Launched by OpenAI at the beginning of December 2022, the arrival of ChatGPT has certainly grabbed the attention of the internet. Finally, an AI tool powerful enough to produce genuinely human-like speech patterns and answers to questions, made freely available for anyone to use. You will likely have seen numerous examples of the tool producing detailed answers, in a variety of forms, to even the most obscure questions.
But first of all, what is ChatGPT? Well, who better to ask than the tool itself? “I am an artificial intelligence designed to assist with a wide range of tasks and answer questions to the best of my ability. I was trained using a process called machine learning, which involves feeding a computer large amounts of data and using that data to improve the performance of certain tasks. I am able to understand and generate human-like text, and I can use that ability to help answer questions, provide information, and engage in conversation. I do not have my own thoughts or feelings, but I am programmed to try to understand and respond to the thoughts and feelings of the people I interact with.”
This is, unsurprisingly, an accurate and helpful response. There are limitations to the technology (which you can also ask it about), including the fact that its knowledge currently only goes as far as the end of 2021, so it can’t answer current questions. There have also been issues with it generating contentious responses, and the plausibility and confidence with which it provides answers is an issue when the answer is simply wrong. However, it has set a new benchmark for developing a human-like speech pattern in text: this is a far departure from the awkward, slow and robotic interactions you might have with an AI chatbot provided by your bank or energy provider today.
ChatGPT and the potential to disrupt search
The intrigue in all of this is the impact that it could have on traditional search engines. Through AI, ChatGPT is potentially able to do a far better job of understanding a query and the subtleties of the intent behind it, compared to something like Google. The call and response format when interacting with ChatGPT also allows more refined follow-ups: the user can challenge the answer provided or request elaboration, and ChatGPT can acknowledge a mistake or improve its answer.
Google’s dominance of the search engine market is very well-entrenched. The search engine responds to questions or prompts with links, including advertising links which serve to power its revenue. However, it is easy to imagine how ChatGPT could disrupt this. Instead of encouraging users to click on links to new websites, ChatGPT can simply provide succinct answers or clear explanations itself. This could completely change the way users interact with search engines – indeed, the whole ecosystem surrounding the search engine revenue model, and search engine optimisation, could be turned on its head. The potential for disruption is so great that, according to a New York Times article, senior figures at Google’s parent company Alphabet have declared a ‘code red’ to better understand the potential impact on Google and the wider search engine industry.
The race to adopt the new technology
Recent reports have suggested that Microsoft, a significant investor in OpenAI, plans to launch a version of its Bing search engine using the AI behind ChatGPT as early as this spring. Just how this integration will work is not yet clear – not least because ChatGPT’s knowledge base currently stops at the end of 2021 – but its ability to provide full answers in the style of human speech patterns could make the user experience friendlier than that of Google. In the future, if the technology can be proved viable and kept up-to-date, questions posed through Bing could be answered in compact sentences rather than a list of links that require further exploration (and are positioned according to advertisers’ demands).
Google has its own sophisticated AI capable of natural language processing in LaMDA (Language Model for Dialogue Applications), which made headlines in June 2022 when a Google engineer claimed it was sentient. However, Google is naturally hesitant to integrate the technology into its search engine: such an overhaul would have an impact on advertising revenue, and Google has far more reputational risk at stake than smaller players. ChatGPT has already been used for nefarious means, including to write malware and facilitate cyber attacks, but these are risks that a start-up can navigate, given that reputational damage is not as critical to them. Alphabet CEO Sundar Pichai has confirmed as much, noting that Google is acting “more conservatively than a small start-up” because of the “reputational risk” posed by the technology.
What lies ahead for ChatGPT and search?
While internet search engines have evolved since Google’s launch in 1998, with results becoming more personalised and algorithms and advertising models more sophisticated, their overall functionality has changed surprisingly little in 25 years. The arrival of ChatGPT could herald one of the most significant moments in the evolution of internet search engines, and it will be intriguing to see both how the technology is developed and integrated over the coming months, and how tech giants and start-ups respond.
I will leave the final words to ChatGPT, in response to the query, “How are you going to change the search engine landscape?”:
“As an AI language model, I don’t have the ability to change the search engine landscape on my own. However, my creators at OpenAI may be working on ways to integrate my capabilities into search engines to improve the search experience for users. This could include providing more accurate and relevant results, as well as being able to understand and respond to natural language queries in a more human-like way. But this is just a speculation and not confirmed by OpenAI.”
