When the Tailor beta launches, the app will use a small model from Arcee AI called Trinity-Mini-Base<\/a>, a 26B model with a mixture-of-experts layer that helps it work efficiently even at its small size.<\/p>\n\n\n\n Why Trinity-Mini?<\/p>\n\n\n\n Anyway, I encourage you to read The Trinity Manifesto<\/a>.<\/p>\n\n\n\n You don’t need a 600B model to break down your task list. You don’t need to burn down the rainforest to unpack your sprint.<\/p>\n\n\n\n A small model, trained well for its specific job, can nearly match a large generalist in domain expertise. I proved this with Lenina. <\/p>\n\n\n\n Lenina is my fine-tune of Trinity-Nano-Base (6B), trained on approximately 31,000 data pairs to be a publishing assistant. It learned US copyright law. How to fill a form TX. How to apply for CiP data. How to choose BISAC codes. How to create structured metadata. And it hit 68.5% semantic similarity on complex tasks when I validated it against a held-out set of 1,543 data pairs. To put that in perspective, it performed within 2.5 percentage points of a 399B model even though it has 1\/66th the parameters.<\/p>\n\n\n\n The 399B model runs in a data center. Lenina runs on my desktop PC<\/em>.<\/p>\n\n\n\n Why does that matter for Tailor?<\/p>\n\n\n\n This isn’t just about efficiency. It’s about empowering the app with AI that I don’t lose sleep over.<\/p>\n\n\n\n What’s going to make Tailor special<\/em> is the model I’m training right now.<\/p>\n\n\n\n The Tailor model I’m training will know ADHD, not as a label, but as a lived reality. It will have behavioral training specifically designed to:<\/p>\n\n\n\n Not a generic productivity bot. A focus companion that understands how a brain with ADHD works.<\/p>\n\n\n\n The productivity apps I’ve tried that market themselves as “ADHD friendly,” frankly, are not. They’re generic productivity apps. The assumption is that if<\/em> it’s a productivity app then it must<\/em> be for people with ADHD (because we don’t focus well). That’s not what Tailor is. Tailor\u2014the app and the model\u2014is built from the ground up to meet the challenges that adults with ADHD really have.<\/p>\n\n\n\n I’m not an ML engineer. Or any kind of engineer. I’m a writer, editor, and publishing professional who taught myself fine-tuning because existing models, however big they get, do a handful of things that make them utterly impossible for me to use.<\/p>\n\n\n\n (Oh, and rest is not “earned.” Rest is a human right. But go on.)<\/p>\n\n\n\n So, like I said, not an ML engineer. But I’ve done this before. Lenina wasn’t just a proof of concept. It was an evaluated, documented success. I know how to:<\/p>\n\n\n\n Tailor is the same bet, just in a different domain.<\/p>\n\n\n\n Trinity-Mini-Base will take Tailor to beta. The custom model, when it’s ready, will take Tailor to the next level. I expect that when beta begins, you’ll see a productivity app, a focus companion, that works well and has some novel features (the intention \u2192 sprint \u2192 unpack core loop). But when we make the switch to the custom Tailor model, you’ll see the app come to life (in a good way, not in a creepy Frankenstein way).<\/p>\n\n\n\n I’m working on the training data now. I’ll share progress as I go: what’s working, what’s failing, what’s taking longer than expected, and so on.<\/p>\n\n\n\n If you’ve ever wished a productivity tool actually understood how your brain works, that’s what I’m working on.<\/p>\n\n\n\n Beta signups are open<\/a>.<\/p>\n\n\n\n \u2014Catherine<\/p>\n\n\n\n <\/p>\n","protected":false},"excerpt":{"rendered":" (or, a funny thing happened on the way to the data center) When the Tailor beta launches, the app will use a small model from Arcee AI called Trinity-Mini-Base, a 26B model with a mixture-of-experts layer that helps it work efficiently even at its small size. Why Trinity-Mini? Anyway, I encourage you to read The … Read more<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-19","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/tailorfocus.com\/blog\/wp-json\/wp\/v2\/posts\/19","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/tailorfocus.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/tailorfocus.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/tailorfocus.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/tailorfocus.com\/blog\/wp-json\/wp\/v2\/comments?post=19"}],"version-history":[{"count":5,"href":"https:\/\/tailorfocus.com\/blog\/wp-json\/wp\/v2\/posts\/19\/revisions"}],"predecessor-version":[{"id":24,"href":"https:\/\/tailorfocus.com\/blog\/wp-json\/wp\/v2\/posts\/19\/revisions\/24"}],"wp:attachment":[{"href":"https:\/\/tailorfocus.com\/blog\/wp-json\/wp\/v2\/media?parent=19"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/tailorfocus.com\/blog\/wp-json\/wp\/v2\/categories?post=19"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/tailorfocus.com\/blog\/wp-json\/wp\/v2\/tags?post=19"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}\n
Core AI philosophy: Small models for small jobs<\/h2>\n\n\n\n
\n
The tailor-made version for the app <\/h2>\n\n\n\n
\n
Why I’m the right person for this<\/h2>\n\n\n\n
\n
\n
\n
What’s next<\/h2>\n\n\n\n