The course is good, but the assignments made it a rather frustrating experience. Not only frustrating, but I felt that the assignments were not really adding any value to my skillset. I would not recommend someone to pay for the course. It's not "pay worthy". If you can take it for free...sure go for it. Some of my frustrations were - the auto graders don't work half the time: it fails with rather arbitrary errors which makes you waste time trying to solve non-issues. The grader also randomly fails in consecutive submissions for code that was passing in the previous attempt. the unit tests and auto graders are different: you can spend hours trying to get the tests to pass and then the grader fails Assignments are unnecessarily complex, with long and unclear instructions: More than anything else, Module 3 assignment1 basically made me hate LLMs. It was possibly the worst assignment I have ever taken and the value gained out of it was close to zero.. I think DLAI should simplify the course and make it more focussed on real world usage. Sure converting py2 to py3 code is a valid use case, but in the real world we are dealing with millions of lines of code. How to use the LLM in those situations and how to make LLMs aware of different layers of the system would be a more useful exercise than what's in the course.

Great course! I'm a bit unsatisfied for the grading assignments that are somewhat obscure: I spent more time in understanding what was requested to do than in doing it.

Each course in the "Generative AI for Software Development" curriculum is well thought out, tested, paced well, and graded automatically. There will be many new concepts for someone who is new to computer science or python and software development, but that's what the LLM is there to help with! I gained a deeper appreciation for how to use / partner with an LLM, and throughout the 3 courses, I learned many new Python skills around documentation generation, unit testing, dependency management, and database manipulation. As an experienced software engineer, I found some of the lectures tedious and problems simple, but partnering with an LLM felt fresh and new and was critical to completing exercises in a timely manner (often with a one-shot response!), especially when I didn't know where to start or how to get unstuck. I must stress, that _I still learned a ton_, even though the LLM did some heavy lifting. For example, I knew about Python's `requirements.txt`, `pip install`, and `conda`. But I learned from the LLM some differences in how `pip` and `conda` manage dependencies that makes a smarter `conda` user today. I also learned from the course lectures about Python docstring formats and tools for HTML generation, among other subjects. This course starts with the prompt-engineering practice of assigning a role, being specific, providing examples, iterating on a solution, and maintaining a healthy amount of skepticism about the LLM's fallibility (usually because of how I prompted it), and throughout it provides a good palette of domains in which to practice all of this. **Once you get comfortable with how to talk to an LLM and become familiar with its strengths and weaknesses, using one feels a bit like "cheating" on a math test with a calculator—it's a game-changer for the scope of problems you can solve!** The LLM provides all kinds of great insights and know-how: it handles syntax adeptly, provides perfect algorithmic implementations, and handily recommends and employs libraries and techniques that would have just eaten up my time to discover, let alone put to use. I'm grateful for how Laurence Moroney and his team have distilled these skills into meaningful steps for all to learn and practice at their own pace.

This course was an eye-opening experience on how to team up with AI for software development. Laurence Moroney’s expertise and passion for generative AI really shine, making the learning process engaging and highly applicable. The course focuses on leveraging large language models (LLMs) to enhance team collaboration and boost efficiency in software projects. A standout aspect was learning to use AI for managing and debugging complex software dependencies, which is often a daunting task. The hands-on labs were challenging but highly rewarding, pushing me to think creatively about teaming up with LLMs to solve real-world problems. The ability to generate comprehensive tests and clear documentation with AI tools was another major takeaway that will streamline my workflow. Laurence’s approach equips you with practical skills, from writing automated tests with LLMs to implementing testing frameworks and managing dependencies with AI assistance. Whether you're working in a team or handling large-scale projects, this course shows how AI can be an invaluable collaborator in software development. Highly recommended for anyone looking to boost their team's productivity and efficiency with AI!

I recently completed this course, and I found it to be an excellent resource for software engineers. The course effectively covers essential concepts of generative AI and its practical applications in software development. One of the highlights was learning prompt techniques to maximize the utility of large language models (LLMs). The hands-on exercises allowed me to practice pair-coding with LLMs, which significantly improved my coding efficiency. I highly recommend this course to software engineers looking to enhance their skills and stay competitive in the tech landscape. It provides a great blend of theory and practical application, equipping participants with valuable tools for daily development tasks.

This course explained how LLM can enhance understanding and efficiency in team collaboration, including document generation, code reviews, and more. It also covered using LLM to assist with automation, performance, and security testing. However, LLM has limitations and isn’t all-powerful. What impressed me most was its ability to resolve dependencies and conflicts, which are common in development practices. Despite not always having up-to-date training data or specific resources for niche dependencies, LLM is still highly effective for troubleshooting. Through simple explanations and practice, this course helped us understand the practical applications of these tools, which I found very beneficial.

A nice course taught by Laurence. I learned about several new Python libraries like pip-audit, pip-tools, etc. I really enjoyed the quizzes, programming assignments, and especially the GPT-4o sandbox lab environment. My only feedback would be to add more programming assignments and slightly increase their difficulty.

It provides a comprehensive and systematic approach, along with best practices, for integrating Generative AI into modern software development. While it is designed for beginners, even senior software developers and engineers can gain significant insights from it

Laurence is exceptional and amazing teacher, above all he's amazing human being for highlighting human errors that he himself faces sometimes. Any course taught by him I follow.

This is an awesome course teach you how to use the AI as your developer partner and no as a tool that do the work for you!

Learned quite a bit and honed existing skills

Best content and explained it very well.

useful as one would expect

Very Engaging Course!!!1

An excellent course.

Exceptional!!!!!

The best

Nice

The contents themselves are great and well explained. Lawrence is an awesome instructor. This course is way too easy for experienced developers who have already been using LLMs in their day-to-day tasks.

Expected the Jupiter Book section to be a little more user-friendly. Particularly it had scrolling issues.