Article List
Explore latest news, discover interesting content, and dive deep into topics that interest you
Alignment Research @ EleutherAI
A breif overview of EAIs approach to alignment...
Interacting with LLMs with Minimal Chat
Should chat be the main UX for LLMs? I don't think so and believe we can do better....
Building a Q&A Bot for Weights & Biases' Gradient Dissent P…
In this article, we explore how to utilize OpenAI's ChatGPT and LangChain to build a Question-Answering bot for Weights & Biases' podcast series, Grad...
More Design Patterns For Machine Learning Systems
9 patterns including HITL, hard mining, reframing, cascade, data flywheel, business rules layer, and more....
Aidan Gomez - Scaling LLMs and Accelerating Adoption
On this episode of Gradient Dissent, we’re joined by Aidan Gomez, Co-Founder and CEO at Cohere. Cohere develops and releases a range of innovative AI-...
Transformer Math 101
We present basic math related to computation and memory usage for transformers...
Raspberry-LLM - Making My Raspberry Pico a Little Smarter
Generating Dr. Seuss headlines, fake WSJ quotes, HackerNews troll comments, and more....
Jonathan Frankle: Neural Network Pruning and Training
Jonathan Frankle and Lukas Biewald discuss neural network pruning and training, the "Lottery Ticket Hypothesis" and much more on this episode of Gradi...
Experimenting with LLMs to Research, Reflect, and Plan
Also, shortcomings in document retrieval and how to overcome them with search & recsys techniques....
Exploratory Analysis of TRLX RLHF Transformers with Transfo…
A demonstration of interpretabilty for RLHF models...
A ChatGPT clone, in 3000 bytes of C, backed by GPT-2
This program is a dependency-free implementation of GPT-2, including...
EleutherAI Second Retrospective: The long version
What we've been up to for the past year EleutherAI....
LLM-powered Biographies
Asking LLMs to generate biographies to get a sense of how they memorize and regurgitate....
How to Write Data Labeling/Annotation Guidelines
Writing good instructions to achieve high precision and throughput....
The View from 30,000 Feet: Preface to the Second EleutherAI…
(Some of) what we've been up to for the past year-and-a-half at EleutherAI....
Content Moderation & Fraud Detection - Patterns in Industry
Collecting ground truth, data augmentation, cascading heuristics and models, and more....
Sarah Catanzaro — Remembering the Lessons of the Last AI Re…
Sarah discusses the lessons learned from the "AI renaissance" of the mid 2010s and shares her thoughts on machine learning from her perspective as an...
Cristóbal Valenzuela — The Next Generation of Content Creat…
Cris gives a demo of Runway, a new video editing platform that uses machine learning to make content creation easier, and discusses the future of comp...