Skip to main content

A first look at ChatGPT's new web search

What happens when you ask AI to describe something it doesn't know? Hallucinations. That’s what I found when I asked the old version of ChatGPT about inkubatour.ch. Then, I tried the latest version—with augmented Web search. The result? Accurate, timely, and real.



This morning I run an experiment with ChatGPT's new Web Search functionality. First I asked the prior version to describe our inkubatour.ch program. Here is the original information on the Web: 

I kept it simple, typing: "Write an extended description of the inkubatour.ch program." intor the o1-preview version of ChatGPT. And then I watched as it produced a response that was mostly incorrect. Instead of giving me a straightforward, factual description, the AI dove into an elaborate story about entrepreneurship, mentorship, and workshops—all with colorful but largely fictional details. It was a hallucination, a well-crafted collection of non-existent facts. I couldn't help but laugh: 

In the meantime, I had gained access to the new ChatGPT — the one equipped with Web search capabilities. 

So, I asked again: "Write an extended description of the inkubatour.ch program." 

This time, it was different. Instead of weaving a web of misinformation, the AI provided an accurate, detailed description of the program. The response was filled with precise information about the Inkubatour initiative—its goals, its activities, and how it helps local tourism businesses grow through innovative ideas and support. The details were spot on, sourced directly from the actual inkubatour.ch and seco.admin.ch website and reliable references:

It was a moment that left me a little bluffed. The difference between these two interactions was not just striking—it demonstrated another milestone in the evolution of AI and its interaction with the vast ocean of information that is the Web.

The Power of Web-Augmented AI

Non-web-connected versions of chats —as impressive as it can be—has limitations when it comes to the most up-to-date or niche information. Without real-time data, it's like an encyclopedia from 2021, 2022 or 2023 —rich with general knowledge but lacking in current or specific details.

The new Web-augmented version of ChatGPT changes the game. When I tried the same prompt, I wasn't simply interacting with a language model trained on past data—I was interacting with an AI that could actively search, interpret, and deliver precise, up-to-date information. 

The potential of this leap in AI technology is enormous. Imagine you’re a business owner trying to gather insights about the latest market trends—now, you can ask an AI that doesn't just rely on static knowledge but can also gather fresh information from the Web, offering you data-driven insights in real-time. Or think about students who need to research recent topics—instead of sifting through outdated data, they can have an AI assistant that can give them accurate and timely information instantly.

The experiment of asking ChatGPT about inkubatour.ch was a simple one, but the outcome revealed the profound impact of Web-augmented AI. This shift, from isolated AI to web-connected intelligence, brings us closer to a world where our digital assistants can truly keep pace with our curiosity and need for real-time information.

I can’t help but wonder: What’s next?

Popular posts from this blog

An Ethical Framework for Exams and Continuous Assessment with AI

Throughout the history of education, a multitude of diverse and even contentious methodologies have been employed to assess knowledge and aptitude. Several assessment methods have been employed, ranging from oral examinations to written tests, all with the overarching objective of discerning the extent to which students comprehend the subject matter in a manner that is equitable, comprehensive, and optimal. In the present context, amidst the cusp of a forthcoming epoch, the ongoing discourse persists, albeit with a futuristic inclination. The emergence of Artificial Intelligence (AI) has brought about transformative changes in the field of education, revolutionizing the tools and methodologies employed for assessment and evaluation. As we transition into this emerging era, it is crucial to discuss the implications for the fundamental principles and ideals of education. The conventional methods of assessment, commonly characterized by high-stakes examinations and standardized tests, ha

Rethinking Exams in the Age of Chatbots

Today's experiment explores the potential of ChatGPT to assist me in the realm of exams, particularly within my field of teaching, Business Analysis. Can ChatGPT create a question for an exam? Indeed, it can do even more! In the experiment below, ChatGPT showcases (to varying extents) its ability to not only generate an exam question but also to engage in several related tasks: Generate a difficult critical question Solve the question Critically evaluate the solution (its own solution!) Attribute a mark between 1 and 6 Attribute a severe mark between 1 and 6 Defend a mark Refute a mark Generate a variation of the question which is difficult to solve Generate a variation of the question which is even more difficult to solve Give a correction scale with marks from 1 to 6  The impact of AI and chatbots like ChatGPT impact on university exams is becoming increasingly evident. Students and teachers alike are beginning to discover these tools, questioning their potential to generate, cor

How to augment a Course with AI and Student Personas

As an educator in the field of business analysis, I've always sought innovative ways to enhance the learning experience for my students. My latest experiment (see below) into this endeavor involved leveraging ChatGPT to not only understand the learning process better but also to tailor it to individual student needs. Here's a glimpse into this fascinating journey. It began with identifying eight phases of a learning process with ChatGPT. These phases ranged from orientation to reflection and evaluation, encompassing the entire spectrum of a student's learning journey. The goal was to understand how students navigate through these phases and how they could be supported in each step. Building on these phases, I adapted them into a model for student personas . This involved considering various aspects of a student's academic life, personal characteristics, and learning styles. From this model, I created ten distinct student personas. Each persona represented a unique c