When second-year computer science major Alexzendor Misra first came to UC Santa Barbara in Fall Quarter 2022, he had no idea an ill-fated encounter with a conspiracy-believing peer would inspire the creation of an artificial intelligence search engine, Correkt. 

Merely two months into college, Misra began a project that he hopes can truly change the ethics of artificial intelligence (AI) chatbots. 

Now, Misra and his team, consisting of first-year statistics and data science major Andre Braga, first-year computer science major Ryan Hung, first-year statistics and data science major Chan Park, first-year computer engineering major Khilan Surapaneni and second-year computer science majors Noah Wang and Ramon Wang, are ready to showcase the outcome of their project. They are preparing themselves to present their product, Correkt, an AI search engine, to the UCSB community at the AI Community of Practice (CoP) Spring Symposium on May 20. 

Correkt is not so different from ChatGPT — in fact, what ChatGPT does, Correkt can do too. Yet, Correkt aims to solve one critical issue with ChatGPT: misinformation. 

It is known that ChatGPT is prone to “hallucinations,” and according to IBM, it refers to the generation of false information due to the AI software’s misinterpretation of patterns or objects. Correkt is designed to prevent these instances of misinformation dissemination in two ways. 

Correkt is linked solely to reputable data sources — newspapers, textbooks and peer-reviewed journals. The AI model currently draws its information from an expansive data bank of over 180 million well-established, trustworthy resources — a number set to grow with time. This greatly lowers the risk of receiving inaccurate information by eliminating unreliable sources. However, it still does not give users the freedom to verify the information they access.

This is where Correkt truly sets itself apart from pre-existing AI chatbots: it includes a built-in citation function that details the precise location where every piece of information it presents to the user was retrieved. Essentially, Correkt is a hybrid between a search engine and an AI chatbot. The citation function allows users to judge for themselves the accuracy and validity of the information they receive as they would when conducting research through a search engine. The difference would be that the results will be much more streamlined with the support of AI. 

“[Correkt] has so much more value as a way to find information, like a new generation of [a] search engine,” Misra comments enthusiastically. 

Looking back, Misra recalls how the initial idea of building a fact-checking software had come to him in November 2022. 

During his first year, Misra was shocked to discover that one of his peers’ worldview was deeply impacted by the many inaccurate conspiracy theories they believed in. After much contemplation, Misra identified the power of misinformation to lead people to become brainwashed in such a way. 

“That sort of misinformation, that sort of brainwashing happens when sources of information that you consider trustworthy become polluted,” he shares. Examining the immense impact of AI chatbots only two years after their release, Misra foresees that it will only be a matter of time until AI becomes a main source of information for people. Paired with the hallucinating nature of AI chatbots, this could lead to a particularly dangerous era of information misalignment.

Hence, when an opportunity unveiled itself at the club Data Science UCSB to pitch an innovative project for a club-wide competition, Misra did not hesitate to gather a group of like-minded individuals to find a potential solution to the problem of AI misinformation. Though he had initially incentivized his teammates to pursue the project with the competition and a good mark on a resume, he was delighted to discover that his team unanimously supported his ambition of continuing the project beyond Data Science UCSB’s activities. 

By the time the competition ended in the Spring Quarter 2023, the team had completed basic information software that they excitedly presented to those around them. Although the project had not started out intending to create a product for the average person to use, Misra’s team was quick to recognize its potential to be of help to the general public. 

With this in mind, over the summer, the team of engineers began reaching out to more potential users to test their software, which led them to focus on creating a fact-checking AI catered to the needs of college students. 

The past year for Misra and his team has been one of discovery and dedication. As young college students who are still in the process of gaining the knowledge and the experience required to accomplish a great feat, they took it upon themselves to seek out mentors and learning opportunities along the way. 

Their hard work paid off when they launched their website, Correkt.ai, on April 25 and received positive feedback from close family and friends. The success of their startup can also be observed from the 5,000 users they have been able to reach organically within this short time. 

The group has now entered a new phase of their project; their attention is directed towards marketing and promoting Correkt.ai, and the upcoming AI CoP Spring Symposium could be helpful with this. The engineers behind Correkt will present their project at 3 p.m. on May 20 at an online panel that all UCSB students and faculty are able to register for. They are hoping to grow their users and attract potential investors with this presentation. 

Finally, Misra and his teammates emphasize their goal of adapting AI to advocate for more ethical usage of information.

“Transparency is the number one priority for AI ethics and credibility,” says Park, one of the engineers who has worked alongside Misra since Fall Quarter 2023. 

The Pandora’s box to an era of AI information has been opened, and projects like “Correkt” give hope that this complex balance between technological advancement and ethics can be navigated.