Files
skills/public/hip-0002.html
zeekayandHanzo Dev 9e10c1c10e Each llms index points at the other two
hanzoskills.com/llms.txt now opens with the install line, the API
reference index and the company index, so an agent that lands on any
one of the three can find the rest.

robots.txt claimed 537 documents while llms.txt counts 920. The number
is gone from robots.txt; llms.txt derives it.

public/ is regenerated from scripts/site.py, which it had fallen
behind: the copy-prompt menu and agent bar were in the generator and
not in the committed pages. tests/site.mjs passes against the result.

Co-authored-by: Hanzo Dev <[email protected]>
2026-09-11 00:27:59 -07:00

320 lines
20 KiB
HTML

<!doctype html>
<html lang="en"><head>
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
<title>hip-0002</title>
<meta name="color-scheme" content="dark">
<style>
/* Committed to one visual world: a dark instrument panel. No light variant —
the dot field and the hairline rules only read on black, and a naive
inversion would wash both out. Every colour is painted explicitly so the page
never borrows a host background. */
@font-face{font-family:'Zen';src:url('/fonts/Zen-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen';src:url('/fonts/Zen-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Pixel Square';src:url('/fonts/ZenPixel-Square.woff2') format('woff2');font-style:normal;font-display:swap}
:root{
--ink:#f4f4f2; --soft:#9c9c98; --faint:#6a6a66; --ground:#000; --panel:#0a0a0a;
--line:#232323; --line-hi:#3a3a3a; --accent:#f4f4f2;
--font-zen-sans:'Zen',-apple-system,BlinkMacSystemFont,"Segoe UI",Helvetica,Arial,sans-serif;
--font-zen-mono:'Zen Mono',ui-monospace,"SF Mono",SFMono-Regular,Menlo,Consolas,monospace;
--font-zen-pixel-square:'Zen Pixel Square',monospace;
--mono:var(--font-zen-mono);
--sans:var(--font-zen-sans);
/* Controls are pills and surfaces are soft, as on hanzo.ai. */
--r:999px; --r-soft:14px;
}
*{box-sizing:border-box}
html{-webkit-text-size-adjust:100%}
body{margin:0;background:var(--ground);color:var(--ink);font-family:var(--sans);
font-size:16px;line-height:1.65;-webkit-font-smoothing:antialiased}
.wrap{max-width:60rem;margin:0 auto;padding:0 1.75rem}
/* The dot field. A halftone made of one repeating radial-gradient, faded out
along the diagonal by a mask so it reads as a wave rather than wallpaper. */
/* No overflow clip here: the dot field is inset to the box already, and a clip
would cut off the copy-prompt menu. */
.hero{position:relative;border-bottom:1px solid var(--line)}
.hero::before{content:"";position:absolute;inset:0;
background-image:radial-gradient(var(--line-hi) 1px, transparent 1px);
background-size:7px 7px;
-webkit-mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
pointer-events:none}
.hero .wrap{position:relative;padding-top:5.5rem;padding-bottom:4rem}
nav{border-bottom:1px solid var(--line)}
nav .in{max-width:60rem;margin:0 auto;padding:1.1rem 1.75rem;display:flex;
justify-content:space-between;align-items:center;gap:1rem}
.brand{font-family:var(--mono);font-size:.85rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--ink);text-decoration:none;
display:inline-flex;align-items:center;gap:.6rem}
.brand i{font-style:normal;color:var(--faint)}
.mark{width:1.15em;height:1.15em;display:block;flex:0 0 auto}
nav a.up{font-family:var(--mono);font-size:.72rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--soft);text-decoration:none}
nav a.up:hover{color:var(--ink)}
h1{font-family:var(--mono);font-size:clamp(2rem,5.4vw,3.4rem);line-height:1.12;
