danielgross

import requests
import time
import os
import sys
import openai
import tiktoken
from termcolor import colored

openai.api_key = open(os.path.expanduser('~/.openai')).read().strip()

sayakpaul

veekaybee

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

ChrisHayduk

"""

The code below combines approaches published by both @eugene-yh and @jinyongyoo on Github. 

Thanks for the contributions guys!

"""

import torch
import peft

fofr

from openai import OpenAI
import os
from datetime import datetime
import requests

client = OpenAI()

prompt = "a portrait photo of a woman"
qualities = ["standard", "hd"]
styles = ["natural", "vivid"]

emlazzarin

	title	author	link
1	The Captive Mind	Czesław Miłosz	Amazon
2	Private Truths, Public Lies: The Social Consequences of Preference Falsification	Timur Kuran	Amazon
3	When Reason Goes on Holiday: Philosophers in Politics	Neven Sesardić	Amazon
4	Intellectuals and Society	Thomas Sowell	Amazon
5	Intellectuals: From Marx and Tolsoy to Sartre and Chomsky	Paul Johnson	Amazon
6	The Making of an American Thinking Class: Intellectuals and Intelligentsia in Puritan Massachusetts	Darren Staloff	[Amazon](ht

andrewyu0

obsidian copilot

your notes = your lifelong ai companion + intelligence augmentation

COMMENTS VERY WELCOME! this is a first pass to put these ideas in one place

tldr - combine obsidian + openinterpreter to create a bespoke pkm copilot experience. if you follow the "file over app" philosophy, this combination can be your lifetime AI companion

alexweberk

bhimrazy

import concurrent.futures
from typing import Any, Callable, List
from tqdm import tqdm

def concurrent_task_executor(task: Callable[[Any], None], data_list: List[Any], max_workers: int = 32, description: str = None) -> None:
    """
    Execute tasks concurrently on a list of data objects using ThreadPoolExecutor.

    Args:
        task (Callable): The function to apply to each data object.