Inspiration
What really sparked our motivation to make this extension is the current situation where people on the internet have become numbers. Every day thousands are dying, starving, and suffering—some of them children. Yet the human eye has normalized these scenes. Scenes that, if we imagined our own friends and families going through, we would get up from our places leaving everything behind.
The "Add Image" functionality was included so people can see the little kids when they are reading about them, to see how they look and compare them to their own kids or siblings. Technology makes our lives easier, but that doesn’t mean it’s "better." This project is a desperate call to invite people to think and reflect thoroughly on what they are reading. Summarizing is never the purpose, as the human essence is so complex, and it’s unjust for it to be squished into a couple of sentences.
No matter how many pros this project has, if the user doesn’t have the will to know and learn, then this is just another "note taker" on the internet.
What it does
VIVE is a Chrome extension that uses prompt and summarizer APIs to provide meaningful interactions with online content. It enables users to engage with the human side of what they read by offering features like note-taking and displaying images alongside text. This dual approach helps bridge the emotional gap between written content and the reality it represents.
How we built it
We built VIVE using Chrome AI APIs, along with JavaScript, HTML, and CSS. These technologies were combined to create an intuitive and functional extension that integrates AI-powered summarization and rephrasing capabilities directly into the browser.
Challenges we ran into
During the development of this project, we faced several challenges, particularly with the APIs. Issues included unexpected deviations in outputs, inconsistencies in model performance (working at times and failing at others), and difficulties with the rewriter/writer API when dealing with larger text chunks. However, we were pleased with the results when using the Gemini API, which showed potential for reliability and quality with further improvements.
Accomplishments that we're proud of
We take pride in completing this project despite the many errors and obstacles we encountered. Overcoming these challenges and ultimately developing something innovative and original, after extensive brainstorming and refining ideas, has been rewarding. We are also proud of surviving the API's hurdles.
What we learned
Through this project, we learned a lot about the challenges of working with APIs, handling unexpected errors, and improving functionality step by step. We also figured out how to work better as a team, from coordinating tasks to sharing progress effectively. Designing something that’s easy to use and truly helpful taught us the value of putting ourselves in the user’s shoes while balancing technical goals.
What's next for Vive
For the future, we aim to refine the extension by improving API reliability, enhancing error handling, and optimizing the tool for larger inputs. We also plan to explore additional features to make VIVE even more engaging and reflective.
Log in or sign up for Devpost to join the conversation.