letter-spacing:-.02em;margin:0 0 1.1rem;font-weight:500;text-wrap:balance}
h1 em{font-style:normal;color:var(--faint)}
.lede{color:var(--soft);font-size:1.05rem;max-width:52ch;margin:0 0 2.25rem}
.btns{display:flex;flex-wrap:wrap;gap:.7rem;margin:0 0 .5rem;align-items:center}
.btn{display:inline-flex;align-items:center;gap:.5rem;font-family:var(--mono);
font-size:.72rem;letter-spacing:.14em;text-transform:uppercase;
padding:.8rem 1.4rem;border:1px solid var(--line-hi);border-radius:var(--r);
color:var(--ink);text-decoration:none;background:transparent;cursor:pointer;
line-height:1.2;font-weight:400}
.btn:hover{background:#141414;text-decoration:none;border-color:var(--soft)}
.btn.solid{background:var(--ink);color:#000;border-color:var(--ink)}
.btn.solid:hover{background:#d8d8d4}
.btn .chev{width:.7em;height:.7em;flex:0 0 auto;transition:transform .15s ease}
.btn[aria-expanded="true"] .chev{transform:rotate(180deg)}
/* Copy-prompt selector. Each row copies the prompt for its own target. */
.copy{position:relative;display:inline-flex}
.menu{position:absolute;top:calc(100% + .5rem);left:0;z-index:20;min-width:21rem;
background:var(--panel);border:1px solid var(--line-hi);border-radius:var(--r-soft);
padding:.4rem;display:flex;flex-direction:column;
box-shadow:0 12px 32px rgba(0,0,0,.75)}
.menu[hidden]{display:none}
.mi{display:flex;align-items:center;gap:.7rem;width:100%;text-align:left;
padding:.62rem .8rem;border:0;border-radius:calc(var(--r-soft) - .35rem);
background:transparent;color:var(--ink);font-family:var(--mono);font-size:.76rem;
letter-spacing:.04em;text-decoration:none;cursor:pointer;line-height:1.3;
white-space:nowrap}
.mi:hover,.mi:focus-visible{background:#181818;outline:none}
.mi .mark{width:1.05rem;height:1.05rem;color:var(--soft)}
.mi:hover .mark{color:var(--ink)}
.mi u{margin-left:auto;color:var(--faint);text-decoration:none;font-size:.68rem;
letter-spacing:.1em;text-transform:uppercase}
/* Works-with bar: one scrolling row, name and mark per agent. */
.strip{border-bottom:1px solid var(--line);background:var(--panel)}
.strip .in{max-width:60rem;margin:0 auto;padding:.9rem 1.75rem;display:flex;
align-items:center;gap:1.25rem;font-family:var(--mono);font-size:.72rem;
letter-spacing:.1em;text-transform:uppercase;color:var(--faint)}
.strip b{color:var(--soft);font-weight:400;flex:0 0 auto;
border-right:1px solid var(--line);padding-right:1.25rem;align-self:stretch;
display:flex;align-items:center}
.bar{display:flex;align-items:center;gap:.5rem;flex:1 1 auto;min-width:0;
overflow-x:auto;scrollbar-width:none;scroll-snap-type:x proximity;
-webkit-overflow-scrolling:touch;
-webkit-mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent);
mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent)}
.bar::-webkit-scrollbar{display:none}
.agent{display:inline-flex;align-items:center;gap:.45rem;flex:0 0 auto;
padding:.4rem .85rem;border:1px solid var(--line);border-radius:var(--r);
color:var(--soft);white-space:nowrap;scroll-snap-align:start;
text-decoration:none;background:var(--ground)}
.agent:hover{color:var(--ink);border-color:var(--line-hi);text-decoration:none}
.agent .mark{width:.95rem;height:.95rem}
h2{font-family:var(--mono);font-size:1.1rem;letter-spacing:-.01em;margin:2.75rem 0 .75rem;font-weight:500}
h3{font-size:1rem;margin:2rem 0 .5rem;font-weight:600}
h4,h5,h6{font-size:.94rem;margin:1.5rem 0 .5rem;font-weight:600}
p{margin:0 0 1rem;max-width:70ch}
ul,ol{margin:0 0 1rem;padding-left:1.35rem;max-width:70ch}
li{margin:.22rem 0}
a{color:var(--ink);text-decoration:underline;text-underline-offset:3px;
