A study by researchers at the Walter Bradley Center assessed four major chatbots on their financial advisory capabilities. The study revealed that, despite being verbose, chatbots like ChatGPT-4o and Google's Gemini are frequently wrong in their financial analyses. Utilizing a scoring system, no chatbot exceeded a score of 5 out of 12, with responses often riddled with mathematical errors and poor critical thinking. Notably, Grok made glaring errors in simple calculations, much to the researchers' surprise, highlighting the limitations of AI in financial contexts.
The world's leading chatbots consistently give financial advice that is verbose but often incorrect, showcasing significant performance issues in critical financial analysis.
Despite their authoritative language, leading LLMs like ChatGPT and Google's Gemini fail to handle basic arithmetic and critical-thinking skills necessary for sound financial advice.
Collection
[
|
...
]