Diff-in-Means Concept Editing is Worst-Case Optimal
Explaining a result by Sam Marks and Max Tegmark
Full feed
Feed 5,413 posts
Every story across every category, newest first. Each card links to the original publisher; daily-brief posts open as editorial pages.
The third New England RLHF Hackers Hackathon
Introduction At the third New England RLHF Hackathon, several interesting projects were showcased, each focusing on different aspects of machine learning and reinforcement learning. Participants and…
Adversarial Attacks on LLMs
The use of large language models in the real world has strongly accelerated by the launch of ChatGPT. We (including my team at OpenAI, shoutout to…
Neural algorithmic reasoning
In this article, we will talk about classical computation: the kind of computation typically found in an undergraduate Computer Science course on Algorithms and Data Structures…
Multimodality and Large Multimodal Models (LMMs)
For a long time, each ML model operated in one data mode – text (translation, language modeling), image (object detection, image classification), or audio (speech recognition).…
The Artificiality of Alignment
This essay first appeared in Reboot. Credulous, breathless coverage of “AI existential risk” (abbreviated “x-risk”) has reached the mainstream. Who could have foreseen that the smallcaps…
Open challenges in LLM research
[LinkedIn discussion, Twitter thread] Never before in my life had I seen so many smart people working on the same goal: making LLMs better. After talking…
LLM Powered Autonomous Agents
Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as…
Generative AI Strategy
I had a lot of fun preparing the talk: “Leadership needs us to do generative AI. What do we do?” for Fully Connected. The idea for…
Generative AI and AI Product Moats
Here are eight observations I’ve shared recently on the Cohere blog and videos that go over them.: Article: What’s the big deal with Generative AI? Is…
Prompt Engineering
Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the…
The Transformer Family Version 2.0
Many new Transformer architecture improvements have been proposed since my last post on “The Transformer Family” about three years ago. Here I did a big refactoring…
Large Transformer Model Inference Optimization
[Updated on 2023-01-24: add a small section on Distillation.] Large transformer models are mainstream nowadays, creating SoTA results for a variety of tasks. They are powerful…
Remaking Old Computer Graphics With AI Image Generation
Can AI Image generation tools make re-imagined, higher-resolution versions of old video game graphics? Over the last few days, I used AI image generation to reproduce…
The Illustrated Stable Diffusion
Translations: Chinese, Vietnamese. (V2 Nov 2022: Updated images for more precise description of forward diffusion. A few more images in this version) AI image generation is…
Some Math behind Neural Tangent Kernel
Neural networks are well known to be over-parameterized and can often easily fit data with near-zero training loss with decent generalization performance on test dataset. Although…
Generalized Visual Language Models
Processing images to generate text, such as image captioning and visual question-answering, has been studied for years. Traditionally such systems rely on an object detection network…
Learning with not Enough Data Part 3: Data Generation
Here comes the Part 3 on learning with not enough data (Previous: Part 1 and Part 2). Let’s consider two approaches for generating synthetic data for…
Applying massive language models in the real world with Cohere
A little less than a year ago, I joined the awesome Cohere team. The company trains massive language models (both GPT-like and BERT-like) and offers them…
Learning with not Enough Data Part 2: Active Learning
This is part 2 of what to do when facing a limited amount of labeled data for supervised learning tasks. This time we will get some…
The Illustrated Retrieval Transformer
Discussion: Discussion Thread for comments, corrections, or any feedback. Translations: Korean, Russian Summary: The latest batch of language models can be much smaller yet achieve GPT-3…
Learning with not Enough Data Part 1: Semi-Supervised Learning
When facing a limited amount of labeled data for supervised learning tasks, four approaches are commonly discussed.
How to Train Really Large Models on Many GPUs?
[Updated on 2022-03-13: add expert choice routing.] [Updated on 2022-06-10]: Greg and I wrote a shorted and upgraded version of this post, published on OpenAI Blog:…
Understanding Convolutions on Graphs
Understanding the building blocks and design choices of graph neural networks.