Published 2 months ago

Microsoft Creates Tools To Stop People From Tricking Chatbots

Summary by Bloomberg

(Bloomberg) -- Microsoft Corp. is trying to make it harder for people to trick artificial intelligence chatbots into doing weird things. New safety features are being built into Azure AI Studio, a service powered by OpenAI that lets developers build customized AI assistants using their own data, the Redmond, Washington-based company said in a blog post on Thursday. The tools include “prompt shields,” which are designed to detect and block delibe…

0 Articles

All

Left

Center

Right

Bloomberg

Microsoft Creates Tools To Stop People From Tricking Chatbots

2 months ago·United States

Read Full Article

Cryptopolitan

Microsoft Enhances AI Chatbot Security to Thwart Tricksters

Microsoft Corp has added a number of security features in the Azure AI Studio that should, over time, continue reducing the likelihood that its users configure AI models into a mode that would have them act abnormally or inappropriately.The multinational technology company based in Redmond, Washington, outlined the improvements in a blog post, emphasizing guaranteeing the integrity of AI interactions and fostering trust in the user base. Prompt…

2 months ago

Read Full Article

Think freely.Subscribe and get full access to Ground NewsSubscriptions start at $9.99/year

Stories disproportionately reported by the Left or the Right

Ground News Article Assistant

Not enough coverage to generate an Article Assistant.