Hello friend. Welcome to my digital patch of land. Feel free to look around.
About Me
I do research on AI – mostly on how to train LLMs to be agents through Reinforcement Learning. At this moment, I believe that this is the most promising direction for bringing us closer to AGI.
I currently work on building a library for LLM-RL researchers that allows them to more easily do research. You can find it here.
Structure of the website
My website consists of two different kinds of web pages – posts and notes.
Posts
Posts are a snapshot of my current digested thoughts. As a rule, I do not retroactively change them, though I may add disclaimers or meta commentary. I attach an importance score and a confidence score from 1-10 to each post. I do this to make sure the reader knows how certain I am about what I write.
Latest posts
No posts published yet. I’ll write something worth your time eventually.
Notes
Notes can be thought of as living documents. Whenever I come across new information or feel like something is not accurate enough, I change them. I regularly cross-reference notes, as well as link to them in my posts. They do not follow a linear structure in time and instead are more like a knowledge base.