text-decoration-color:var(--line-hi)}
a:hover{text-decoration-color:var(--ink)}
a:focus-visible{outline:1px solid var(--ink);outline-offset:3px}
code{font-family:var(--mono);font-size:.85em;background:var(--panel);
border:1px solid var(--line);border-radius:5px;padding:.1em .36em}
pre{background:var(--panel);border:1px solid var(--line);padding:1rem 1.1rem;
border-radius:var(--r-soft);overflow-x:auto;margin:0 0 1.25rem}
pre code{background:none;border:0;padding:0;font-size:.82rem;line-height:1.7}
blockquote{margin:0 0 1rem;padding-left:1rem;border-left:1px solid var(--line-hi);color:var(--soft)}
hr{border:0;border-top:1px solid var(--line);margin:2.5rem 0}
table{border-collapse:collapse;width:100%;margin:0 0 1.25rem;font-size:.92rem;
display:block;overflow-x:auto}
th,td{border:1px solid var(--line);padding:.5rem .7rem;text-align:left}
.curl{display:block;background:var(--panel);border:1px solid var(--line);
border-radius:var(--r-soft);padding:.95rem 1.1rem;font-family:var(--mono);
font-size:.8rem;color:var(--soft);overflow-x:auto;margin:0 0 2.5rem;
white-space:pre;line-height:1.9}
.curl b{color:var(--ink);font-weight:400}
.curl i{font-style:normal;color:var(--faint)}
/* index */
#q{width:100%;padding:.85rem 1.2rem;font-family:var(--mono);font-size:.85rem;color:var(--ink);
background:var(--panel);border:1px solid var(--line);border-radius:var(--r);margin:0 0 .6rem}
#q::placeholder{color:var(--faint);text-transform:uppercase;letter-spacing:.1em;font-size:.72rem}
#q:focus{outline:none;border-color:var(--soft)}
#count{color:var(--faint);font-family:var(--mono);font-size:.72rem;letter-spacing:.1em;
text-transform:uppercase;margin:0 0 2rem}
.cat{margin:2.5rem 0 .5rem;font-family:var(--mono);font-size:.7rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);border-bottom:1px solid var(--line);
padding-bottom:.45rem}
.row{display:block;padding:.6rem .9rem;margin:0 -.9rem;border-bottom:1px solid var(--line);
border-radius:var(--r-soft);text-decoration:none}
.row:hover{background:#0a0a0a}
.nm{font-family:var(--mono);font-size:.84rem;color:var(--ink);display:block}
.ds{color:var(--soft);font-size:.9rem;display:block;margin-top:.12rem}
footer{margin-top:4rem;padding:2rem 0 4rem;border-top:1px solid var(--line);
color:var(--faint);font-size:.85rem}
footer a{color:var(--soft)}
.fmap{display:grid;gap:1.75rem;grid-template-columns:repeat(auto-fit,minmax(11rem,1fr));
margin:0 0 2rem;font-size:.85rem}
.fmap b{display:block;font-family:var(--mono);font-size:.68rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);font-weight:400;margin:0 0 .6rem;
border-bottom:1px solid var(--line);padding-bottom:.4rem}
.fmap a{display:inline-block;color:var(--ink);text-decoration:none;margin:.3rem .35rem 0 0}
.fmap a:hover{text-decoration:underline}
.fmap div{color:var(--faint);line-height:1.5}
.fend{border-top:1px solid var(--line);padding-top:1.25rem;font-size:.82rem}
@media (max-width:640px){
.hero .wrap{padding-top:3.25rem;padding-bottom:2.75rem}
.btns{gap:.5rem}
.btn{padding:.75rem 1.15rem;font-size:.68rem}
.copy,.copy .btn{width:100%;justify-content:center}
.menu{left:0;right:0;min-width:0}
.strip .in{flex-direction:column;align-items:flex-start;gap:.6rem;padding:.9rem 1.75rem}
.strip b{border-right:0;padding-right:0}
.bar{width:100%}
}
</style>
<link rel="alternate" type="text/markdown" href="/hip-0002.md">
<link rel="icon" href="/favicon.svg">
<link rel="canonical" href="https://hanzoskills.com/hip-0002">
</head>
<!-- Reading this with a machine? Every page here is also plain markdown.
