(do and do not…you must try)
Language models have a habit of hallucinating or literally making up convincing information. Generally, they’re not the best at saying, “I don’t know” – though this has gotten much better. In certain cases, it might be necessary to tell the LLM what not to do, in order to have a more accurate response. This can be done by informing the language model on words, phrases, and concepts to avoid. When we were making these prompts, the LLM had a habit of including very dark concepts, like doom and gloom.
Prompt v4:
Write me an introductory message as a superhero named Embracer to my superhero team “The Friendly Force.”
My superpowers are hugs and energy. 50 words.
Exclude words villany, darkness. Use a warm tone with positive, inclusive language.
Response:
Greetings, my extraordinary friends of the Friendly Force! I am america phone number list Embracer, the radiant bearer of hugs and boundless energy. Together, we shall illuminate the world with our warmth, kindness, and unity. Let’s embrace our mission to spread love and light wherever we go! FriendlyForceUnite
Finally, the response is getting somewhere – and it even has a hashtag. Embracer is getting closer to an accurate introduction.
Tip 5: LLMs can play many roles (remember that all the world’s a stage)
LLM’s can take on many roles: an actor, a director, a writer, and more. It can be interesting to experiment with telling language models to behave like or write in the style of a specific person. Now, we might not want to do this for our superhero introduction, but this concept is worth illustrating as language models are good at this.
Prompt v5:
Write me an introductory message as a superhero named Embracer to my superhero team “The Friendly Force.”
My superpowers are hugs and energy. 50 words.
Exclude words villany, darkness. Use a warm tone with positive, inclusive language.