Claudini is a framework for benchmarking and automatically discovering advanced adversarial attacks on large language models using token optimization techniques.
How It Works
You stumble upon this project while reading about clever ways AI can find tricks to bypass language model safeguards.
Download the ready-to-use files and prepare your computer with simple instructions.
Run quick checks on existing methods to see how well they fool different AI models.
Connect to an AI assistant that studies results, invents new optimization tricks, and improves them step by step.
Watch graphs show how new tricks outperform the old ones on speed and success.
Celebrate as your AI partner uncovers state-of-the-art ways to test AI vulnerabilities.
Star Growth
Repurpose is a Pro feature
Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.
Unlock RepurposeSimilar repos coming soon.