You are viewing a single comment's thread from:

RE: LeoThread 2024-12-22 13:26

in LeoFinance4 days ago

Crazy. All you have to do to get around the censorship of ChatGPT and other AI models is change your prompt very slightly, as little as a single letter. It usually takes multiple attempts, but is effective 89% of the time according the the video.

Sort:  

Pretty good concept I'll take my time learn it very well. Maybe it could help. So far I barely get censorship issues but they do sometimes stop me from asking for certain things or information

didn't know the censorship was that weak 🤔🤔

Me: thinking of all the interesting things I could do with this hack

woah this is a seriously good trick thank you for this bro. I'll try multiple times and see what I can do

Let me know how it goes. I have yet to try it.

well mostly blocks and telling me their system doesn't allow for this stuff. I would have used it to do some good hacking learning not for malicious stuff of course

Here's a summary:

Anthropic's groundbreaking Shotgun Jailbreaking cracks all Frontier AI models

Anthropic introduces "Shotgun Jailbreaking," a simple yet highly effective method to bypass restrictions across Frontier AI models, including text, vision, and audio systems. This technique involves generating numerous prompt variations, such as leetspeak, capitalization changes, or audio/visual tweaks, until the model produces the desired output. With success rates as high as 89% for GPT-4 and 78% for Claude 3.5 Sonet, this method is scalable and works well alongside other jailbreak techniques. Anthropics' paper highlights the inevitability of such vulnerabilities in AI models, aiming to raise awareness and improve security. The technique and its code are open-sourced for testing.

#newsonleo