kconner

macOS Internals

Understand your Mac and iPhone more deeply by tracing the evolution of Mac OS X from prelease to Swift. John Siracusa delivers the details.

Starting Points

How to use this gist

You've got two main options:

yoavg

Reinforcement Learning for Language Models

Yoav Goldberg, April 2023.

Why RL?

With the release of the ChatGPT model and followup large language models (LLMs), there was a lot of discussion of the importance of "RLHF training", that is, "reinforcement learning from human feedback". I was puzzled for a while as to why RL (Reinforcement Learning) is better than learning from demonstrations (a.k.a supervised learning) for training language models. Shouldn't learning from demonstrations (or, in language model terminology "instruction fine tuning", learning to immitate human written answers) be sufficient? I came up with a theoretical argument that was somewhat convincing. But I came to realize there is an additional argumment which not only supports the case of RL training, but also requires it, in particular for models like ChatGPT. This additional argument is spelled out in (the first half of) a talk by John Schulman from OpenAI. This post pretty much

VictorTaelin

Notes on this tweet.

• The screenshots were taken on different sessions.

• The entire sessions are included on the screenshots.

• I lost the original prompts, so I had to reconstruct them, and still managed to reproduce.

• The "compressed" version is actually longer! Emojis and abbreviations use more tokens than common words.

orneo1212

#!/bin/env -S deno run --allow-run --allow-env --allow-read

/* ResticTS

# Example toml config - resticfolders.toml
[config]
debug = false

[vars]
password = "secret_password"

hwchase17

from langchain.llms import Anthropic
from langchain.agents import load_tools, initialize_agent
from langchain.tools import AIPluginTool
PREFIX = """\n\nHuman: Answer the following questions as best you can. You have access to the following tools:"""
SUFFIX = """Begin!

Question: {input}
\n\nAssistant:
Thought:{agent_scratchpad}"""

rain-1

The reverse turing test

I asked GPT-4 to come up with 10 questions to determine if the answerer was AI or human.

I provided my own answers for these questions and I also asked ChatGPT to answer them.

The result is that GPT-4 was able to correctly differentiate between AI and Human.

rain-1

Purpose

Bootstrap knowledge of LLMs ASAP. With a bias/focus to GPT.

Avoid being a link dump. Try to provide only valuable well tuned information.

Prelude

Neural network links before starting with transformers.

hwchase17

# STEP 1: Load

# Load documents using LangChain's DocumentLoaders
# This is from https://langchain.readthedocs.io/en/latest/modules/document_loaders/examples/csv.html

from langchain.document_loaders.csv_loader import CSVLoader
loader = CSVLoader(file_path='./example_data/mlb_teams_2012.csv')
data = loader.load()

kfox

TCP echo server for Node.js

Usage

1. Make sure you have a modern-ish version of Node.js installed.
2. Type npx https://gist.github.com/kfox/1280c2f0ee8324067dba15300e0f2fd3
3. Connect to it from a client, e.g. netcat or similar: nc localhost 9000

geoffreylitt