Building Systems with the ChatGPT API vs MITx 6.86x: Machine Learning with Python — From Linear Models to Deep Learning

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.

Graduate-level MIT curriculum: linear classifiers, SVMs, neural nets, clustering, recommender systems, and reinforcement learning, taught from first principles. Reviewers praise the depth and the under-the-hood focus, though several find the lectures terse with too few worked examples.

Taught by MIT faculty Regina Barzilay, Tommi Jaakkola, and Karene Chu. Strong expertise, but learner feedback on the lectures is polarized — praised for intuition by some, called short and example-light by others. Most learning happens through the projects, not the videos.

A verified certificate (~$300) buys MIT-grade material that builds algorithms from scratch and counts toward the Statistics and Data Science MicroMasters. The course can also be audited for free, so the paid tier is mainly for the credential and graded autograder access.

As a self-paced MOOC there is no 1:1 instructor support; help comes from course forums and learner-run Discord groups. Multiple reviewers explicitly recommend joining a class Discord to stay motivated and unblock on projects, which signals the official support channel alone is thin.

You implement linear models, kernels, neural nets, and RL by hand, which builds durable intuition for how ML actually works. The trade-off, noted by reviewers, is that it deliberately avoids high-level libraries like scikit-learn, so it is foundational rather than a job-ready tooling course.