Inspiration
Exposé was developed in response to the growing issue of misinformation online, aiming to provide users with reliable tools for evaluating news content.
What it does
Exposé analyzes news articles and images for misinformation, bias, and AI generation, offering users reliability scores and detailed insights to support informed decision-making.
How we built it
We built Exposé using React for the frontend, Supabase for backend services and authentication, and OpenAI's GPT-4 models for content & image analysis, with Tailwind CSS for styling.
Challenges we ran into
We encountered challenges in ensuring accurate content analysis. Our program was extremely inconsistent and buggy in the initial stages.
Accomplishments that we're proud of
We successfully created a platform that effectively combines AI analysis with a user-friendly experience, including a chrome browser extension for easy access.
What we learned
We gained insights into the complexities of integrating AI models into web applications. We also learnt many things on bug fixes and framework design.
What's next for Exposé
Moving forward, we plan to refine our AI analysis algorithm by incorporating other LLMs, and using a larger and more robust database for storage.
Built With
- css
- html
- javascript
- node.js
- npm
- openai
- postgresql
- react
- rest
- supabase
- tailwind
- typescript
- vercel
- vite
Log in or sign up for Devpost to join the conversation.