April 28, 2025 - 06:14
Despite the hype surrounding artificial intelligence, recent evaluations reveal that some of the most prominent chatbots struggle significantly when it comes to providing sound financial advice. AI specialists Gary Smith, Valentina Liberman, and Isaac Warshaw from the Walter Bradley Center for Natural and Artificial Intelligence conducted a thorough assessment by posing a set of 12 finance-related questions to four major large language models: OpenAI's ChatGPT-4o, DeepSeek-V2, Elon Musk's Grok 3 Beta, and Google's Gemini 2.
The results were concerning, as the chatbots often provided responses that lacked accuracy and depth. Many of the answers failed to consider essential financial principles, leading to potentially misguided advice for users seeking reliable guidance. This raises questions about the readiness of AI technology to handle complex financial topics and the implications for users who may rely on these systems for critical financial decisions. As the landscape of AI continues to evolve, it is crucial for developers to address these shortcomings and enhance the financial literacy of chatbots.
