WebsiteHunt is broughtBrought to you by Redact Everything
Johnny
Persuade LLMs to Jailbreak each other
This project explores the systematic persuasion of LLMs to jailbreak them. It introduces 40 persuasion techniques and achieves a 92% attack success rate on aligned LLMs.
The study also reveals that advanced models like GPT-4 are more vulnerable to persuasive adversarial prompts (PAPs), and adaptive defenses against these PAPs provide effective protection against other attacks.
Comments
Loading comments...
You might also like
HiAPI
One API for leading AI image, video, and text generation models. ✨ Premium
ProjectManagementTools
Optimize your Projects with ProjectManagementTools 🌱 Sponsored
Jailbreak Chat
Collection of ChatGPT jailbreak prompts
tokenspeed
feel LLM tokens-per-second
Code Language Converter
Quickly convert code to other programming languages using AI
RI
Real Image Alphabet
Type your name; each letter is matched to a real image.
The Paper Airplane Guy
Learn to fold record-breaking paper airplanes
Postcard
Easiest way to make a personal website
Tune My Music
Transfer Playlists From Any Music Platform to Any Other!
Which Face is Real?
Click on the person who is real.
Breachsense
Hackers don't break in — They log in
Code Translator
Use AI to translate code from one language to another
DevObserver
App For Each Developer
GPT-Migrate
Easily migrate your codebase from one language to another
100 Jumps
Hold to charge, release to jump. Reach 100 platforms to win.
JSON Formatter
Makes JSON easy to read.
Paper Tactics
Play a pen-and-paper game with other people around the world
Hustle Cafe
Connect and meet with other founders online to exchange ideas
Use plaintext email
The guide to using plain text email
Socialsonic
LinkedIn Personal Branding Made Easy with AI
PersonalData.info
What personal data you are exposing to the web.
OC