Trapping Malicious AI Knowledge Into On/Off Switchable Modules Gets Underway

Researchers are developing modular add-ons for large language models that can trap and switch off malicious AI knowledge, aiming to enhance AI safety. The approach, detailed in new research, involves adding modules to traditional LLMs to isolate and control harmful capabilities.

Trapping Malicious AI Knowledge Into On/Off Switchable Modules Gets Underway By Lance Eliot, ContributorSource: Forbes Innovation https://www.forbes.com/innovation/ New research is adding modules to traditional LLMs to increase AI safety /glossary/ai-safety . Maybe this will do the trick. An AI Insider analysis and scoop.Get AI news in your inbox Daily digest of what matters in AI.