Best method for making easy money in 2024-2025

const sentence = "I like poop."
const seed = sentence
const rng = new RNG(seed)
const chat_gpt_probability = rng.get()

const dictionary = new Set();

// Fetch and load the dictionary if not already loaded
async function loadDictionary() {
    if (dictionary.size === 0) {
        const response = await fetch('https://raw.githubusercontent.com/dwyl/english-words/master/words.txt');
        const text = await response.text();
        const lines = text.split('\n');
        for (const line of lines) {
            const word = line.trim().toLowerCase();
            if (word) dictionary.add(word);
        }
    }
}

// Calculate the ratio of valid words in a given sentence
async function getValidWordRatio(sentence) {
    // Ensure the dictionary is loaded
    await loadDictionary();

    // Split the sentence into words by spaces
    const words = sentence.split(/\s+/);
    const totalWords = words.length;
    let validWordsCount = 0;

    // Count the number of valid words
    for (const word of words) {
        const cleanedWord = word.trim().toLowerCase();
        if (cleanedWord && dictionary.has(cleanedWord)) {
            validWordsCount++;
        }
    }

    // Calculate and return the ratio of valid words to total words
    return totalWords ? validWordsCount / totalWords : 0;
}

// Example usage
getValidWordRatio("hello world").then(console.log); // Output: 1.0 (both words are valid)
getValidWordRatio("h3llo world").then(console.log); // Output: 0.5 (only "world" is valid)
getValidWordRatio("This is a valid sentence.").then(console.log); // Output: 0.75 (valid words: "this", "is", "a", "valid")
getValidWordRatio("This sentence not r1ght.").then(console.log); // Output: 0.5 (valid words: "this", "sentence", "not")

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

def calculate_probability(sentence, model_name='gpt2'):
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForCausalLM.from_pretrained(model_name)
    inputs = tokenizer(sentence, return_tensors='pt')
    with torch.no_grad():
        loss = model(**inputs, labels=inputs['input_ids']).loss
    return torch.exp(-loss).item()

# Example usage
sentence = "Hello, how are you today?"
print(f"Probability: {calculate_probability(sentence):.10f}")