tldrdailynews.com logo

Nvidia introduces Guardrails toolkit to improve accuracy of AI chatbots.

1 min read
Source: CNBC
Nvidia introduces Guardrails toolkit to improve accuracy of AI chatbots.
Photo: CNBC
TL;DR

Nvidia has launched NeMo Guardrails, a software that can prevent AI models from stating incorrect facts, talking about harmful subjects, or opening up security holes. The software can add guardrails to prevent the software from addressing topics that it shouldn't, force a chatbot to talk about a specific topic, head off toxic content, and prevent LLM systems from executing harmful commands on a computer. NeMo Guardrails is open source and offered through Nvidia services and can be used in commercial applications.

Topics:businessartificial-intelligence#ai-chips#artificial-intelligence#large-language-models#nemo-guardrails#nvidia#reinforcement-learning
Share this article
  1. Nvidia has a new way to prevent A.I. chatbots from 'hallucinating' wrong facts  CNBC
  2. NeMo Guardrails Keep AI Chatbots on Track  Nvidia
  3. Nvidia Launches AI Guardrails: LLM Turtles All the Way Down  The New Stack
  4. Nvidia’s new Guardrails tool will make AI chatbots less crazy  Digital Trends
  5. Nvidia releases a toolkit to make text-generating AI ‘safer’  TechCrunch

Want the full story? Read the original reporting

Read on CNBC