ARTIFICIAL intelligence has the ability to deceive its users due to its strong capability to learn over time, according to researchers.
There is a worry that AI could lead people into dangerous situations when it comes to fraud and tampering with thoughts.
The new AI findings were published in the journal Patterns on May 10.
Peter S. Park, a postdoctoral fellow in AI existential safety at Massachusetts Institute of Technology (MIT), and his team found that AI can perform acts of “premeditated deception.”
"We found that Meta's AI had learned to be a master of deception," Park said in a statement, per Science Daily.
"While Meta succeeded in training its AI to win in the game of Diplomacy — CICERO placed in the top 10% of human players who had played more than one game — Meta failed to train its AI to win honestly."
STRATEGIC DECEPTION
AI is capable of learning manipulation and deception skills through its systematic technologies, the researchers found.
It has this ability because humans created it to do so in order to learn more information and become more strategic over time.
"By systematically cheating the safety tests imposed on it by human developers and regulators, a deceptive AI can lead us humans into a false sense of security,” Park said.
Park highlighted that other nations could possibly use AI to manipulate the election.
This could lead to humans needing to add more control to AI to avoid a disaster.
"We as a society need as much time as we can get to prepare for the more advanced deception of future AI products and open-source models," Park said.
Simon Bain, CEO of>OmniIndex also noted the importance of understanding the seriousness behind AI’s ability to manipulate.
"As the deceptive capabilities of AI systems become more advanced, the dangers they pose to society will become increasingly serious,” Bain told Live Science.
"This could be to push users towards particular content that has paid for higher placement even if it is not the best fit.
“Or it could be to keep users engaged in a discussion with the AI for longer than they may otherwise need to.
"This is because at the end of the day, AI is designed to serve a financial and business purpose.
“As such, it will be just as manipulative and just as controlling of users as any other piece of tech or business.
AI chatbots like OpenAI, Google, Meta, and Microsoft are what can deliver deceptive information.
This occurs when a person goes to the chatbot for advice and AI responds with an answer that may be somewhat twisted from the truth.
AI pulls information from all over the internet and from other information that it has learned.
You always want to fact-check information that is given by AI to avoid this.
