Our blog

AI Experiments
Exploring the Uncharted Limits of AI

To understand AI’s true capabilities, experimenting with the latest tools is essential. Hands-on testing reveals strengths and weaknesses more clearly.Take large language models (LLMs) as an example. They exhibit emergence—unexpected behaviors that even developers struggle to explain. Some abilities surpass current theories, leaving researchers puzzled.If developers find it hard to fully grasp LLMs, it’s even harder for others to assess them accurately. That’s why AI experiments are crucial—they provide a glimpse into the latest LLM capabilities.
AI Experiment

Exploring Manus AI: Revolutionizing Research with Autonomous AI Agents

In the age of rapidly advancing artificial intelligence, Manus AI stands out as a groundbreaking system, redefining how research and data analysis are conducted. Recently, we tested Manus AI's potential with two experiments: one analyzing the economic impact of tariffs on Hong Kong and another examining a significant market shift in the Hang Seng Index. These experiments showcased how an AI Assistant look like
AI Experiment

Pushing the Limits of AI: Reflections on Vibe Coding and a New Minigame Experiment

In the ever-evolving landscape of AI research and development, we’re continually seeking tools and methodologies that not only streamline processes but also amplify creativity. Today, I’d like to share some thoughts on the potentials and limitations of AI development tools, specifically through my recent experiment: creating a minigame called 《Mind Control Simulator》 using the Poe App Creator.