Skip to content

Instantly share code, notes, and snippets.

View aksinor's full-sized avatar

Dmytro Vizir aksinor

  • Kyiv
  • 05:34 (UTC +02:00)
View GitHub Profile
@aksinor
aksinor / contemplative-llms.txt
Created January 10, 2025 23:11 — 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
const cars = [
{ brand: 'Nissan', model: '300 ZX', topSpeed: 155 },
{ brand: 'Mitsubishi', model: '3000GT', topSpeed: 165 },
{ brand: 'Chevrolet', model: 'C4 ZR1', topSpeed: 180 },
{ brand: 'Audi', model: 'S8', topSpeed: 155 },
{ brand: 'Dodge', model: 'Neon', topSpeed: 153 },
]
function getTopSpeedCar(arr) {
let fastestCar = null,
from abc import ABC, abstractmethod
class Jungle:
# Singleton
def __new__(cls, predators, herbivorous):
if not hasattr(cls, 'isinstance'):
cls.isinstance = super().__new__(cls)
return cls.isinstance
ROMAN = {
1: 'I', 2: 'II', 3: 'III', 4: 'IIII', 5: 'V', 6: 'VI', 7: 'VII', 8: 'VIII', 9: 'VIIII', 10:
'X', 50: 'L', 100: 'C', 500: 'D', 1000: 'M',
}
ARABIC = {
'I': 1, 'II': 2, 'III': 3, 'IIII': 4, 'V': 5, 'VI': 6, 'VII': 7, 'VIII': 8, 'VIIII': 9, 'X': 10,
'L': 50, 'C': 100, 'D': 500, 'M': 1000,
}