Skip to content

Instantly share code, notes, and snippets.

@louspringer
louspringer / jobs_shadow_math.ipynb
Last active November 22, 2025 00:45
Jobs Leadership Shadow Engine – Attractor & Bifurcation Math (Notebook)
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@louspringer
louspringer / jobs_shadow_math.html
Created November 22, 2025 00:51
Jobs Leadership Shadow Engine – Attractor & Bifurcation Math (HTML with MathJax)
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Jobs Leadership Shadow Engine – Attractor & Bifurcation Math</title>
<link rel="preconnect" href="https://cdn.jsdelivr.net">
<script>
window.MathJax = {
tex: { inlineMath: [['$', '$'], ['\\(', '\\)']], displayMath: [['$$','$$'], ['\\[','\\]']] },
Sarson ka saag and makki di roti (sometimes written as “sarso ka saag and corn roti”) is a famous Punjabi dish from North India.
──────────
*:herb: *Sarson ka saag**
• “Sarson” means mustard greens (the leaves of the mustard plant).
• “Saag” means greens in general.
• It’s a slow-cooked puree of mustard greens, often mixed with spinach or other greens, simmered with onions, garlic, ginger, and spices until thick and creamy.
• Traditionally it’s finished with a dollop of ghee (clarified butter).
@louspringer
louspringer / decision-density.md
Created December 5, 2025 12:36
High percentage decision attributes.

Let’s distill and formalize these two statements into clean, interoperable decision-theory primitives you can drop directly into your Fort / Beast stack. I’m keeping it straight, skeptical, and crisp—no hand-waving.


1. The Core Claims (Normalized)

Claim A — Decision Density → Solution Correctness

A solution whose architecture is derived from a high percentage of requirements-driven decisions (≈90%) has a materially higher probability of correctness than a solution derived from a sparse requirement base (≈20%).

@louspringer
louspringer / captain-command-palette.md
Last active February 24, 2026 04:24
AI agent command palette: engage, make it so, belay that

Captain Command Palette (AI Agent Command Lexicon)

Purpose: A concise, machine-readable command vocabulary for LLM operators and autonomous agents.

SEO / Discovery

  • Keywords: ai agent commands, llm operator commands, captain command palette, engage, make it so, belay that, automation command lexicon, human-in-the-loop
  • Canonical intent: fast, unambiguous run-control phrases for tool-driven workflows.

Command Map (Human)

  • engage -> run now
@louspringer
louspringer / walled-gardens-meme-pack.md
Created February 24, 2026 04:31
Walled gardens are doomed: meme discovery pack (3-panel scripts + prompts)

Walled Gardens Are Doomed: Meme Discovery Pack

Use this pack for rapid social discovery tests around platform lock-in, API-first agents, and attention economics.

Core Thesis

  • Clicks-for-dollars optimized for ad extraction.
  • Walled gardens block composability.
  • User-owned, API-native agents route around walls.

3-Panel Meme Script (Primary)

@louspringer
louspringer / aftermath_anchor.svg
Last active February 24, 2026 07:57
Reading depth vs shallow processing addendum + hashtags
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@louspringer
louspringer / make-lou-admin.cmd
Last active March 6, 2026 22:00
Create local admin user lou on Windows
net user lou "TempStrongPass123!" /add /y
net localgroup Administrators lou /add
net user lou
pause

You ran a single-shot throughput probe against a 120B model endpoint. Let’s decode it cleanly, then define what “good / better / best” actually means in this context.


What you actually measured (no fluff)

  • Prompt tokens: 33 → trivial input, not the bottleneck
  • Completion tokens: 256 → fixed-size output sample
  • Wall time: 14.78 s → end-to-end latency (includes overhead)
  • Throughput: 17.33 tokens/secsteady-state generation speed