=\"look-for-the-bear-necessities\"\/><br \/>\n    <meta name=\"token\" content=\"mLwAMBCdSXUvFwLQjfgi\"\/><\/p>\n<p><!-- Primary Meta Tags --><br \/>\n<meta name=\"title\" content=\"Some recent applications of AI\"\/><br \/>\n<meta name=\"description\" content=\"Trevor McKendrick asked for favorite recent applications of AI. Here are some of mine:&#13;&#10;I have a large corpus in which I want to find the most frequently occ...\"\/><\/p>\n<p><!-- Open Graph \/ Facebook --><br \/>\n<meta property=\"og:site_name\" content=\"Nate Meyvis\"\/><br \/>\n<meta property=\"og:title\" content=\"Some recent applications of AI\"\/><br \/>\n<meta property=\"og:type\" content=\"article\"\/><br \/>\n<meta property=\"og:url\" content=\"https:\/\/www.natemeyvis.com\/some-recent-applications-of-ai\/\"\/><br \/>\n<meta property=\"og:description\" content=\"Trevor McKendrick asked for favorite recent applications of AI. Here are some of mine:&#13;&#10;I have a large corpus in which I want to find the most frequently occ...\"\/><br \/>\n<meta property=\"og:image\" content=\"\/static\/og-image.png\"\/><\/p>\n<p><!-- Twitter --><br \/>\n<meta property=\"twitter:card\" content=\"summary\"\/><br \/>\n<meta property=\"twitter:url\" content=\"https:\/\/www.natemeyvis.com\/some-recent-applications-of-ai\/\"\/><br \/>\n<meta property=\"twitter:title\" content=\"Some recent applications of AI\"\/><br \/>\n<meta property=\"twitter:description\" content=\"Trevor McKendrick asked for favorite recent applications of AI. Here are some of mine:&#13;&#10;I have a large corpus in which I want to find the most frequently occ...\"\/><br \/>\n<meta property=\"twitter:image\" content=\"\/static\/og-image.png\"\/><\/p>\n<p><!-- Microdata --><\/p>\n<link rel=\"alternate\" type=\"application\/atom+xml\" href=\"https:\/\/www.natemeyvis.com\/feed\/\" title=\"Nate Meyvis\"\/>\n    <link rel=\"alternate\" type=\"application\/rss+xml\" href=\"https:\/\/www.natemeyvis.com\/feed\/?type=rss\" title=\"Nate Meyvis\"\/>\n<link rel=\"icon\" type=\"image\/svg+xml\" href=\"data:image\/svg+xml,%3Csvg%20xmlns=\" http:=\"\"\/>\n<p><\/head><\/p>\n<p><body class=\"post \" onload=\"(function() { document.cookie = `timezone=${Intl.DateTimeFormat().resolvedOptions().timeZone};path=\/`; })()\" id=\"wp_automatic_ReadabilityBody\"><\/p>\n<header>\n    <a class=\"title\" href=\"https:\/\/www.natemeyvis.com\/\"><\/p>\n<p>    <\/a><\/p>\n<nav>\n<p><a href=\"https:\/\/www.natemeyvis.com\/\">Home<\/a> <a href=\"https:\/\/www.natemeyvis.com\/blog\/\">Blog<\/a><\/p>\n<\/nav>\n<\/header>\n<p>  <main><\/p>\n<p>\n            <i><br \/>\n                <time datetime=\"2026-08-25T10:51Z\"><br \/>\n    25 Aug, 2026<br \/>\n<\/time><br \/>\n            <\/i>\n        <\/p>\n<p><a href=\"https:\/\/ckarchive.com\/b\/xmuph6hp4en3kurnppvnqc20gw8kranhd6g7\">Trevor McKendrick asked<\/a> for favorite recent applications of AI. Here are some of mine:<\/p>\n<ol>\n<li>I have a large corpus in which I want to find the most frequently occurring facts. I&#8217;ve built a system that (i) attempts to extract the facts from items in the corpus, (ii) generates their embeddings, and (iii) runs a clustering algorithm over the result to estimate which of the extracted facts should count as the same.<\/li>\n<li>I&#8217;m keeping all important school-related documents in a Claude project. It is <a href=\"https:\/\/www.natemeyvis.com\/civic-applications-of-generative-ai\/\">reliable enough<\/a> at extracting and interpreting practical information that I can ask it to, e.g., update my personal calendar with all the relevant dates.<\/li>\n<li>Speaking of &#8220;now good enough at juggling nontrivial real-world information,&#8221; I&#8217;m finding it not only amusing but actually worthwhile to ask an email- and calendar-connected LLM something like &#8220;please find all the information related to my trip to <em>X<\/em> next week and make sure everything seems on track.