Building Systems with the ChatGPT API vs Machine Learning Specialization

The course is tightly structured across 11 short lessons: how LLMs and tokenization work, the chat format, input classification, the Moderation API, chain-of-thought reasoning, prompt chaining, output checking and system-level evaluation, all tied together by a running customer-service example. Reviewers repeatedly praise the clarity and the theory-to-practice balance. The honest mark-down is depth and age: it was built on GPT-3.5 Turbo in 2023, so it predates tool calling, structured JSON outputs and reasoning models, and it does not go deep on real-world deployment beyond the safety checks.

Isa Fulford (Member of Technical Staff at OpenAI) demonstrates while Andrew Ng frames the concepts, and reviewers consistently call the pairing knowledgeable and effective communicators. The teacher-demonstrator dynamic mirrors how a beginner actually thinks through each step, and the pacing of 5-20 minute lessons keeps momentum. This is the most authoritative free source for building multi-step LLM systems, and it shows.

Free on the DeepLearning.AI platform with runnable in-browser notebooks, and free to audit the Coursera version. For roughly 90 minutes of content that teaches a reusable architecture for chaining LLM calls, the value is hard to beat. The only caveats are that the platform's graded assignment and certificate sit behind a Pro upgrade, and that the aging notebook code can eat time if you insist on running it locally rather than in-browser.

The standout feature for most reviewers is the hands-on coding: you build prompt chains that consume prior completions, glue Python around model calls, and assemble a full customer-service chatbot that classifies queries, moderates input, reasons step by step and evaluates its own output. The caveat is that there is no graded, kept portfolio artefact on the free tier, and the supplied notebooks now require fixes (deprecated API syntax, missing Utils.py and products.json) to run outside the course sandbox.

The patterns taught — chaining, moderation, evaluation, routing — are exactly the building blocks of production LLM features, and developers report the course gave them a structured mental model they could apply immediately. But it is a one-hour primer with no certificate on the free tier and no capstone, so on its own it is a strong foundation rather than a credential. Its career value is as the second step in a sequence, not a destination.

Praised for intuitive explanations and the expanded neural networks unit, but reviewers note the new version trades depth for accessibility — backprop is brushed past, RL feels like a preview.

Andrew Ng's pedagogy gets near-universal praise across HN and blogs. Multiple commenters describe him as the best instructor they ever had; complaints are essentially absent.

Content is strong relative to cost, and auditing remains possible. The friction comes from Coursera's subscription gating around grading and certificates — a recurring HN gripe.

Browser-hosted Jupyter notebooks with auto-grading remove a major friction point from the original. The community forum is active but not deeply mentioned in reviews.

Builds a real foundation in ideas and Python tooling, but datasets are clean and deployment is out of scope. Reviewers flag the need to supplement with Kaggle or a portfolio project.