Datawhale dry goods
Latest: ChatGPT course, editor: Heart of the machine
Important courses, Wu Enda personally taught.
ChatGPT is here, everything is changing fast, and some technology companies are starting to recruit "prompt engineers". Unlike traditional computer engineers who write code, Prompt engineers test the system for irrational behavior or problems by asking the AI a series of logically rigorous questions. However, there has been no unified standard or systematic experience on how to do it.
Just now, Wu Enda officially announced a good news: he and OpenAI have produced a new course on ChatGPT Prompt Engineering, and the course is free.
Course link: https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/
Wu Enda said that there are too many materials on how to write prompts on the market. But for developers, how to call the large model API to build application software is more important, but there are few materials in this area. That's the value of their class.
The course is about one and a half hours long and aims to help developers:
Learn the prompt engineering best practices needed for application development;
Discover new ways to use LLM, including how to build your own custom chatbot;
Gain hands-on experience writing and iterating prompts using the OpenAI API.
On a practical level, the course will demonstrate how the LLM API can be used in applications for a variety of tasks, including:
Summaries (e.g. simplified summaries of user reviews)
Inference (e.g. sentiment classification, topic extraction)
Transforming text (e.g. translation, spelling and grammar correction)
Extensions (e.g. auto-composing emails)
All concepts are illustrated with numerous examples, and developers can conduct interactive experiments directly in the Jupyter notebook environment to gain hands-on experience in prompt engineering.
This course is very beginner-friendly, requiring only a basic understanding of Python. It's also a good fit for advanced machine learning engineers who want to get in touch with Prompt Engineering and use LLM.
Andrew Ng said that so far, there has been relatively little material on best practices (compared to how to prompt a Web UI) for developers who want to use the API to access LLM to build applications. They are happy to make some changes.
Chinese tutorial: ChatGPT development and application guide !
Participate in learning: AIGC team learning is here!
Dry goods learning, like three times ↓