This is a great article/thread that illustrates how you can chain together prompts + API calls to allow a large language model (LLM) to create robust task-specific workflows
When you prompt an LLM directly, you rely on what it can do "from memory", but this is limiting
🧵
Quote Tweet
The intelligence of generative LLMs is surprising. But people often overestimate it in areas while underestimating it in others.
Key concepts:
1- It's important to augment their information with the right sources.
So it's not
Human: Question
GPT: Factual answer.
It's more
Show this thread
