Stefan Taranu alertor

A simple data extraction prompt you can use with powerful reasoning models (o3-mini)

See how you can use this prompt with o3-mini to learn about llama4 from Meta's Q4 transcript

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

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.

	[
	{
	"url": "http://money.cnn.com",
	"rss": "http://rss.cnn.com/rss/money_topstories.rss"
	},
	{
	"url": "http://thehill.com",
	"rss": "http://thehill.com/rss/syndicator/19110"
	},
	{

	import paho.mqtt.client as paho
	import os
	import socket
	import ssl
	from time import sleep
	from random import uniform
	import json

	import logging
	logging.basicConfig(level=logging.INFO)

	from flask import Flask, current_app
	from blinker import Namespace

	app = Flask(__name__)
	app.secret_key = 'WOO'

	my_signals = Namespace()


	def moo_signal(app, message, **extra):

	<VirtualHost _default_:443>
	ServerName yourhost
	ServerAdmin [email protected]

	SSLEngine on
	SSLCertificateFile /etc/ssl/private/yourorg.com.crt
	SSLCertificateKeyFile /etc/ssl/private/yourorg.com.key
	SSLCertificateChainFile /etc/ssl/private/chain.pem

	SSLProxyEngine On

	# This gist shows how to integrate Flask into a
	# custom Gunicorn-WSGI application described
	# here: http://docs.gunicorn.org/en/stable/custom.html

	from __future__ import unicode_literals

	import multiprocessing

	import gunicorn.app.base

	import os

	import falcon
	import jinja2


	def load_template(name):
	path = os.path.join('templates', name)
	with open(os.path.abspath(path), 'r') as fp:
	return jinja2.Template(fp.read())