Skip to content

Instantly share code, notes, and snippets.

@Sambosis
Sambosis / contemplative-llms.txt
Created January 11, 2025 06:36 — 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
@Sambosis
Sambosis / crypto-gsheet-populator.py
Created May 31, 2024 02:49 — forked from rhettre/crypto-gsheet-populator.py
I built this script to populate trades made in any trading pair available on Coinbase Pro or Gemini into a Google Sheet so it would be easier to track trades, profitability, and cost basis. This could be extended to other exchanges. See https://www.youtube.com/watch?v=hutDJ-FVatw for full explanation.
import json
import gspread
import time
import sys
import base64
import hashlib
import hmac
import urllib.request
import requests
from datetime import datetime, timezone
import os
import argparse
import requests
import replicate
PROJECT_NAME = "photomash"
def interpolate():
model = replicate.models.get("google-research/frame-interpolation")
version = model.versions.get(
@Sambosis
Sambosis / 1 - Intro---README.md
Created October 1, 2023 02:16 — forked from lostintangent/1 - Intro---README.md
Learning MobX (Side-Effects)

1: Intro

Welcome to the interactive tutorial on how to use side-effect "operators" in MobX! Over the course of the next three samples, you'll learn (and be able to explore) exactly how autorun, when and reaction work, and when/why you would use them when building reactive applications.

@Sambosis
Sambosis / chat.py
Created June 7, 2023 01:54 — forked from Kotrotsos/chat.py
Simple chatGPT clone.
import openai
import sys
openai.api_key = "add your key here" #should be an environment variable, but this will do for now
def call_gpt4_api(prompt, messages):
data = {
"model": "gpt-3.5-turbo", #gpt-4 is also possible..but slow
"messages": messages,
"max_tokens": 50,