Scientists develop AI monitoring agent to detect and stop harmful outputs By Cointelegraph

A crew of researchers from synthetic intelligence (AI) agency AutoGPT, Northeastern College and Microsoft (NASDAQ:) Analysis have developed a device that displays massive language fashions (LLMs) for doubtlessly dangerous outputs and prevents them from executing.

The agent is described in a preprint analysis paper titled “Testing Language Mannequin Brokers Safely within the Wild.” In accordance with the analysis, the agent is versatile sufficient to watch present LLMs and might cease dangerous outputs, akin to code assaults, earlier than they occur.

Proceed Studying on Cointelegraph