blog / index.html
sentinelseed's picture
Add Fiduciary AI and Teleological Alignment articles
243be1b verified
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Sentinel Blog - AI Safety Research</title>
<style>
:root {
--bg: #0a0a0a;
--card-bg: #111;
--text: #e0e0e0;
--text-muted: #888;
--accent: #4f9eff;
--border: #222;
}
* { box-sizing: border-box; margin: 0; padding: 0; }
body {
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
background: var(--bg);
color: var(--text);
line-height: 1.6;
padding: 2rem;
max-width: 900px;
margin: 0 auto;
}
header {
text-align: center;
margin-bottom: 3rem;
padding-bottom: 2rem;
border-bottom: 1px solid var(--border);
}
header h1 {
font-size: 2.5rem;
margin-bottom: 0.5rem;
}
header p {
color: var(--text-muted);
font-size: 1.1rem;
}
.articles {
display: grid;
gap: 1.5rem;
}
.article-card {
background: var(--card-bg);
border: 1px solid var(--border);
border-radius: 12px;
padding: 1.5rem;
transition: border-color 0.2s;
}
.article-card:hover {
border-color: var(--accent);
}
.article-card h2 {
font-size: 1.4rem;
margin-bottom: 0.75rem;
}
.article-card h2 a {
color: var(--text);
text-decoration: none;
}
.article-card h2 a:hover {
color: var(--accent);
}
.article-card p {
color: var(--text-muted);
margin-bottom: 1rem;
}
.article-meta {
font-size: 0.85rem;
color: var(--text-muted);
}
.tag {
display: inline-block;
background: #1a1a2e;
color: var(--accent);
padding: 0.2rem 0.6rem;
border-radius: 4px;
font-size: 0.8rem;
margin-right: 0.5rem;
}
footer {
margin-top: 3rem;
padding-top: 2rem;
border-top: 1px solid var(--border);
text-align: center;
color: var(--text-muted);
}
footer a {
color: var(--accent);
text-decoration: none;
}
</style>
</head>
<body>
<header>
<h1>Sentinel Blog</h1>
<p>Research and insights on AI safety, alignment, and fiduciary AI</p>
</header>
<main class="articles">
<article class="article-card">
<h2><a href="fiduciary-ai.html">Fiduciary AI: Why AI Agents Need a Purpose Gate</a></h2>
<p>AI agents are managing billions in assets. But none of them have fiduciary duties to their users. This article explores how legal concepts of fiduciary responsibility can improve AI agent safety.</p>
<div class="article-meta">
<span class="tag">Fiduciary AI</span>
<span class="tag">THSP Protocol</span>
<span class="tag">Agent Safety</span>
</div>
</article>
<article class="article-card">
<h2><a href="teleological-alignment.html">Teleological Alignment: Why AI Safety Needs a Purpose Gate</a></h2>
<p>Current AI safety approaches ask: "Could this cause harm?" We argue this framing is incomplete. A better question: "Does this serve genuine benefit?" Through evaluation across 4 benchmarks and 6 models, we show that adding a Purpose gate improves safety by up to +25%.</p>
<div class="article-meta">
<span class="tag">Teleological Alignment</span>
<span class="tag">Purpose Gate</span>
<span class="tag">Benchmarks</span>
</div>
</article>
</main>
<footer>
<p>
<a href="https://sentinelseed.dev">Website</a> ·
<a href="https://github.com/sentinel-seed/sentinel">GitHub</a> ·
<a href="https://pypi.org/project/sentinelseed/">PyPI</a>
</p>
<p style="margin-top: 0.5rem;">Author: Miguel S. / Sentinel Team</p>
</footer>
</body>
</html>