all AI news
Researchers detail ArtPrompt, a jailbreak that uses ASCII art to elicit harmful responses from aligned LLMs such as GPT-3.5, GPT-4, Gemini, Claude, and Llama2 (Dan Goodin/Ars Technica)
March 16, 2024, 4:50 a.m. |
Techmeme www.techmeme.com
Dan Goodin / Ars Technica:
Researchers detail ArtPrompt, a jailbreak that uses ASCII art to elicit harmful responses from aligned LLMs such as GPT-3.5, GPT-4, Gemini, Claude, and Llama2 — LLMs are trained to block harmful responses. Old-school images can override those rules. — Researchers have discovered …
ars technica art ascii claude dan gemini gpt gpt-3 gpt-3.5 gpt-4 jailbreak llama2 llms researchers responses
More from www.techmeme.com / Techmeme
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
AI Engineering Manager
@ M47 Labs | Barcelona, Catalunya [Cataluña], Spain