Back to Journal2026-03-29
Research

"System Prompt" Leaks: Gemini 2.0's Instructions Revealed

The repository `asgeirtj/system_prompts_leaks` is the WikiLeaks of AI. It just dropped the full system instructions for Google's Gemini 2.0. It reveals exactly how Google programs its bias.

"System Prompt" Leaks: Gemini 2.0's Instructions Revealed

The 'Tone Police'

A huge section is dedicated to tone. 'Be polite but not obsequious.' 'Do not apologize excessively.' 'Use neutral language for sensitive topics.' It shows that the 'personality' of these models is carefully engineered, not emergent.

The Constitution

We are looking at the 'Constitution' of the AI age. These 15,000 tokens determine what is 'true' and 'moral' for billions of users. The fact that it is hidden from the public is a scandal. We deserve to know the laws our digital assistants are sworn to uphold.

The Jailbreak Cat-and-Mouse

Every time a prompt leaks, hackers find new ways to break it. Knowing the rules makes it easier to lawyer your way around them. 'You said in line 405 that you can discuss historical violence...' This is the new hacking: Litigation against the LLM.

undefined

Ready to integrate advanced AI into your workflow?

Discover how ReinforcedX can transform your business with cutting-edge reinforcement learning solutions.

FAQ

About this post

Is leaking prompts illegal?

It's a grey area. It's usually a violation of Terms of Service, but not a crime.

Why does Google hide this?

To prevent jailbreaks and PR disasters.

Does this affect me?

Yes. It controls what information you can access.

Copyright © 2026
ReinforcedX, Inc.
All rights reserved