pamelafox

import json
import logging
import re
from typing import Any, AsyncGenerator, Optional, Union

import aiohttp
import openai
from azure.search.documents.aio import SearchClient
from azure.search.documents.models import QueryType

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

Hellisotherpeople

You probably don't know how to do Prompt Engineering

(This post could also be titled "Features missing from most LLM front-ends that should exist")

Apologies for the snarky title, but there has been a huge amount of discussion around so called "Prompt Engineering" these past few months on all kinds of platforms. Much of it is coming from individuals who are peddling around an awful lot of "Prompting" and very little "Engineering".

Most of these discussions are little more than users finding that writing more creative and complicated prompts can help them solve a task that a more simple prompt was unable to help with. I claim this is not Prompt Engineering. This is not to say that crafting good prompts is not a difficult task, but it does not involve doing any kind of sophisticated modifications to general "template" of a prompt.

Others, who I think do deserve to call themselves "Prompt Engineers" (and an awful lot more than that), have been writing about and utilizing the rich new eco-system

veekaybee

ChatGPT Resources

Context

ChatGPT appeared like an explosion on all my social media timelines in early December 2022. While I keep up with machine learning as an industry, I wasn't focused so much on this particular corner, and all the screenshots seemed like they came out of nowhere. What was this model? How did the chat prompting work? What was the context of OpenAI doing this work and collecting my prompts for training data?

I decided to do a quick investigation. Here's all the information I've found so far. I'm aggregating and synthesizing it as I go, so it's currently changing pretty frequently.

Model Architecture

kovetskiy

#!/bin/bash
###
### my-script — does one thing well
###
### Usage:
###   my-script <input> <output>
###
### Options:
###   <input>   Input file to read.
###   <output>  Output file to write. Use '-' for stdout.

IanColdwater

Mute these words in your settings here: https://twitter.com/settings/muted_keywords

ActivityTweet
generic_activity_highlights
generic_activity_momentsbreaking
RankedOrganicTweet
suggest_activity
suggest_activity_feed
suggest_activity_highlights
suggest_activity_tweet

intentionally-left-nil

#!/bin/python3
# Largely copied from http://www.mathewinkson.com/2015/03/delete-old-tweets-selectively-using-python-and-tweepy
# However, Mathew's script cannot delete tweets older than something like a year (these tweets are not available from the twitter API)
# This script is a complement on first use, to delete old tweets. It uses your twitter archive to find tweets' ids to delete
# How to use it :
#     - download and extract your twitter archive (tweet.js will contain all your tweets with dates and ids)
#     - put this script in the extracted directory
#     - complete the secrets to access twitter's API on your behalf and, possibly, modify days_to_keep
#     - delete the few junk characters at the beginning of tweet.js, until the first '['   (it crashed my json parser)
#     - review the script !!!! It has not been thoroughly tested, it may have some unexpected behaviors...

AlexArcPy

ledmaster

Swizec

import cheerio from 'cheerio-without-node-native';

const convertRequestBodyToFormUrlEncoded = (data) => {
    const bodyKeys = Object.keys(data);
    const str = [];
    for (let i = 0; i < bodyKeys.length; i += 1) {
        const thisKey = bodyKeys[i];
        const thisValue = data[thisKey];
        str.push(`${encodeURIComponent(thisKey)}=${encodeURIComponent(thisValue)}`);