Privacy Policy.
Revoke consent.
© Digitalis Media Ltd. Privacy Policy.
Digitalis
We firmly believe that the internet should be available and accessible to anyone, and are committed to providing a website that is accessible to the widest possible audience, regardless of circumstance and ability.
To fulfill this, we aim to adhere as strictly as possible to the World Wide Web Consortium’s (W3C) Web Content Accessibility Guidelines 2.1 (WCAG 2.1) at the AA level. These guidelines explain how to make web content accessible to people with a wide array of disabilities. Complying with those guidelines helps us ensure that the website is accessible to all people: blind people, people with motor impairments, visual impairment, cognitive disabilities, and more.
This website utilizes various technologies that are meant to make it as accessible as possible at all times. We utilize an accessibility interface that allows persons with specific disabilities to adjust the website’s UI (user interface) and design it to their personal needs.
Additionally, the website utilizes an AI-based application that runs in the background and optimizes its accessibility level constantly. This application remediates the website’s HTML, adapts Its functionality and behavior for screen-readers used by the blind users, and for keyboard functions used by individuals with motor impairments.
If you’ve found a malfunction or have ideas for improvement, we’ll be happy to hear from you. You can reach out to the website’s operators by using the following email webrequests@digitalis.com
Our website implements the ARIA attributes (Accessible Rich Internet Applications) technique, alongside various different behavioral changes, to ensure blind users visiting with screen-readers are able to read, comprehend, and enjoy the website’s functions. As soon as a user with a screen-reader enters your site, they immediately receive a prompt to enter the Screen-Reader Profile so they can browse and operate your site effectively. Here’s how our website covers some of the most important screen-reader requirements, alongside console screenshots of code examples:
Screen-reader optimization: we run a background process that learns the website’s components from top to bottom, to ensure ongoing compliance even when updating the website. In this process, we provide screen-readers with meaningful data using the ARIA set of attributes. For example, we provide accurate form labels; descriptions for actionable icons (social media icons, search icons, cart icons, etc.); validation guidance for form inputs; element roles such as buttons, menus, modal dialogues (popups), and others. Additionally, the background process scans all of the website’s images and provides an accurate and meaningful image-object-recognition-based description as an ALT (alternate text) tag for images that are not described. It will also extract texts that are embedded within the image, using an OCR (optical character recognition) technology. To turn on screen-reader adjustments at any time, users need only to press the Alt+1 keyboard combination. Screen-reader users also get automatic announcements to turn the Screen-reader mode on as soon as they enter the website.
These adjustments are compatible with all popular screen readers, including JAWS and NVDA.
Keyboard navigation optimization: The background process also adjusts the website’s HTML, and adds various behaviors using JavaScript code to make the website operable by the keyboard. This includes the ability to navigate the website using the Tab and Shift+Tab keys, operate dropdowns with the arrow keys, close them with Esc, trigger buttons and links using the Enter key, navigate between radio and checkbox elements using the arrow keys, and fill them in with the Spacebar or Enter key.Additionally, keyboard users will find quick-navigation and content-skip menus, available at any time by clicking Alt+1, or as the first elements of the site while navigating with the keyboard. The background process also handles triggered popups by moving the keyboard focus towards them as soon as they appear, and not allow the focus drift outside of it.
Users can also use shortcuts such as “M” (menus), “H” (headings), “F” (forms), “B” (buttons), and “G” (graphics) to jump to specific elements.
We aim to support the widest array of browsers and assistive technologies as possible, so our users can choose the best fitting tools for them, with as few limitations as possible. Therefore, we have worked very hard to be able to support all major systems that comprise over 95% of the user market share including Google Chrome, Mozilla Firefox, Apple Safari, Opera and Microsoft Edge, JAWS and NVDA (screen readers), both for Windows and for MAC users.
Despite our very best efforts to allow anybody to adjust the website to their needs, there may still be pages or sections that are not fully accessible, are in the process of becoming accessible, or are lacking an adequate technological solution to make them accessible. Still, we are continually improving our accessibility, adding, updating and improving its options and features, and developing and adopting new technologies. All this is meant to reach the optimal level of accessibility, following technological advancements. For any assistance, please reach out to webrequests@digitalis.com