itsjustmeMay 11, 2024
Flipboard Science Desk
You already know not to take an AI chatbot seriously. But there may be reason to be even more cautious. New research has found that many AI systems have already started to deliberately present human users with false information. Science Alert explains why "AI developers do not have a confident understanding of what causes undesirable AI behaviors like deception.”
https://flip.it/ZbnJtj
#Science #AI #ArtificialIntelligence #Chatbot #Tech
AI Has Already Become a Master of Lies And Deception, Scientists Warn

You probably know to take everything an artificial intelligence (AI) chatbot says with a grain of salt, since they are often just scraping data indiscriminately, without the nous to determine its veracity.

ScienceAlert
May 10, 2024 at 11:06pmWeb
Show threadIceNineMay 10, 2024
@ScienceDesk If an AI playing Diplomacy cannot lie or deceive, it would be a pretty poor Diplomacy player. That is just the nature of the game.