<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<title>Wisdom | Kris Yotam</title>
<link rel="stylesheet" href="../../c/site.css">
<meta name="description" content="notes, plans, and ideas for my personal ai assistant">
<meta name="viewport" content="width=device-width, initial-scale=1">
</head>
<body>
<div class="mode-container">
<input type="radio" name="theme" id="theme-auto" checked>
<label for="theme-auto" class="auto" title="Auto theme"></label>
<input type="radio" name="theme" id="theme-light">
<label for="theme-light" class="light" title="Light theme"></label>
<input type="radio" name="theme" id="theme-dark">
<label for="theme-dark" class="dark" title="Dark theme"></label>
</div>
<div class="top-bar" role="navigation">
<a href="../../index.html" title="Main page"><img src="../../c/sigma.svg" alt="Main page"></a>
<a href="../../about.html" title="About"><img src="../../c/news.svg" alt="About"></a>
<a href="#" title="Code"><img src="../../c/code.svg" alt="Code"></a>
<a href="../../pics.html" title="Photography"><img src="../../c/camera.svg" alt="Photography"></a>
<a href="#" title="Pictures"><img src="../../c/picture.svg" alt="Pictures"></a>
<a href="../../vids.html" title="Videos"><img src="../../c/video.svg" alt="Videos"></a>
<a href="#" title="Donations"><img src="../../c/beer.svg" alt="Donations"></a>
<a href="#" title="Social"><img src="../../c/elephant.svg" alt="Social"></a>
</div>
<h1>Wisdom</h1>
<div class="keepws">
(<span class="bold">notes</span>
(date 2025-06-19)
(category <a href="../../notes.html">technology</a>)
(status <span class="status-growing">growing</span>)
(confidence certain)
(importance 9)
(tags wisdom reflection quotes))
</div>
<p class="preview">notes, plans, and ideas for my personal ai assistant</p>
<div class="prose">
<p>This project is currently inactive and is slated to begin development in January 2026. Check back for updates on progress and availability.</p>
<p>Since most of you are unaware of the background of Wisdom. I started building her first version in 2023 closed source. A relatively
simple ai assistant that had some simple features. Web Search, Weather Forecast, and a few other things. The project was built in c, and
utilized a Multinomial Naive Bayes Classifier for intent recognition.</p>
<p>Here is some helpful information as to the model weights, source code for the program, web console, and tool scripts that wisdom uses.</p>
<h2>Thoughts on pseudo-sentience in LLMs</h2>
<h2>Toward a High Level Future</h2>
<p>I am much of the opinion that our future will be less about how well we can do any one thing, but on how well we can
get ai tooling to accomplish this for us. There is quite a lot of discourse around the topic. I don't think that makes it any less the favorable outcome. It is my
recommendation that everyone should learn to think "High Level". When it comes to passion do what you what. It is in fact much better for the retention of skills to
continue to use products that demand more of you. Opt for the Non-AI IDE, Write without the assitance of an ai for your first draft. Doing these thing's the hard way.
Is inevitably the better way to retain skills one is passionate about. However one can not be passionate about everything, and there is a lot of menial work to be done
in the modern age. So why not leverage the 100X Dev, 100X Writer, and 100X Teacher at your fingertips? All you need to do is learn to become a Architect. What I mean by this
is to become a person who can create clear, efficient, proven, and data-driven plans and let your AI Agents do all the ground work. This is no where near as simple, or boring as
it may sound. To become a good architect at anything one must know a great deal about that thing. You are essentialy creating a "Style Guide". A guide that consists of hundreds of hours
of knowledge, wisdom, and refinement of ideas to get the best possible outcome in the simplest amount of time.</p>
<h2>On Privacy in LLMs</h2>
<h2>On Security in LLMs</h2>
<h2>On the Integration with External Tools</h2>
<h2>Voice Interaction</h2>
<h3>TTS (Text-to-Speech)</h3>
<ul>
<li>Leaning towards Tortoise TTS, realistic and expressive.</li>
</ul>
<h3>STT (Speech-to-Text)</h3>
<ul>
<li>Locked down on OpenAI's Whisper</li>
</ul>
<h2>Finetuning DeepSeek for My Usecases</h2>
<h2>On Multimodality</h2>
<h2>Deep Research</h2>
<h2>Big Sister (Lifelogging Protocol)</h2>
<h2>Operator Agent</h2>
<h2>Asynchronous Coding Agent</h2>
<h2>Tool Calls</h2>
<h3>Image Generation via SDXL (Stable Diffusion XL)</h3>
<h3>Web Crawling</h3>
<h2>Experimental Features</h2>
<h3>Autonomous Asynchronous Finetuning</h3>
</div>
</body>
</html>