Jimmy Briggs jimbrig

Comprehensive Guide to Review and Optimize Windows Registry on Windows 11 with AI Support

This guide provides a comprehensive PowerShell script that allows you to backup, restore, analyze, and optimize your Windows Registry. Additionally, it integrates the OpenAI GPT-4 API to provide AI-powered analysis of your registry settings.

Meta Prompting

In the Generative AI Age your ability to generate prompts is your ability to generate results.

Guide

Claude 3.5 Sonnet and o1 series models are recommended for meta prompting.

Replace {{user-input}} with your own input to generate prompts.

Use mp_*.txt as example user-inputs to see how to generate high quality prompts.

Four Level framework for prompt engineering

Watch the breakdown here in a Q4 2024 prompt engineering update video

LLM library

Ollama

Level 1: Ad hoc prompt

Quick, natural language prompts for rapid prototyping
Perfect for exploring model capabilities and behaviors

	options(shiny.maxRequestSize = 5 * 1024^2) # Limit uploads to 5 MB

	library(shiny)
	library(magick)
	library(base64enc)
	library(bslib)

	# Helper function to sanitize file names
	safeFileName <- function(filename) {
	gsub("[^a-zA-Z0-9_.-]", "_", filename)

	# This is a sample R Shiny app chatbot that runs local models with an Ollama server.
	# You also need Ollama installed and a ollama server running, plus at least one local model pulled.
	# I hard-coded a few local models,
	# If you use this, you'll want to hard code yours (including descriptions, or take those out)

	# Coded with lots of LLM help + Posit's Shiny Assistant.

	library(shiny)
	library(shinychat)
	library(bslib)

	library(elmer)
	library(tidyverse)
	library(DiagrammeR)
	library(glue)

	code <- "starwars %>%
	group_by(species) %>%
	summarise(
	n = n(),
	mass = mean(mass, na.rm = TRUE)

	library(shiny)
	library(reactable)
	library(dplyr)

	ui <- fluidPage(
	actionButton(inputId = "edit",
	label = "Edit"),
	reactableOutput("table")
	)

	library(shiny)

	reactiveTrigger <- function() {
	counter <- reactiveVal( 0)
	list(
	depend = function() {
	counter()
	invisible()
	},
	trigger = function() {

	$inputString = "Password123"

	$sha256 = [System.Security.Cryptography.SHA256]::Create()
	$bytes = [System.Text.Encoding]::UTF8.GetBytes($inputString)
	$hashBytes = $sha256.ComputeHash($bytes)

	$base64String = [System.Convert]::ToBase64String($hashBytes)

	$binaryString = [System.Text.StringBuilder]::new()
	foreach ($byte in $hashBytes) {