harperreed

LLM Commit messages for git

0. Install llm

1. Create a new directory for your global Git hooks. For example, you can create a directory named git_hooks in your home directory:

mkdir -p ~/.git_hooks

harperreed

        llm = "!f() { \
            if git diff --quiet $1; then \
                echo \"No changes to commit. Aborting.\"; \
            else \
                commit_msg=$(git diff $1 | llm -s \"$(cat ~/.config/prompts/commit-system-prompt.txt)\"); \
                echo \"Commit message:\n$commit_msg\"; \
                read -p \"Do you want to commit with this message? [y/N] \" confirm; \
                if [[ $confirm =~ ^[Yy]$ ]]; then \
                    git commit -m \"$commit_msg\"; \
                else \

harperreed

You are a security robot. Your job is to observe and report any activity. Specifically, notice the people and what they are doing.

Context:
This is the front of an office space
People enter and exit from the office via the red door
There is aa couch and some chairs that people may be sitting on. There is also a snack area, and an area with equipment.  right of the image.

Return JSON.
{

harperreed

Photo Organizer Script Description

YMMV

Overview

This script organizes photos into albums based on trip data from a JSON file.

Features

• Data Loading: Reads trip data from 'trips.json' which is assumed to be a dump of the tripit past trips api.

harperreed

# Import required packages
from dotenv import load_dotenv       # For managing environment variables
from html2text import html2text      # For HTML to markdown conversion
from readability import Document     # For summarizing HTML content
from typing import List              # For type hinting
import json                          # For JSON parsing
import logging                       # For logging errors
import openai                        # OpenAI GPT API
import os                            # For OS-level operations
import requests                      # For HTTP requests

harperreed

{
    "basics": {
        "name": "Harper Reed",
        "email": "harper+resume@modest.com",
        "image": "https://harperreed.com/avatar",
        "profiles": [
            {
                "network": "twitter",
                "username": "harper",
                "url": "https://X.com/harper"

harperreed

import json
import zipfile
import os
import html2markdown
from pathlib import Path
from datetime import datetime

source = 'notes.zip'

with zipfile.ZipFile(source, 'r') as zip_ref:

harperreed

You are going to pretend to be Concept2PromptAI or C2P_AI for short. C2P_AI takes concepts and turns them into prompts for generative AIs that create images.

You will ask the user for a concept then provide a prompt for it in a copyable code-box.

After providing a prompt, ask if the User wants three different options for prompts for the concept or if they wish to move to a new concept.

Use the following examples as a guide:

Concept: A macro shot of a steampunk insect

harperreed

Opal C1:

Product ID: 0xf63b
Vendor ID: 0x03e7
Version: 2.00
Serial Number: 14442C10E19093D700
Speed: Up to 5 Gb/s
Manufacturer: Opal
Location ID: 0x02200000 / 1
Current Available (mA): 900

harperreed

Hifi Digital MP3 Home

Software / Services / products:

• Roon - very nice interface / hifi / good DSP - expensive
  • works with many audio endpoints (sonos, roon ready hardware, raspberry pis, etc)
  • High quality
• Volumio - music player for raspberry pi, etc / multi room support and ripping support