Blog & Talks
-
Essential vs Accidental Difficulty: Programming with LLMs for Process, Not Output
There's a right way and a wrong way to code with LLMs. Fixate on the output and you lose your grip on your codebase's internals. Here's how to use LLMs to stay in control.
-
My Ph.D. was Pointless, Noisy, and Exploitative–and I would do it again.
A systems-level look at a California-based STEM Ph.D. An honest reflection on exploitation, noise, and uncertainty in academia—and why I'd still do it again.
-
[Video] Design Out Helplessness: AI Interventions for Game Inclusivity
My PhD dissertation defense on using AI techniques to make games more accessible and inclusive, covering diagnostic taxonomy of failure, dynamic tutorials, and reinforcement learning-powered assistance methods.
-
[Video] The Today and Tomorrow of Machine Learning in the Games Industry
An overview of how machine learning is currently used in the games industry and a survey of exciting research projects that may shape its future—from testing and matchmaking to procedural generation and co-creation tools.
-
Designer-centered reinforcement learning
Making RL more accessible to game designers through preference learning, automatic reward balancing, and designer-friendly workflows. Research conducted during my internship at Microsoft Research Cambridge.
-
So You Want to Get a PhD?
Things I wish I had known before starting my PhD. A guide for those considering the academic path, covering the decision, the search, and the application process.
Enter your email to get notified of new posts directly in your inbox