Welcome to my blog, a space dedicated to documenting my thoughts, ideas, and progress in AI research. This blog is primarily a personal endeavor—a way to organize my work, clarify my thinking, and track my journey in this rapidly evolving field. While most posts will center on topics like mechanistic interpretability, you may occasionally find posts on other subjects that capture my interest. My goal is to keep this blog flexible, serving both as a record of my progress and a platform for exploring ideas.

A Few Things to Note

First off, I want to set some expectations (or lack thereof):

  • I’ll probably get help from LLMs. Yes, I’m a researcher in LLMs, and yes, I’ll absolutely use them to help me draft or refine these posts. It feels fitting, doesn’t it? That said, I’ll make sure the final content reflects my own thoughts and voice.
  • I may not post regularly. This blog is more of a personal experiment than a commitment. Some weeks might have multiple posts, while others might have none. It all depends on how much inspiration (and free time) I have.
  • This is a learning tool for me. Writing helps me clarify my ideas and track my progress over time. Even if no one else reads this blog, I think it’s an invaluable way to document my journey.

Why Start a Blog?

I’ve always found writing to be an incredibly powerful way to organize my thoughts. As someone working in the fast-paced world of AI research, it’s easy to get lost in the constant stream of papers, experiments, and projects. This blog is my attempt to slow things down, reflect on what I’m learning, and share those insights with anyone who might find them useful. Plus, I think it’s important to have a record of where I started and how far I’ve come.

What You Can Expect

Here’s a rough idea of what you might find here:

  • Posts about LLM interpretability—how we can better understand the inner workings of large language models
  • Discussions on AI safety—exploring ways to ensure AI systems are ethical and aligned with human values
  • Updates on my research projects and collaborations
  • Deep dives into technical topics or papers that excite me
  • Explorations into computational neuroscience, as I’ve recently developed a strong interest in understanding the intersection of AI and biological intelligence
  • Random musings about science, technology, or whatever else captures my attention

In short: expect a mix of structured posts about my research interests and spontaneous reflections on whatever’s on my mind.

Let’s See Where This Goes

I don’t know how often I’ll post or how this blog will evolve over time—but that’s part of the fun! For now, it’s just me putting my thoughts out there and seeing where it takes me.

If you’re reading this—thank you! Feel free to reach out if you have any thoughts or questions about what I write here.

Until next time,
Jun