Prompt Engineering has become a passion topic of mine. It's super fun to tinker with GenAI, to ask it questions and to optimize the way that I ask those questions.
"Prompting bridges communication" - generated using Midjourney
The basic of Prompt Engineering are simple:
Task specify a task that you want the LLM to do for you.
Context give the chatbot the context that it needs to complete your task.
Format how do you want the LLM to respond to you? A bullet point list? A table? A slide deck? a blogpost?
Process if you already know a great process to solve the problem, tell the AI to follow it. If you don't, at least give it room to think.
Recently I noticed that following these practices for using AI has honed my communication skills even when talking to colleagues. The same principles apply. My coworker also needs to know any context that I do but they don't. They need to know who am I to talk to them, how do I see them, why do I think they can help and what do i need help with. And finally, how would I like them to support me.
I never would have expected that learning to talk with AI would make me a better communicator with humans. But it does, and I love it.
Robot Emoji
Author
I am a JavaScript and GenAI Enthusiast; developer for the fun of it! Here I write about webdev, technology, personal thoughts and anything I finds interesting.
"A path into the AI future" - generated using Midjourney
Some reflections on what 2022 showed us about the future.
Generative AI describes AI that takes a prompt and generates something from it. Prime examples include Copilot which takes code or comments as a prompt to complete the code I want to write, ChatGPT which takes a chat message and replies with a human-like answer and Stable-Diffusion (or Dall-E, or Midjourney) which takes a prompt and returns a fitting image. All of these AIs made massive progress in 2022!
Daily notes in Obsidian are ephemeral, they matter most for the day there were written and maybe the days surrounding them. But, after a week, we hardly ever refer back to them. If something truly mattered, we probably pulled it out to another note.
That being said, I often find myself wanting to refer to yesterdays note. And Obsidian doesn't provide a native way to get to yesterdays note. My current solution to this is to add links to the last and next daily note into every daily note via a template.
