Elijah-Bodden

How to make an LLM clone of yourself

Wanna create and play with an AI clone of yourself or someone else (my lawyer says please don't)[^1] like this one? You're in luck because it's super easy!

Step one: get you some datas

This step really varies depending on your data sources, but the end goal is to turn some of real-you's conversations (from your platforms of choice) into a ShareGPT format dataset with you as the gpt. Here's what your (json) file should end up looking like:

{"conversations": [{"from": "human", "value": "Hi"}, {"from": "gpt", "value": "Hello"}]} 
{"conversations": [{"from": "human", "value": "What's up "}, {"from": "gpt", "value": "not much, you?"}, {"from": "human", "value": "Just thinking, what if you're a robot and I don't realize it?"}, {"from": "gpt", "value": "hahaha don't be crazy"}]}
...

NOTE: Make sure every line starts with a message from the other person ("human")

Elijah-Bodden

import json

filenames = []
out_name = "processed.json"
myname = "YOURDISCORDUSERNAME"

for filename in filenames:
    with open(filename, encoding="utf-8") as file:
        data = json.load(file)["messages"]
    newdata = [[data[i]["author"]["name"], data[i]["content"]] for i in range(len(data)) if data[i]["content"] != ""]

Elijah-Bodden

.intel_syntax noprefix
.globl _start

.section .text

_start:
    # Open socket
    mov rdi, 2
    mov rsi, 1
    mov rdx, 0

Elijah-Bodden

import random
def PI(precision):
    j = 0
    for i in range(precision):
        x = random.random()
        y = random.random()
        if (x ** 2 + y ** 2 < 1): j += 1
    return j/precision * 4

Elijah-Bodden

function checkTypes(...requiredArgs, expectedTypes) {
  var mistyped = requiredArgs.filter((argumentObj, index) => {
    return expectedTypes[index]
      ? !expectedTypes[index].includes(typeof Object.values(argumentObj)[0])
      : false;
  });
  if (mistyped != "") {
    throw new TypeError(
      `expected the argument "${
        Object.keys(mistyped[0])[0]