Generative AI with Large Language Models vs Stanford CS229 Machine Learning

Across three weeks (roughly 16 hours), the course covers the full generative AI project lifecycle: the Transformer architecture from the "Attention Is All You Need" paper, prompt engineering, in-context learning, Chinchilla scaling laws, instruction fine-tuning, parameter-efficient fine-tuning (LoRA), and reinforcement learning from human feedback (RLHF). Reviewers repeatedly praise how it grounds each technique in the relevant research paper before showing the "how," which builds genuine understanding of the "why." The most consistent content criticism is that week three squeezes too many topics (RLHF, model optimisation, RAG, ReAct) in at shallow depth and feels disjointed after the RLHF section.

The course is fronted by Andrew Ng with AWS instructors Antje Barth, Mike Chambers, Shelbee Eigenbrode and Chris Fregly delivering the technical content. Reviewers describe the delivery as technically clear, well-diagrammed and well-paced, with one calling Andrew Ng "like a rock star in Artificial Intelligence teaching." The multi-instructor AWS panel draws consistently positive marks for explaining production concepts from real experience, though it is a panel format rather than a single narrative voice.

At roughly USD 49 with six months of access — and the AWS SageMaker lab compute included in that price — multiple reviewers explicitly call it "not overpriced" for the breadth of current, applied content. The main value caveats are that the labs do not require writing original code (so you can finish for the certificate without coding), and that the included lab budget is finite — at least one learner exhausted it after a technical glitch on the very first lab and could not continue.

The three SageMaker labs (dialogue summarisation prompt engineering, PEFT fine-tuning with LoRA, and RLHF detoxification) give learners an end-to-end view of real LLM pipelines using PyTorch and the Hugging Face transformers library. The near-universal complaint is that the labs are "run all the cells" walkthroughs with no original coding, no graded homework, and no self-built project — you can submit by clicking through. Reviewers value them as illustrations but warn they do not verify skill or prepare you to build a similar application from scratch.

The curriculum maps closely to how LLM applications are actually scoped, adapted and deployed in industry — model selection, cost-aware optimisation (quantisation, pruning, distillation), fine-tuning strategy, RLHF alignment and RAG-style augmentation. The modern toolchain (SageMaker, Hugging Face, PyTorch) is exactly what practitioners use. The gap is between conceptual fluency and hands-on ability: because the labs require no original code, several reviewers recommend pairing the course with a build-it-yourself resource such as the Hugging Face NLP course to close the implementation gap.

Reviewers consistently praise the mathematical depth — full derivations of GLMs, SVMs, EM, factor analysis and learning theory. The honest caveat is that the curriculum predates the Transformer era and deep learning gets brief treatment.

Andrew Ng's blackboard teaching gets repeated praise — one HN reviewer specifically prefers it to the Coursera version because he uses the board. The lecture pacing is academic and unhurried, which some find rigorous and others find slow.

Completely free — full 2018 lecture series on YouTube, all lecture notes, problem sets and section materials at cs229.stanford.edu. No certificate, no grading, no paywall. Reviewers consistently call it the highest-value rigorous ML resource available.

Zero official support for the YouTube cohort — no forum, no grading, no TA office hours, no cs50.ai-style tutor. Self-learners rely on community GitHub repos for solutions. Honest weakness, not unique to CS229.

Theory transfers durably — gradient descent, GLMs, regularisation, EM and learning theory remain foundational. The honest gap is that CS229 was not designed as a practical-first course; deployment, modern frameworks and Transformers are out of scope.