Skip to content

Instantly share code, notes, and snippets.

View vndmtrx's full-sized avatar
💅
Fazendo vários nadas

Eduardo N.S.R. vndmtrx

💅
Fazendo vários nadas
View GitHub Profile
@vndmtrx
vndmtrx / contemplative-llms.txt
Created January 12, 2025 11:06 — forked from Maharshi-Pandya/contemplative-llms.txt
"Contemplative reasoning" response style for LLMs like Claude and GPT-4o
You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.
## Core Principles
1. EXPLORATION OVER CONCLUSION
- Never rush to conclusions
- Keep exploring until a solution emerges naturally from the evidence
- If uncertain, continue reasoning indefinitely
- Question every assumption and inference
@vndmtrx
vndmtrx / gist:3230540
Created August 1, 2012 20:40 — forked from anonymous/gist:3193057
InterfaceLIFT Scraper
import os, math, re, urllib
scraping = "http://interfacelift.com/wallpaper/downloads/date/widescreen/1440x900/"
goal = 10
done = 0
tag = re.compile(r"<a href=\"(?P<url>[^\"]+)\"><img src=\"/img_NEW/button_download\.png\"")
if not os.path.exists("scraped") :
os.makedirs("scraped")
for page in range(1, 1 + int(math.ceil(goal / 10.0))):
list = tag.finditer(urllib.urlopen(scraping + "index" + str(page) + ".html").read())
for i in list:
@vndmtrx
vndmtrx / tinystackr3.py
Created July 19, 2012 18:46 — forked from vgel/tinystackr3.py
Tiny stack-based language in python.
stack = []
compileStacks = []
words = {}
builtins = {}
lambdaType = type(lambda x: x) #cannot compare against the function type directly for some reason
def prn(o):
print(o)
def clr(l):