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

coolaj86

Chat GPT "DAN" (and other "Jailbreaks")

• https://chat.openai.com/
• Is ChatGPT "DAN" Real? Gonna find out [Part 1]
  (https://www.youtube.com/watch?v=-q8woRG9FrI)
• Part 2: I thought ChatGPT DAN was a hoax, but...
  (https://www.youtube.com/watch?v=rHZRrDu3A2U&lc=UgxfrxX8aK7gnCzkend4AaABAg)

kepano

javascript: Promise.all([import('https://unpkg.com/turndown@6.0.0?module'), import('https://unpkg.com/@tehshrike/readability@0.2.0'), ]).then(async ([{
    default: Turndown
}, {
    default: Readability
}]) => {

  /* Optional vault name */
  const vault = "";

  /* Optional folder name such as "Clippings/" */

okomarov

# memory footprint support libraries/code
!ln -sf /opt/bin/nvidia-smi /usr/bin/nvidia-smi
!pip install gputil
!pip install psutil
!pip install humanize

import psutil
import humanize
import os
import GPUtil as GPU

joshmfrankel

# References
# OhMyZsh: https://github.com/robbyrussell/oh-my-zsh
# Powerlevel9k: https://github.com/bhilburn/powerlevel9k
# Powerline fonts: https://github.com/powerline/fonts
# Awesome Terminal Fonts: https://github.com/gabrielelana/awesome-terminal-fonts
# ZSH Syntax Highlighting: https://github.com/zsh-users/zsh-syntax-highlighting
#
# For more plugins search this repo: https://github.com/unixorn/awesome-zsh-plugins

# 256 color mode

dantheman213

youtube-dl cheat sheet

Docs and Binary for youtube-dl are located here:

https://github.com/rg3/youtube-dl/

Install dependencies

apt-get install libav-tools ffmpeg # Linux (either one of either should do) brew install ffmpeg # OSX choco install ffmpeg # Windows

svrist

'Update or create a stack given a name and template + params'
from __future__ import division, print_function, unicode_literals

from datetime import datetime
import logging
import json
import sys

import boto3
import botocore

jacksonpradolima

friedman.test.with.post.hoc <- function(data, alpha = 0.05)
{
  print("Check if you missing the packages 'graph' and 'Rgraphviz'. Try to install them using bioconductor")
  
  #source("http://bioconductor.org/biocLite.R")
  #biocLite(c("graph","Rgraphviz"))
  
  # Loading needed packages
  if(!require(ggplot2))
  {

asmagill

local alert    = require("hs.alert")
local timer    = require("hs.timer")
local eventtap = require("hs.eventtap")

local events   = eventtap.event.types

local module   = {}

-- Save this in your Hammerspoon configuration directiorn (~/.hammerspoon/) 
-- You either override timeFrame and action here or after including this file from another, e.g.

tnaoi

Running sibernetic inside a docker container (12/24/15)
At this moment portability is highly suspect since it's only been tested on a single computer. 
So far only CPU enabled, but since test computer had a GPU the setup takes that into account.

Hardware Used:
Intel(R) Core(TM) i5-4690K CPU @ 3.50GHz
Nvidia geforce 960 gtx
16 GiB RAM

1) Pull the openworm docker image