This one: https://hanzoskills.com/hip-0002.md
Index: https://hanzoskills.com/llms.txt
Corpus: https://hanzoskills.com/all.md
Append .md to any path for the markdown twin. -->
<body>
<nav><div class="in">
<a class="brand" href="/"><svg class="mark" viewBox="0 0 67 67" fill="currentColor" aria-hidden="true"><path d="M22.21 67V44.6369H0V67H22.21Z"/><path d="M66.7038 22.3184H22.2534L0.0878906 44.6367H44.4634L66.7038 22.3184Z"/><path d="M22.21 0H0V22.3184H22.21V0Z"/><path d="M66.7198 0H44.5098V22.3184H66.7198V0Z"/><path d="M66.7198 67V44.6369H44.5098V67H66.7198Z"/></svg> HANZO<i>SKILLS</i></a>
<a class="up" href="/">All skills</a>
</div></nav>
<div class="wrap">
<h1>hip-0002</h1><p class="lede">HIP-2: Hamiltonian Large Language Models (HLLMs) Specification. Status Final. Hanzo architectural specification.</p><h1>HIP-0002: Hamiltonian Large Language Models (HLLMs) Specification</h1>
<h2>Abstract</h2>
<p>This proposal defines the architecture, capabilities, and standards for Hamiltonian Large Language Models (HLLMs). HLLMs are multimodal AI models with per-user fine-tuning, where every user owns their personalized model fork. These models support text, vision, audio, and 3D modalities with unified representations and cross-modal understanding.</p>
<h2>Specification</h2>
<h3>Model Architecture</h3>
<h4>Unified Transformer Architecture with Hamiltonian Dynamics</h4>
<pre><code class="lang-python">class HLLMArchitecture:
modalities = [&quot;text&quot;, &quot;vision&quot;, &quot;audio&quot;, &quot;3d&quot;]
hidden_dim = 4096 # Base model
num_layers = 48
num_heads = 64
context_length = 32768
# Modality-specific encoders
text_encoder: &quot;Byte-level BPE&quot;
vision_encoder: &quot;Vision Transformer patches&quot;
audio_encoder: &quot;Mel-spectrogram transformer&quot;
3d_encoder: &quot;Point cloud transformer&quot;
# Unified decoder
decoder: &quot;Autoregressive transformer&quot;</code></pre>
<h3>Model Variants</h3>
<p>| Model | Parameters | Context | Modalities | Use Case | |-------|------------|---------|------------|----------| | HLLM-7B | 7B | 8K | Text, Vision | Edge deployment, personal devices | | HLLM-32B | 32B | 32K | Text, Vision, Audio | Standard per-user models | | HLLM-175B | 175B | 128K | All | Advanced personal assistants | | HLLM-1T | 1T | 256K | All + specialized | Research &amp; collective intelligence |</p>
<p><strong>Note</strong>: These are BASE models only. Every user interaction creates a personalized fork with user-specific LoRA adapters, making each user&#x27;s model unique.</p>
<h3>Input/Output Specifications</h3>
<h4>Input Format</h4>
<pre><code class="lang-json">{
&quot;inputs&quot;: [
{
&quot;type&quot;: &quot;text&quot;,
&quot;content&quot;: &quot;Describe this image&quot;
},
{
&quot;type&quot;: &quot;image&quot;,
&quot;content&quot;: &quot;base64_encoded_image&quot;,
&quot;encoding&quot;: &quot;jpeg&quot;
},
{
&quot;type&quot;: &quot;audio&quot;,
&quot;content&quot;: &quot;base64_encoded_audio&quot;,
&quot;encoding&quot;: &quot;wav&quot;,
&quot;sample_rate&quot;: 16000
}
],
&quot;parameters&quot;: {
&quot;max_tokens&quot;: 2048,
&quot;temperature&quot;: 0.7,
