Cameron R. Wolfe, Ph.D. (@cwolferesearch) / X

Cameron R. Wolfe, Ph.D.

4,726 posts

Cameron R. Wolfe, Ph.D.

@cwolferesearch

Research @Netflix • Writer @ Deep (Learning) Focus • PhD @optimalab1

Austin, TX

cameronrwolfe.substack.com

Joined August 2021

Pinned
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Apr 16, 2025
Reinforcement Learning (RL) is quickly becoming the most important skill for AI researchers. Here are the best resources for learning RL for LLMs… TL;DR: RL is more important now than it has ever been, but (probably due to its complexity) there aren’t a ton of great resources
106K
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Nov 23, 2023
Q-Learning is *probably* not the secret to unlocking AGI. But, combining synthetic data generation (RLAIF, self-instruct, etc.) and data efficient reinforcement learning algorithms is likely the key to advancing the current paradigm of AI research… TL;DR: Finetuning with
545K
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Aug 20, 2023
Replying to @MerabDvalishvil
86K
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Mar 27, 2023
Large language models (LLMs) are fun to use, but understanding the fundamentals of how they work is also incredibly important. One major idea and building block of LLMs is their underlying architecture: the decoder-only transformer model. 🧵[1/6]
393K
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Nov 27, 2023
Due to the recent surge in popularity of AI and language models, one of the most common questions I hear is: How can we train a specialized LLM over our own data? The answer is actually pretty simple… TL;DR: Training LLMs end-to-end is quite difficult due to the size of the
411K
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Mar 2, 2023
The ChatGPT API was released yesterday and it costs 90% less than expected. Here’s five methods (and resources to learn about them) that are **probably** being used to enable this price reduction… 🧵[1/6]
263K
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Aug 25, 2023
One of the best ways to reduce hallucinations with LLMs is by retrieving useful, factual information and injecting it into the LLM’s prompt as added context. Although this might sound complicated, it’s actually quite easy to implement with standard vector search functionality…
357K
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Feb 5, 2024
RAG is one of the best (and easiest) ways to specialize an LLM over your own data, but successfully applying RAG in practice involves more than just stitching together pretrained models… What is RAG? At the highest level, RAG is a combination of a pretrained LLM with an
184K
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Jan 23, 2024
The volume of LLM research being released is staggering. Although there are too many new papers for any one person to read, this work can be largely distilled into a much smaller set of overlapping themes. Recently, there are three trends in LLM research that have been especially
191K
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Mar 31, 2023
Self-attention is the primary building block of large language models (LLMs) and transformers in general. But, how exactly does it work? 🧵 [1/8]
328K
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Sep 26, 2024
I find it so interesting (and smart) that Meta / LLaMA is eliminating the dependence of their models on the HuggingFace stack. The LLaMA models now: - Have their own website to download weights. - Have one of the best LLM cookbooks that's available. - Provide extensive
253K
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Mar 14, 2023
Although large language models (LLMs) are incredibly capable, they are pretty simple to understand. In fact, the core components of most LLMs can be distilled into five major components… 🧵[1/7]
195K
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Nov 4, 2024
Prompt engineering requires a lot of manual effort. Here are four automatic prompt optimization algorithms that can help to improve your prompt with minimal effort… (1) Automatic Prompt Engineer (APE) [1] searches over a pool of prompts proposed by an LLM–usually ~32-64
97K
Cameron R. Wolfe, Ph.D.
@cwolferesearch
Jan 12, 2024
Generative large language models (LLMs) are based upon the decoder-only transformer architecture. Currently, these types of generative LLMs are incredibly popular. However, I use encoder-only architectures for 90% of use cases as a practitioner. Here’s why… History of
261K