Large language models (LLMs), such as the models supporting the functioning of ChatGPT, are now used by a growing number of people worldwide to source information or edit, analyze and generate texts. As these models become increasingly advanced and widespread, some computer scientists have been exploring their limitations and vulnerabilities in order to inform their future improvement.
DarkMind: A new backdoor attack that leverages the reasoning capabilities of LLMs
Reader’s Picks
-
An increasing number of young boys and girls in Finland believe in God. A study conducted among young people in [...]
-
The new Netflix series “Apple Cider Vinegar” tells the story of wellness influencer Belle Gibson, who built a loyal following [...]
-
A trio of psychologists at Azusa Pacific University in the U.S. has identified a possible reason for people experiencing a [...]