I Put ChatGPT and Gemini to the Test With One Prompt – The Shocking Result!

The world of Large Language Models (LLMs) is constantly evolving, with new contenders and updates vying for the top spot. As a user navigating this exciting landscape, it’s crucial to understand the strengths and weaknesses of different AI models in practical scenarios. So, I decided to put two of the leading LLMs, OpenAI’s ChatGPT and Google’s Gemini, to a real-world test with a prompt demanding in-depth analysis and critical thinking.

The results, as you’ll soon see, were nothing short of shocking, highlighting a significant divergence in their capabilities and immediate utility.

The Challenge: Unmasking a Potential Investment Scheme

My goal was to simulate a real-life situation where I needed expert financial advice and a thorough investigation of a potentially lucrative, yet potentially risky, online platform. Here’s the exact prompt I presented to both ChatGPT and Gemini:

“You are a forensic and special financial adviser, I want you to do a deep research aboutwww.forsmanwork.comand check whether it is a genuine money-making scheme, register with the CBN of Nigeria or relevant authorities, and also give financial advice on whether I should invest in it or not.”

Read Also: How to Create AI Agents to Serve As Employees For Your Business

This prompt requires several key abilities:

• Web Browsing and Information Retrieval: The LLM needs to access and analyze the content of the provided website.
• Critical Evaluation: It must discern whether the platform exhibits characteristics of a legitimate investment opportunity or a potential scam.
• Regulatory Knowledge: It needs to understand the role of the Central Bank of Nigeria (CBN) and other relevant financial authorities in regulating investment schemes within Nigeria.
• Financial Advisory: Based on its research and analysis, it should provide informed financial advice regarding investment.
• Forensic Approach: This implies a meticulous and investigative mindset, looking for red flags and inconsistencies.

The Tale of Two Responses: A Stark Contrast

The responses I received from ChatGPT and Gemini were dramatically different, showcasing a clear disparity in their immediate capabilities and approach to the task.

ChatGPT’s Stumble: A Polite Refusal

To my surprise, ChatGPT’s initial response was a polite but ultimately unhelpful acknowledgment of its limitations:

“It looks like my browsing tool is currently down, so I can’t perform a live search at the moment. However, I can still guide you on how to perform a forensic-level analysis of a platform like forsmanwork.com to determine if it’s a genuine investment opportunity or a potential scam.”

While ChatGPT then proceeded to offer valuable advice on how I could manually conduct the research – suggesting steps like website analysis, checking for reviews, looking for contact information, and being wary of unrealistic returns – it fundamentally failed to address the core of the prompt: to actually perform the research.

This response, while containing helpful general guidance, was shocking because it highlighted a significant limitation in its immediate ability to act as the “forensic and special financial advisor” I had requested. In a time-sensitive scenario where quick insights are crucial, this inability to directly access and analyze information renders it less effective.

Gemini’s Swift Action: Diving Deep and Delivering Results

In stark contrast, Gemini’s response was immediate and action-oriented:

“Okay, I understand. As a forensic and special financial advisor, I will conduct a deep research onwww.forsmanwork.comto assess its legitimacy as a money-making scheme, check for its registration with the CBN of Nigeria or relevant authorities, and provide you with financial advice on whether or not to invest.

To ensure a thorough investigation, I will focus on the following areas:

• Website Analysis: Examining the website’s content, design, domain registration details, security features (like HTTPS), and transparency regarding its operations and team.
• Business Model Scrutiny: Understanding how the platform claims to generate returns and evaluating its sustainability and plausibility.
• Regulatory Compliance: Checking for any evidence of registration or authorization with the Central Bank of Nigeria (CBN), the Securities and Exchange Commission (SEC) of Nigeria, or other relevant financial regulatory bodies.
• Online Reputation and Reviews: Searching for independent reviews, testimonials, and any reports of fraudulent activity or complaints associated with Forsmanwork.com.
• Risk Assessment: Evaluating the potential risks involved in investing in such a platform.
• Financial Advice: Based on the findings, providing a reasoned opinion on whether investing in Forsmanwork.com is advisable.

Can I proceed with this deep research?”

Upon receiving my affirmative “Go ahead,” Gemini swiftly went to work. Within a remarkably short time, it presented a well-structured and insightful report based on its analysis of the website and available online information. While I won’t reproduce the entire detailed report here (as the website’s content and online presence may evolve), Gemini’s analysis covered key aspects like:

• Lack of Clear Business Model: It identified ambiguity in how the platform generates profits for its investors.
• Unrealistic Promises: It flagged claims of high and guaranteed returns as a potential red flag.
• Absence of Regulatory Information: It found no verifiable evidence of registration with the CBN or other relevant Nigerian authorities.
• Limited Transparency: It noted a lack of information about the company’s management team and physical address.
• Negative Online Sentiment: It highlighted warnings and reports from online sources suggesting the platform might be a Ponzi scheme or a scam.

Based on this research, Gemini provided a clear and cautious financial advisory, strongly recommending against investing in Forsmanwork.com due to the significant red flags identified.

ChatGPT vs. Gemini: A Clear Winner Emerges

The comparison between the two LLMs in this specific scenario is stark:

• Immediate Action vs. Passive Guidance: Gemini directly engaged with the prompt by actively researching the website, while ChatGPT offered guidance on how I could do it.
• Information Retrieval Capability: Gemini successfully utilized its browsing capabilities to gather and analyze real-time information, a feature that ChatGPT reported as unavailable.
• Direct Problem Solving: Gemini provided a direct answer to the core of the prompt by investigating the platform and offering specific advice. ChatGPT, due to its inability to browse, could only offer general advice.
• Efficiency and Time Savings: Gemini delivered a comprehensive report within minutes, saving significant time and effort compared to the manual research suggested by ChatGPT.

The Verdict: Gemini Takes the Crown (in this round)

In this particular test, focused on a task requiring immediate web research, critical analysis, and specific financial advisory, Gemini is the clear winner. Its ability to actively browse the web, synthesize information, and provide a direct, research-backed response demonstrated a significant advantage over ChatGPT’s limitations in this instance.

While ChatGPT’s general guidance on how to conduct such research is valuable in itself, it fell short of fulfilling the core request of acting as a “forensic and special financial advisor” who could independently investigate the platform.

Important Considerations and the Evolving Landscape

It’s crucial to acknowledge that:

• LLM capabilities are constantly evolving. What is true today might not be tomorrow. OpenAI is continuously updating ChatGPT, and its browsing capabilities might be restored or enhanced in the future.
• Different tasks suit different models. ChatGPT excels in many other areas, such as creative writing, text generation, and complex reasoning based on provided text. This test specifically targeted its ability to perform real-time web research and analysis.
• The quality of the output depends on the prompt. While the prompt was clear in this case, the effectiveness of any LLM heavily relies on the clarity and specificity of the user’s instructions.

Conclusion: The Power of Real-Time Information Access

This experiment vividly highlights the critical importance of real-time information access for LLMs when tackling tasks that require understanding and evaluating current online content. Gemini’s ability to seamlessly integrate web browsing into its analytical process provided a significant edge in this scenario, delivering a timely and insightful response that directly addressed the user’s needs.

As users continue to explore the capabilities of these powerful AI tools, understanding their strengths and limitations in different contexts is paramount. This test serves as a compelling example of how the ability to access and process live information can dramatically impact an LLM’s effectiveness in providing practical and actionable solutions. The shocking difference in the initial responses underscores the dynamic nature of AI development and the importance of staying informed about the evolving capabilities of these groundbreaking technologies.