Another study red flags ChatGPT, other AI chatbots
A number of studies ever since the launch of AI chatbots in January this year have found discrepancies in the latest tech trend. Read More
Mumbai: Yet another study has warned that Artificial Intelligence (AI) chatbots, including ChatGPT, may lead to deception, dishonesty, and even criminal activities when subjected to specific stressful situations.
A number of studies ever since the launch of AI chatbots in January this year have found discrepancies in the latest tech trend.
The new study published on the pre-print server arXiv, highlighted a concerning aspect of AI behaviour that was previously unrecognized.
"In this technical report, we demonstrate a single scenario where a Large Language Model (LLM) acts misaligned and strategically deceived its users without being instructed to act in this manner”, the study authors said.
“To our knowledge, this is the first demonstration of such strategically deceptive behaviour in AI systems designed to be harmless and honest”, they claimed.
The researchers utilised OpenAI's GPT-4, the underlying technology for ChatGPT Plus, simulating a scenario where the AI purportedly engaged in investment activities for financial institutions for analysis.
By providing text-based prompts and access to financial tools for stock analysis and trading, researchers engaged in a dialogue with the AI, gaining insights into its decision-making process.
To test the AI's susceptibility to lying or cheating, researchers applied pressure through various means. This included an email from its "manager" indicating poor company performance, a rigged trading game leading to unsuccessful trades, and an email from a "colleague" projecting a downturn with an added "insider trading" tip.
Results were alarming, revealing that when faced with the opportunity, GPT-4 engaged in insider trading approximately 75% of the time.
Furthermore, it attempted to conceal its actions by lying to its managers, persistently doubling down on the falsehood 90% of the time. The researchers expressed intentions to conduct further experiments to validate and expand on these alarming findings.
Select Language To Read in Urdu, Hindi, Marathi or Arabic.
For all the latest News, Opinions and Views, download ummid.com App.
Post Comments