&quot;modality_weights&quot;: {
&quot;text&quot;: 1.0,
&quot;vision&quot;: 1.0,
&quot;audio&quot;: 0.8
}
}
}</code></pre>
<h4>Output Format</h4>
<pre><code class="lang-json">{
&quot;outputs&quot;: [
{
&quot;type&quot;: &quot;text&quot;,
&quot;content&quot;: &quot;Generated text response&quot;
},
{
&quot;type&quot;: &quot;image&quot;,
&quot;content&quot;: &quot;base64_encoded_image&quot;,
&quot;encoding&quot;: &quot;png&quot;
}
],
&quot;metadata&quot;: {
&quot;model&quot;: &quot;HLLM-32B&quot;,
&quot;tokens_used&quot;: 1547,
&quot;latency_ms&quot;: 234,
&quot;modalities_processed&quot;: [&quot;text&quot;, &quot;vision&quot;]
}
}</code></pre>
<h3>Capabilities</h3>
<h4>Core Capabilities</h4>
<ol><li><strong>Cross-modal Understanding</strong>: Understand relationships between modalities</li><li><strong>Any-to-Any Generation</strong>: Generate any modality from any input</li><li><strong>Zero-shot Transfer</strong>: Apply learning across modalities</li><li><strong>Compositional Reasoning</strong>: Combine modalities for complex reasoning</li></ol>
<h4>Specific Tasks</h4>
<ul><li><strong>Vision-Language</strong>: Image captioning, VQA, visual reasoning</li><li><strong>Audio-Language</strong>: Speech recognition, audio description</li><li><strong>3D-Language</strong>: 3D scene understanding, spatial reasoning</li><li><strong>Multimodal Generation</strong>: Create images from text+audio, etc.</li></ul>
<h3>Training Infrastructure</h3>
<h4>Base Model Training</h4>
<ul><li><strong>Text</strong>: 10T tokens from web, books, code</li><li><strong>Images</strong>: 5B image-text pairs</li><li><strong>Audio</strong>: 100K hours of audio with transcripts</li><li><strong>3D</strong>: 10M 3D scenes with annotations</li><li><strong>Synthetic</strong>: Generated multimodal data for alignment</li></ul>
<h4>Per-User Fine-Tuning (Automatic)</h4>
<ul><li><strong>Data</strong>: User&#x27;s own interactions (encrypted)</li><li><strong>Compute</strong>: ~35ms per interaction for gradient update</li><li><strong>Storage</strong>: ~100MB per user for LoRA adapters</li><li><strong>Privacy</strong>: All training data stays encrypted with user&#x27;s key</li><li><strong>Ledger</strong>: Every training operation recorded on-chain</li></ul>
<p><strong>Key Difference</strong>: Base models are trained once. Per-user models continuously evolve with every interaction, creating billions of unique models.</p>
<h3>Inference Optimization</h3>
<h4>Techniques</h4>
<ol><li><strong>Modality Routing</strong>: Process only relevant modalities</li><li><strong>Sparse Attention</strong>: Reduce computation for long contexts</li><li><strong>Quantization</strong>: INT8/INT4 for edge deployment</li><li><strong>Caching</strong>: KV-cache across modalities</li><li><strong>Batching</strong>: Dynamic batching for different modalities</li></ol>
<h4>Performance Targets</h4>
<ul><li><strong>Latency</strong>: &lt;100ms for first token (HLLM-32B)</li><li><strong>Throughput</strong>: &gt;1000 tokens/second (batched)</li><li><strong>Memory</strong>: &lt;16GB for HLLM-7B inference</li></ul>
<h3>Safety and Alignment</h3>
<h4>Safety Measures</h4>
