ChatGPT Prompt Engineering for Developers vs Stanford CS229 Machine Learning

Two core principles (write clear and specific instructions, give the model time to think) plus modules on iterative prompt development, summarizing, inferring, transforming, expanding, and building a chatbot. Reviewers praise the clarity and the runnable Jupyter notebooks. The honest limit is depth: it was built in April 2023 on GPT-3.5 Turbo and does not cover newer patterns like tool calling, structured outputs, or reasoning models.

Isa Fulford (OpenAI) and Andrew Ng (DeepLearning.AI) are about as authoritative as the field gets. The teacher-student dynamic — Ng asking the clarifying questions a beginner would ask while Fulford demonstrates — is repeatedly cited as a strength that mirrors how learners actually think.

Free on the DeepLearning.AI platform with every code example runnable in-browser, no API key or local setup required. Reviewers consistently call out "the best part is that it's free" as a decisive advantage over the paid prompt-engineering courses that flooded the market in 2023.

Being a one-hour self-paced short course, there is no graded assignment, cohort, or mentor support. The OpenAI and DeepLearning.AI community forums are active and useful, but learners are largely on their own. For a course this short the need is limited, but there is no structured help.

Six practical use cases implemented end-to-end give learners patterns they can apply the same day. Developers report it directly improved their ability to build LLM features. The caveat is that the API-level patterns are a foundation, not a production blueprint — several reviewers wanted more on structuring LLMs into real applications.

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.