Introducing a New Class of AI Attacks: LLM Flowbreaking, Resulting in Potential "Self-Harm" Instructions - discu.eu

Linking pages

The Words That Stop ChatGPT in Its Tracks - The Atlantic https://www.theatlantic.com/technology/archive/2024/12/chatgpt-wont-say-my-name/681028/ 23 comments

Related searches:

Search whole site: site:knostic.ai

Search title: Introducing a New Class of AI Attacks: LLM Flowbreaking, Resulting in Potential "Self-Harm" Instructions

See how to search.

Submit link to: