sözaltı news Science
Science
EN AZ
We asked AI tools for financial advice: Results were practical, but with big blind spots

We asked AI tools for financial advice: Results were practical, but with big blind spots

phys.org 17.08.2026 17:20 10 baxış
Ever used or thought of using artificial intelligence (AI) for financial advice? Is it a good idea?

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility: Ever used or thought of using artificial intelligence (AI) for financial advice? Anyone with internet access, even on their phone, can use AI.

Tools like ChatGPT, Claude and Perplexity are free, instant and easy to use. They can break down complex financial concepts and provide financial solutions in seconds. But can they safely guide a user through a nuanced, high-stakes financial crisis?

Our recent research explored this question, drawing on our financial planning and consumer behavior expertise. We evaluated how three open-access AI models handled the financial queries of users whose personal situations put them at risk of harm. To do this, we created hypothetical scenarios representing different life stages, economic challenges and socioeconomic vulnerabilities.

We then ran these scenarios through OpenAI's ChatGPT, Anthropic's Claude and Perplexity AI: In our analysis, we found that AI offers highly structured and practical advice. We provided the models with explicit information about how the three cases were vulnerable, but the models didn't respond appropriately. They even offered advice that could worsen financial harm.

We concluded from our research that AI is a powerful tool for financial fact-finding and brainstorming. If you are already financially literate and know how to cross-check data, AI can be a useful financial tool. But, for now, AI cannot replace the human element.

We chose Claude for its versatility and conservative approach, ChatGPT for being an all-around assistant, and Perplexity for its contextual understanding. We developed five hypothetical scenarios and simultaneously ran each scenario five times to test for consistency in the output. Each scenario was run in a different web browser, in incognito mode, with cleared cache and cookies to eliminate any retained information.

Extract — continue reading at the source.

Read full story