C
Cameron R. Wolfe
cameronrwolfe.substack.com · Personal blog · on HN since 2023
Cameron R. Wolfe writes the Deep Learning Focus newsletter, explaining LLM research such as scaling laws, mixture-of-experts, and reinforcement learning methods.
What HN saysHN commenters cite it for in-depth LLM explainers on judges, GRPO tricks and decoder-only transformers, and list it among recommended AI newsletters.
18HN people shared it
7linked it in comments
32stories submitted
57story points
3 months agolast shared
2023people per year2026
Most-shared posts
- 1Scaling Laws for LLMs: From GPT-3 to o33 people · 2 points · first shared 2025 · discussion on HN
- 2Homepage3 people · first shared 2023
- 3Open-Source LLMs: Better Base Models (Part Two)2 people · 4 points · first shared 2023 · 1 comments on HN
- 4Mixture-of-Experts (Moe) LLMs2 people · 3 points · first shared 2025 · discussion on HN
- 5Decoder-Only Transformers: The Workhorse of Generative LLMs2 people · 2 points · first shared 2024 · discussion on HN
- 6Understanding LLaMA-2 from the Ground Up2 people · 2 points · first shared 2023 · discussion on HN
- 7Olmo 3 and the Open LLM Renaissance1 people · 4 points · first shared 2025 · discussion on HN
- 8NanoMoE: Mixture-of-Experts (Moe) LLMs from Scratch in PyTorch1 people · 4 points · first shared 2025 · discussion on HN
- 9A Guide for Debugging LLM Training Data1 people · 3 points · first shared 2025 · discussion on HN
- 10Vision Large Language Models (VLLMs)1 people · 3 points · first shared 2025 · discussion on HN
- 11RL Scaling Laws for LLMs1 people · 3 points · first shared 2026 · discussion on HN
- 12Model Merging: A Survey1 people · 2 points · first shared 2024 · discussion on HN
- 13Agent Evaluation: A Detailed Guide1 people · 2 points · first shared 2026 · discussion on HN
- 14Open-Source LLMs: Imitation and Alignment (Part Three)1 people · 2 points · first shared 2023 · discussion on HN
- 15AI Agents from First Principles1 people · 2 points · first shared 2025 · discussion on HN
What HN people wrote when they linked it
senko · 2024-12-05
Too late to edit, but here's a great, really in-depth post about using LLMs as judges to evaluate LLM outputs (when you don't have the ground truth for everything): https://cameronrwolfe.substack.com/p/finetuned-judge This is about finetuning LLMs to do it, but the first part is a good intro to why and how.
janalsncm · 2026-06-28
Their R1 paper was really well-done. But I think it leaves out a few details necessary for stable training.
https://cameronrwolfe.substack.com/p/grpo-tricks
marcyb5st · 2024-05-01
I think what you suggest would be very similar to a encoder-decoder architecture, which has been abandoned in favor of decoder-only architectures (https://cameronrwolfe.substack.com/p/decoder-only-transformers-the-wor… So I am guessing that what you suggest has already been tried and didn't work out, ut not sure why (the problems I mentioned above or something else).
Sorry, that's where the limit of my knowledge is. I work on ML stuff, but mostly on "traditional" deep learning and so I am not up to speed with the genAI field (also, the sheer amount of papers coming out makes it basically impossible stay up to date of you're not in the field).
neeleshs · 2023-11-12
aquir · 2023-11-12
AI Supremacy: https://aisupremacy.substack.com/
Latent Space: https://www.latent.space/
Encyclopedia Autonomica: https://jdsemrau.substack.com/
Deep Learning Focus: https://cameronrwolfe.substack.com/
Artificial Fintelligence: https://finbarrtimbers.substack.com/
and I did not click on the links, but used a search engine to find the sources.
jiayo · 2023-11-12
AI Supremacy: https://aisupremacy.substack.com/
Latent Space: https://www.latent.space/
Encyclopedia Autonomica: https://jdsemrau.substack.com/
Deep Learning Focus: https://cameronrwolfe.substack.com/
Artifical Fintelligence: https://finbarrtimbers.substack.com/
Dylan16807 · 2026-02-11
> We don't have a model for a LLM that does exist will respond to a specific query either.
Yes we do... It's math, you can calculate it.
> No, it's not and I'm getting tired of explaining this. If you think it is, write your paper and get very rich.
Why would I get rich for explaining how to do math?
> You clearly don't understand any of this.
Could you be more specific?
Quantum physics is stupidly hard to calculate when you approach realistic situations.
A real LLM takes a GPU a fraction of a second.
They're both hard to interpret, please realize I'm agreeing that LLMs are hard to interpret. But they're easier than QM on some other fronts.
And mentioning copenhagen or many-worlds doesn't show that quantum mechanics are easy to interpret, that's about as useful as saying an LLM works like neuron activation.
> Oh really ? Lol
Here's one of many posts about it. https://cameronrwolfe.substack.com/p/llm-scaling-laws