&#8221;<\/li>\n<li>I&#8217;m now reliant on using the <a href=\"https:\/\/www.zippyflash.com\/\">Zippyflash<\/a> API via LLM for (i) allowing me to do some of my flashcard reviews with pen and paper (by asking it to generate PDFs of paper-friendly due cards and then asking it to grade my work, confirming any nontrivial right-wrong decisions with me), (ii) allowing me to customize my study sessions in <em>ad hoc<\/em> ways that would be very hard to anticipate in advance, and (iii) allowing me to reschedule low-priority cards in smart ways when I run up a backlog.<\/li>\n<\/ol>\n<p>Some patterns, here and in my other recent AI usage:<\/p>\n<ol>\n<li>There&#8217;s a shape of task that prompts a &#8220;OK, I need to gather a bunch of mostly-unstructured real-world data and check stuff&#8221; reaction. (The school- and trip-information cases are like this.) AI has graduated from &#8220;can see the data and be sort of useful&#8221; to &#8220;can reliably handle these tasks, though I double-check the important stuff.&#8221; This is a huge step up.<\/li>\n<li><a href=\"https:\/\/www.natemeyvis.com\/try-the-very-fast-models\/\">Cheaper, faster models<\/a> are good enough that I don&#8217;t feel much friction when I find a question that might be addressable with AI. (The fact-extraction example is one of several like this.) There&#8217;s a big difference, for me at least, between spending three hours and $50 on something and spending 30 minutes (of active time) and $5 on it.<\/li>\n<li>I also find myself deferring some interesting, low-urgency projects in anticipation of their being much cheaper a few months from now. This involves both prioritization and also some guesswork about which kinds of tasks AI will improve at the most.<\/li>\n<li>I <em>don&#8217;t<\/em> find it much better, compared to a few months ago, with questions like &#8220;what books should be on my list but aren&#8217;t?&#8221; and other high-judgment lifestyle questions. As AI gets vastly better at the basic triage and annoying, lower-judgment data management that I imagine a personal assistant might do, it&#8217;s nowhere near replacing the highest-judgment aspects of a PA&#8217;s job. (N.B.: I have no first-hand experience of personal assistants.)<\/li>\n<\/ol>\n<p class=\"tags\">\n<p>                    <a rel=\"nofollow\" href=\"https:\/\/www.natemeyvis.com\/blog\/?q=generative%20AI\">#generative AI<\/a><\/p>\n<p>                    <a rel=\"nofollow\" href=\"https:\/\/www.natemeyvis.com\/blog\/?q=lifestyle\">#lifestyle<\/a><\/p>\n<p>                    <a rel=\"nofollow\" href=\"https:\/\/www.natemeyvis.com\/blog\/?q=software\">#software<\/a><\/p>\n<p>  <\/main><\/p>\n<footer>\n<p>    <span><br \/>\n        Powered by <a href=\"https:\/\/bearblog.dev\">Bear <span role=\"img\" class=\"bear\" aria-label=\"ASCII bear logo\">\u0295\u2022\u1d25\u2022\u0294<\/span><\/a><br \/>\n    <\/span><\/p>\n<\/footer>\n<p><\/body><br \/>\n<!-- ID: nwm --><br \/>\n<!-- &#128059; -->\n<\/div>\n<p><a href=\"https:\/\/www.natemeyvis.com\/some-recent-applications-of-ai\/?utm_source=tldrnewsletter\">Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Some recent applications of AI \u2013 Nate Meyvis Home Blog 25 Aug, 2026 Trevor McKendrick asked for favorite recent applications of AI. Here are some of mine: I have a large corpus in which I want to find the most frequently occurring facts. I&#8217;ve built a system that (i) attempts to extract the facts from [&hellip;]<\/p>\n","protected":false},"author":16,"featured_media":23530,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[143],"tags":[],"class_list":["post-23529","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai"],"_links":{"self":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/posts\/23529","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/users\/16"}],"replies":[{"embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/comments?post=23529"}],"version-history":[{"count":0,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/posts\/23529\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/media\/23530"}],"wp:attachment":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/media?parent=23529"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/categories?post=23529"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/tags?post=23529"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}