@stanfordnlp: Many roughly know how a transformer works To REALLY understand modern neural LMs—MoEs, GPU tiling, kernels, RLHF, data—…
Summary
Stanford's CS336 course on modern neural language models, covering topics like MoEs and RLHF, is being released on YouTube with a two-week delay.
View Cached Full Text
Cached at: 05/13/26, 12:32 AM
Many roughly know how a transformer works To REALLY understand modern neural LMs—MoEs, GPU tiling, kernels, RLHF, data—you need CS336 By @tatsu_hashimoto, @percyliang The 2026 edition appears on yt with ~2 weeks delay http://youtube.com/playlist?list=PLoROMvodv4rMqXOcazWaTUHhq-yembLCV… Materials https://cs336.stanford.edu
@stanfordnlp: Many roughly know how a transformer works To REALLY understand modern neural LMs—MoEs, GPU tiling, kernels, RLHF, data—…
Channel: @stanfordnlp Source: https://www.youtube.com/playlist?list=PLoROMvodv4rMqXOcazWaTUHhq-yembLCV
Similar Articles
@DanKornas: "Stanford CS229 I Machine Learning I Building Large Language Models (LLMs)" (Stanford Online), ... What you will learn:…
Stanford CS229 online course announcement covering building LLMs, deep neural networks, TensorFlow, Keras, OpenCV, and NLP with spaCy.
@Rassh_RAJ: Stanford CS336: Large Language Models from Scratch (2026) is now fully on YouTube, with a few additions beyond the 2025…
Stanford's CS336 course 'Large Language Models from Scratch' (2026) is now fully available on YouTube, with additions beyond the 2025 playlist, offering an in-depth understanding of LLMs beyond APIs.
@stanfordnlp: The “problem” with CS336 is not the ~22 hours of videos but the larger number of hours it takes to do the assignments. …
Stanford's CS336 course on language modeling from scratch is announced, featuring intensive hands-on assignments covering tokenizers, transformers, data, and alignment.
@stanfordnlp: There are two paths to learning the details (aka “tricks” or “secrets”) of successfully training state-of-the-art langu…
Stanford NLP promotes the CS336 course as a path to learning the tricks of successfully training state-of-the-art language models.
@techNmak: Learn LLMs from Stanford this weekend. Stanford's Autumn 2025 Transformers & LLMs course is fully public and 100% free.…
Stanford University's Autumn 2025 Transformers & LLMs course is fully public and free, covering transformer fundamentals, advanced techniques, LLM training, inference optimization, and more in 9 lectures.