A new technique teaches a large language model to perform a safety check on an AI chatbot so it doesn’t give toxic responses. “Our work is an attempt to reduce the human effort to ensure a safer and trustworthy AI future,” Pulkit Agrawal says. http://mitsha.re/46Jp50RcfRg | Massachusetts Institute of Technology (MIT)

7.6K views · 30 reactions | Machines can’t understand words in the traditional sense. So how does AI deal with ambiguity and double meanings? In the second video of our Understanding with Unbabel series, we take a look at the techniques used to teach computers to “understand” words in context. Check it out! | Unbabel | Facebook