all AI news
If you teach a chatbot how to read ASCII art, it will teach you how to make a bomb
March 18, 2024, 9:57 p.m. | Cal Jeffrey
TechSpot www.techspot.com
University researchers have developed a way to "jailbreak" large language models like Chat-GPT using old-school ASCII art. The technique, aptly named "ArtPrompt," involves crafting an ASCII art "mask" for a word and then cleverly using the mask to coax the chatbot into providing a response it shouldn't.
Read Entire Article
art ascii chat chatbot gpt jailbreak language language models large language large language models researchers school university will word
More from www.techspot.com / TechSpot
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US