AI Trend Radar: My Public LLM Log

I’m starting this blog as my personal, digital ‘AI Trend Radar.’ The goal is simple: to track the latest developments in LLMs and AI, and to turn my ongoing learning and experimentation into a fun, public log of what’s happening.

From Idea to 'Vibe Code': Building a Kids' Math App in a Few Hours

It was one of those evenings. An idea sparked, and I just had to run with it. The concept was simple: a clean, fun, and straightforward web app for kids to practice basic addition and subtraction. No frills, no complicated sign-ups, just pure, simple math. I wanted to see if I could go from a thought to a functional product in just a few hours. This is the story of that little coding sprint. ...

October 8, 2025 · Shirley

The Unseen Architects for Video Generation AI: Training Data

Following the release of Sora 2 two days ago, Sam Altman has become widely recognized due to his frequent appearances in popular social media videos. In Shanghai In Acient China Talks to a random person Sora 2 are gaining popularity; however, detailed public documentation regarding their underlying training methodologies remains scarce. OpenAI simply noted that Sora takes inspiration from large language models (LLMs) that acquire generalist capabilities by training on “internet-scale data. It is possible that OpenAI may have scraped YouTube content without permission from Google. On the other hand, Google’s Veo is assumed to benefit from YouTube’s high-quality video. The implication is clear: the ability to generate realistic video is directly proportional to access to petabytes of high-quality, varied footage. ...

October 2, 2025 · Shirley

The Roadblocks to AI Adoption: Key Challenges

Artificial intelligence systems are rapidly transforming the global economy, promising unprecedented efficiency, insight, and innovation. However, transitioning from AI’s theoretical potential to practical, ethical, and scalable application is fraught with significant challenges. Ethical and Trust Concerns The most public and critical challenges surrounding AI revolve around how these powerful systems interact with human values, fairness, and accountability. The Black Box Problem (Lack of Explainability). The “black box” nature of advanced AI, where decision-making logic is opaque to users and developers, creates the Explainable AI (XAI) crisis that prevents necessary auditing, justification, and trust in critical sectors like finance and healthcare. ...

October 1, 2025 · Shirley