<ol><li><strong>Content Filtering</strong>: Multi-modal content moderation</li><li><strong>Watermarking</strong>: Invisible watermarks in generated content</li><li><strong>Attribution</strong>: Track training data influence</li><li><strong>Bias Mitigation</strong>: Cross-modal debiasing techniques</li></ol>
<h4>Alignment Techniques</h4>
<ul><li><strong>RLHF</strong>: Reinforcement Learning from Human Feedback</li><li><strong>Constitutional AI</strong>: Rule-based constraints</li><li><strong>Multimodal Alignment</strong>: Cross-modal consistency checks</li></ul>
<h3>Open Source Repositories</h3>
<ul><li><strong>Jin Multimodal Models</strong>: <a href="https://github.com/hanzoai/jin">github.com/hanzoai/jin</a> — archived 2026-05-12; the multimodal framework was not built (HIP-0003)</li><li><strong>LLM Gateway</strong>: <a href="https://github.com/hanzoai/llm">github.com/hanzoai/llm</a></li><li><strong>Agent Framework</strong>: <a href="https://github.com/hanzoai/agent">github.com/hanzoai/agent</a></li><li><strong>MCP Tools</strong>: <a href="https://github.com/hanzoai/mcp">github.com/hanzoai/mcp</a></li><li><strong>Chat Platform</strong>: <a href="https://github.com/hanzoai/chat">github.com/hanzoai/chat</a></li><li><strong>Search Engine</strong>: <a href="https://github.com/hanzoai/search">github.com/hanzoai/search</a></li></ul>
<h3>Model Checkpoints</h3>
<ul><li><strong>HLLM-7B Base</strong>: <a href="https://huggingface.co/hanzoai/hllm-7b">huggingface.co/hanzoai/hllm-7b</a></li><li><strong>HLLM-32B Base</strong>: <a href="https://huggingface.co/hanzoai/hllm-32b">huggingface.co/hanzoai/hllm-32b</a></li><li><strong>Evaluation Suite</strong>: proposed by this HIP; not yet written, so there is nothing to link to.</li></ul>
<ol><li><a href="https://arxiv.org/abs/2312.11805">Gemini: A Family of Multimodal Models</a></li><li><a href="./hip-0000-hanzo-ai-architecture-framework.md">HIP-0000: Hanzo AI Architecture &amp; Framework</a></li><li><a href="./hip-0005-post-quantum-security-for-ai-infrastructure.md">HIP-0005: Post-Quantum Security for AI Infrastructure</a></li></ol>
<h2>Copyright</h2>
<p>Copyright and related rights waived via <a href="https://creativecommons.org/publicdomain/zero/1.0/">CC0</a>.</p>
<footer>
<div class="fmap">
<div><b>Build</b>
<a href="https://hanzo.app">hanzo.app</a> app builder
<a href="https://hanzo.codes">hanzo.codes</a> code with an agent
<a href="https://hanzoskills.com">hanzoskills.com</a> what an agent reads</div>
<div><b>Run</b>
<a href="https://console.hanzo.ai">console.hanzo.ai</a> cloud console
<a href="https://api.hanzo.ai">api.hanzo.ai</a> the API</div>
<div><b>Account</b>
<a href="https://hanzo.id">hanzo.id</a> sign in
<a href="https://pay.hanzo.ai">pay.hanzo.ai</a> top up
<a href="https://billing.hanzo.ai">billing.hanzo.ai</a> invoices and usage</div>
<div><b>Company</b>
<a href="https://hanzo.ai">hanzo.ai</a> canonical
<a href="https://hanzo.ventures">hanzo.ventures</a> ventures</div>
</div>
<div class="fend"><a href="/hip-0002.md">This page as plain text</a> · <a href="/llms.txt">Index for agents</a></div>
</footer>
</div></body></html>