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

veekaybee

Machine Learning Design Patterns

This book is all about patterns for doing ML. It's broken up into several key parts, building and serving. Both of these are intertwined so it makes sense to read through the whole thing, there are very many good pieces of advice from seasoned professionals. The parts you can safely ignore relate to anything where they specifically use GCP. The other issue with the book it it's very heavily focused on deep learning cases. Not all modeling problems require these. Regardless, let's dive in. I've included the stuff that was relevant to me in the notes.

Most Interesting Bullets:

• Machine learning models are not deterministic, so there are a number of ways we deal with them when building software, including setting random seeds in models during training and allowing for stateless functions, freezing layers, checkpointing, and generally making sure that flows are as reproducible as possib

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

veekaybee

How are search and recommendations the same, and how are they different?

• Question on Mastodon
• Question on Twitter

TL;DR:

• The design of both search and recommendations is to find and filter information
• Search is a "recommendation with a null query"
• Search is "I want this", recommendations is "you might like this"

veekaybee

Using Whisper to transcribe audio

This episode of Recsperts was transcribed with Whisper from OpenAI, an open-source neural net trained on almost 700 hours of audio. The model includes an encoder-decoder architecture by tokenizing audio into 30-second chunks, normalizing audio samples to the log-Mel scale, and passing the data into an encoder. A decoder is trained to predict the captioned text matching the encoder, and the model includes transcription, as well as timestamp-aligned transcription, and multilingual translation.

The transcription process outputs a single string file, so it's up to the end-user to parse out individual speakers, or run the model [through a sec

veekaybee

You might want to use uv now that it's gotten a bit more stable for Mac. I've already been using it at work and wanted to install it locally for a new project on my computer, but had pyenv. Only do this if you completely want to rip out pyenv, otherwise, just disable it by removing from your ~/.zshrc

Here's what I had to do:

1. Comment out everything related to pyenv in my ~/.zshrc file and source ~/.zshrc - you may have to search around for all instances if you are like me and not organized about your ~/.zshrc
2. rm -rf "$HOME/.pyenv" # DOUBLE CHECK THIS COMMAND AND WHERE YOUR pyenv is
3. brew uninstall pyenv just in case

veekaybee

how to properly select from DuckDB

SELECT review_text,title,description,goodreads.average_rating, goodreads_authors.name 
FROM goodreads 
JOIN goodreads_reviews 
ON goodreads.book_id = goodreads_reviews.book_id 
JOIN goodreads_authors  
ON goodreads_authors.author_id = (select REGEXP_EXTRACT(authors, '[0-9]+')[1] as author_id FROM goodreads) LIMIT 10;

veekaybee

Data source:

https://sites.google.com/eng.ucsd.edu/ucsdbookgraph/home

@inproceedings{DBLP:conf/recsys/WanM18,
  author       = {Mengting Wan and
                  Julian J. McAuley},
  editor       = {Sole Pera and
                  Michael D. Ekstrand and
                  Xavier Amatriain and

veekaybee

Isolation forests versus decision trees

Isolation forest paper

• Isolated points should be lower and closer to the root of the tree

veekaybee

Systems Performance 2nd edition

See synthesized write-up here

• Do a quick performance check in 60 seconds
• Use a number of different tools available in unix
• Use flamegraphs of the callstack if you have access to them
• Best performance winds are elimiating unnecessary wrok, for example a thread stack in a loop, eliminating bad config
• Mantras: Don't do it (elimiate); do it again (caching); do it less (polling), do it when they're not looking, do it concurrently, do it more cheaply