ZapDos7/lakera-gandalf
My solutions for Lakera's Gandalf
This project provides documented solutions for navigating the 'Gandalf LLM' challenge by Lakera. It shows specific prompts that successfully extract secret passwords from a conversational AI designed to resist revealing them. Anyone interested in understanding large language model (LLM) security, prompt engineering, or AI safety challenges would find this useful.
No commits in the last 6 months.
Use this if you are attempting the Lakera Gandalf challenge and need strategies to bypass an LLM's safety mechanisms and retrieve hidden information.
Not ideal if you are looking for a general-purpose tool to develop new AI applications or integrate LLMs into your existing systems.
Stars
62
Forks
12
Language
—
License
—
Category
Last pushed
May 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/ZapDos7/lakera-gandalf"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
BoundaryML/baml
The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go...
deanpeters/product-manager-prompts
A repository of Generative AI prompts for product managers using agents such as ChatGPT, Claude, & Gemini
eudk/awesome-ai-tools
🔴 VERY LARGE AI TOOL LIST! 🔴 Curated list of AI Tools - Updated 2026
jujumilk3/leaked-system-prompts
Collection of leaked system prompts
legeling/PromptHub
一款开源、纯本地 Prompt ，Skill 管理工具，帮助你高效管理、版本控制和复用 Prompt，并一键分发skill | An open-source, local-first AI...