The course called Building Systems with the ChatGPT API will be taught by OpenAl’s Isa Fulford and Andrew Ng. Learners will go beyond individual prompts, and learn to build complex applications that use multiple API calls to an LLM. Also they will learn to evaluate an LLM’s outputs for safety and accuracy, and drive iterative improvements.
Second course titled LangChain for LLM Application Development will be taught by LangChain’s CEO Harrison Chase and Andrew Ng together. Students will learn about LangChain, a powerful open-source tool for building applications using LLMs, including memory for chatbots, question answering over a doc, and an LLM agent that can decide what action to take next.
Third one, How Diffusion Models Work, will be taught by Lamini’s CEO Sharon Zhou. It will teach the technical details of how diffusion models work, which power Midjourney, DALL E, and Stable Diffusion. Learners will also have at the end working code to generate their own video game sprites in a Jupyter notebook.
All of these courses are free for a limited time, and each of them can be completed in around 1-1.5 hours. All of these courses require a basic knowledge of Python. In the case of How Diffusion Models Work course, Python, Tensorflow, or Pytorch knowledge is required.
Recently, DeepLearning.AI collaborated with OpenAI to offer a course ChatGPT Prompt Engineering for Developers which is designed to help developers effectively utilize LLMs. This course reflects the latest understanding of best practices for using prompts for the latest LLM models.