https://www.tomshardware.com/tech-industry/artificial-int... | Minds

Explore
Minds+
Supermind
Affiliate
Groups
Networks

BBSing, Artscene & Demoscene

PSECmedia: PSEC and Pondscape Documentaries

·

Join

https://www.tomshardware.com/tech-industry/artificial-intelligence/researchers-jailbreak-ai-chatbots-with-ascii-art-artprompt-bypasses-safety-measures-to-unlock-malicious-queries?utm_source=facebook.com&utm_content=tomsguide&utm_campaign=socialflow&utm_medium=social

Researchers jailbreak AI chatbots with ASCII art -- ArtPrompt bypasses safety measures to unlock malicious queries

ArtPrompt bypassed safety measures in ChatGPT, Gemini, Clause, and Llama2.

tomshardware.com

Mar 7 2024 · 11:40 PM

Get replies from creators like PSECmedia: PSEC and ...

2upvotes

1remind