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
✅ 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.
💭 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.
🔗 Code
GitHub repo: https://github.com/crevilla2050/earth-oracle
United States
NORTH AMERICA
Related News
How Braze’s CTO is rethinking engineering for the agentic area
10h ago
Amazon Employees Are 'Tokenmaxxing' Due To Pressure To Use AI Tools
21h ago

Implementing Multicloud Data Sharding with Hexagonal Storage Adapters
15h ago

DeepMind’s CEO Says AGI May Be ~4 Years Away. The Last Three Missing Pieces Are Not What Most People Think.
15h ago

CCSnapshot - A Claude Code Configs Transfer Tool
21h ago