Technology

An analysis of traditional search paradigms and a framework for integrating AI capabilities into content discovery platforms. The Content Discovery Challenge Traditional search paradigms face fundamental limitations in today’s information-rich environment. Users often struggle to articulate their information needs precisely, leading to iterative query refinement and incomplete discovery. Current search systems prioritize keyword matching over intent understanding, resulting in high precision for specific queries but poor recall for exploratory or contextual searches. ...

The Evolution of AI Value The first wave of generative AI focused primarily on content creation - ChatGPT writing articles, Midjourney generating images, essentially replacing traditional production roles. However, as these technologies mature, their greatest value might well shift towards distribution and personalization rather than raw production. From RSS to Recommender Systems The evolution of content distribution reveals how technology repeatedly transforms information access. RSS (Really Simple Syndication) represented an early attempt to solve content discovery, providing a pull-based system where users subscribed to feeds they cared about. ...

Here’s a list of articles that I founding interesting. I’ve attached the original article / transcript for easy refernece as well. Gary Tan on Manus: The New General-Purpose AI Agent Video URL: https://www.youtube.com/watch?v=JOYSDqJdiro Usable AI agents are finally here from deep research platforms out of OpenAI and Google to similar tools from XAI and DeepSeek. Joining the competition now is Manus, a brand new agentic AI platform that has taken the world by storm. ...

Hayao Miyazaki is my favorite artist and director. Though I haven’t watched his entire filmography, every moment of the films I have seen captivates me. In “Spirited Away,” the dust ball creatures exemplify his artistic prowess—his ability to infuse life into the mundane through his drawings. His work is truly a labor of love. Every scene in his animated films is hand-drawn and painted with watercolor. To put this dedication in perspective: a single 4 second crowd scene from Studio Ghibli required 1 year and 3 months to complete. At 24 frames per second, that’s 96 images—roughly 6.4 images per month or one-third of an image in an eight-hour workday. At this rate, animators would spend a decade creating just 28.8 seconds of footage. This extraordinary commitment to craft has established Miyazaki’s work as iconic for decades. ...

The Smart Expense Tracker with Auto-Categorization is a cloud-native application built on AWS serverless architecture. The system automates the tedious process of expense tracking by leveraging AWS services to process receipts, categorize transactions, and provide financial insights. The application offers several key features including receipt scanning and data extraction using AWS Textract, automatic expense categorization with AI (using AWS Bedrock), comprehensive expense tracking, budget setting with automated alerts via SNS, and financial report generation in CSV or PDF formats. ...

Authors: Terry Chen, Kaiwen Che, Matthew Song Abstract Despite advances in large language model (LLM) capability, their fundamental limitation of not being able to store context over long-lived interactions persists. In this paper, a novel human-inspired three-tiered memory architecture is presented that addresses these limitations through biomimetic design principles rooted in cognitive science. Our approach aligns the human working memory with the LLM context window, episodic memory with vector stores of experience-based knowledge, and semantic memory with structured knowledge triplets. ...

Advised by Prof. Kristian Hammond. Developed LLM product that analyzes real-time audio conversations, detects relevancy and misconceptions, and provides targeted Socratic questions and material suggestions through RAG. Groupal aims to help students work together more effectively and build a deeper understanding in study sessions. The project’s goal is to create a virtual learning assistant that listens to real-time student discussions, detects misconceptions, and facilitates discussions through Socratic questioning techniques and relevant background knowledge retrieval. ...

PepTalk: AI Journaling Tool Realtime conversation with aI companion to help you note down feelings and journals for the day. (Prototype: https://peptalk-navy.web.app/) What2Do: AI Trip Planning Tool A trip planning tool for generating itinearies based on article url input and content extraction. (Prototype: what2do-51224.web.app) OHours: Office Hour Scheduling Tool An office hour queuing system to improve student experience and help TAs manage questions more efficiently. (Prototype: ohours.web.app/) Credits: Lian Zhang, Janna Lee, Soham Shah, Jonny Kong ...

Exploring Unknown Unknowns: The Future of Knowledge Interfaces We live in an age of information abundance, yet many of us struggle with two fundamental learning challenges: we don’t know what to read, and we don’t understand what we’ve read. These pain points—“not knowing how to choose” and “not knowing how to comprehend”—represent a massive opportunity for reimagining how we interact with knowledge. The core insight driving next-generation learning interfaces is simple but profound: most people don’t know what they don’t know. We can’t formulate good questions about topics we’re unfamiliar with, yet traditional learning systems expect us to do exactly that. This creates a barrier that conversational AI can uniquely solve by flipping the interaction model entirely. ...

In the rapidly evolving landscape of artificial intelligence, we’re witnessing a fundamental shift in how we consume and interact with knowledge. While early AI applications focused primarily on content summarization and modal conversion, the next generation of AI-native products promises something far more transformative: the ability to create truly personalized learning experiences that adapt to individual needs, interests, and cognitive patterns. The Limitations of Current Approaches Today’s AI content tools largely excel at taking existing information and reformatting it into different modalities. We can convert text to audio, create video summaries, or generate podcast-style conversations from written material. However, as Large Language Model context windows continue to expand, simple content summarization becomes increasingly commoditized. The real value lies not in these mechanical transformations, but in the creative synthesis and novel perspectives that emerge when AI systems understand both the content and the consumer. ...