This is a submission for Weekend Challenge: Earth Day Edition
🌍 What I Built
I built a small command-line experiment called earth-oracle.
You ask the Earth a question…
and it answers.
But not in the way you might expect.
Instead of generating answers, the oracle reveals something more uncomfortable:
the answer was already there.
🎬 Demo
Here’s what it looks like:
earth oracle ready>
the earth listens best to questions.
dear earth, i know you need help, is my following action helping you heal?
Does showering every 3 days instead of daily help?
...
estimating carbon impact...
🌍 the earth says:
"Yes, but buy a good deodorant."
No APIs required.
No datasets.
No knowledge base.
And yet… it feels like the system knew.
🧠The Idea
This project is based on a classic “oracle” illusion I built years ago with friends.
The trick is simple:
the user secretly types the answer first
the interface masks that input
the system later reveals it as if it knew in advance
For this challenge, I reimagined that idea as something more reflective:
a tool that shows we already know what we should be doing for the planet
⚙️ How I Built It
The core of the project is not AI — it’s terminal control.
raw input handling using Python (tty, termios)
character-by-character interception
masking user input while displaying a predefined “invocation”
switching between hidden and visible input phases
controlled reveal timing for dramatic effect
The result is a CLI that feels… slightly uncanny.
✨ AI as Reflection, Not Authority
I integrated GEMINI not to generate answers — but to interpret them.
Instead of asking the model:
“What is the right thing to do?”
The system asks:
“What does this action reveal?”
earth-oracle --use-gemini
Instead of answering the question, Gemini provides a short reflection on the user’s own statement.
This was intentional:
the oracle reveals
the AI reflects
I wanted to avoid building “just another chatbot.”
🏆 Prize Categories
âś… Best Use of Google Gemini
Gemini is used not to generate answers, but to interpret and reflect on user-provided intentions, preserving the core concept of the oracle.
đź’ Why This Matters
Most tools try to tell us what to do for the environment.
This one does something different:
it reminds us that we already know.
🔚 Final Thought
The problem isn’t that we don’t know how to help the Earth.
It’s that we don’t listen to ourselves.
đź”— Code
GitHub repo: https://github.com/crevilla2050/earth-oracle
Top comments (0)