tunib-ai/joker
AI model designed to test the effectiveness in handling external ethical attacks.
This project helps AI safety researchers and ethics professionals evaluate how well their Korean language AI models withstand malicious or unethical prompts. It takes a generative AI model as input and automatically generates simulated "attacks" (unethical prompts), allowing you to quickly assess the target model's responses. This saves significant time and mental effort compared to manually crafting and testing prompts.
Use this if you need to efficiently and comprehensively test your Korean language AI model's robustness against ethical attacks without extensive human effort.
Not ideal if you are looking to generate unethical content for malicious purposes, or if your primary need is for qualitative human judgment of ethical AI behavior.
Stars
11
Forks
1
Language
Python
License
—
Category
Last pushed
Feb 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/tunib-ai/joker"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ludwig-ai/ludwig
Low-code framework for building custom LLMs, neural networks, and other AI models
withcatai/node-llama-cpp
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema...
mudler/LocalAI
:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and...
zhudotexe/kani
kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)
SciSharp/LLamaSharp
A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.