disler

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.

thomasantony

# Save the transcripts using the "Save Page WE" Chrome Extension
# This script was generated by ChatGPT
import sys
from bs4 import BeautifulSoup

# Check if a file was provided as a command line argument
if len(sys.argv) < 2:
    print("Please provide an HTML file as a command line argument.")
    sys.exit(1)

asilbalaban

import keyboard
import time
import random

prompt = str(input('Bir kavram girin: '))


if prompt == '':
    prompt = "reglan arm cycling jersey design in bright green, yellow, blue, red, grey, white, black, purple, vivid colors, sharp, realistic, ultra detailed, 8k"
    prompt = "cycling jersey design in pastel colors, sharp, realistic, ultra detailed, 8k"

lg

#!/bin/bash
#
# CloudyGamerLauncher by Larry Gadea
# Easily start/stop Paperspace and Parsec instances
#
# Make sure to fill out the variables below. For the machine id, use the
# 8-letter identifier for the machine on Paperspace (ex. PS8RGDUY)
#
# Note: Requires Paperspace API key (generate one in account settings)

CapCap

#!/bin/bash


# Don't require you to constantly enter password for sudo:
sudo visudo
# In the bottom of the file, paste the following (without the `#`):
# paperspace ALL=(ALL) NOPASSWD: ALL
# Then press `ctl+o` then `enter` to save your changes, and `ctr+x` to exit nano

# Allow connection from your IP to any port- default seems to be just 22 (ssh)

karpathy

"""
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
BSD License
"""
import numpy as np

# data I/O
data = open('input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)

makkes

var wrtc = require('wrtc');

var pcs = [],
    done = [],
    MAX_PCS = 30;

pcoptions = {
    iceServers: []
};

ceejbot

Go here for the latest + some code.

numbat

An alerting engine for a metrics & monitoring system.

This is the same approach I wanted in my initial spike, only instead of writing a custom collector & using an existing alerting engine (riemann), I'm proposing using an existing collector (hekad) and writing the alerting engine.

The system

deandob

    // Live video stream management for HTML5 video. Uses FFMPEG to connect to H.264 camera stream, 
    // Camera stream is remuxed to a MP4 stream for HTML5 video compatibility and segments are recorded for later playback
var liveStream = function (req, resp) {                                            // handle each client request by instantiating a new FFMPEG instance
    // For live streaming, create a fragmented MP4 file with empty moov (no seeking possible).

    var reqUrl = url.parse(req.url, true)
    var cameraName = typeof reqUrl.pathname === "string" ? reqUrl.pathname.substring(1) : undefined;
    if (cameraName) {
        try {
            cameraName = decodeURIComponent(cameraName);

scottdw

(ns scottdw.plot.demo
  (:import [java.util Random]
           [org.jzy3d.analysis AnalysisLauncher AbstractAnalysis]
           [org.jzy3d.chart Chart]
           [org.jzy3d.chart.factories AWTChartComponentFactory]
           [org.jzy3d.colors Color ColorMapper]
           [org.jzy3d.colors.colormaps ColorMapRainbow]
           [org.jzy3d.maths Coord3d Range]
           [org.jzy3d.plot3d.builder Builder Mapper]
           [org.jzy3d.plot3d.builder.concrete OrthonormalGrid]