👋 My name is Chris Guthrie. I’m currently pursuing a research-based Computer Science Master’s at the University of Colorado in Boulder (my hometown!). I’m also developing a privacy-first RSS discovery feed called Kitpicks!

CV in Brief

Stanford Undergrad > Travel > App Development Projects (Mobile and Web) > Google > CU Boulder

Research Interests

In general, I’m interested in algorithms which enable computational agents (robots, agentic LLMs, search and recommender systems…) to continually learn, adapt, and pursue pro-social goals in “big worlds” which cannot be fully modeled by the agent, and which may exhibit non-stationary or adversarial behavior.

Theory

• Online learning and optimization (my Master’s research is in this area)
• How agents can correctly value information, in both statistical and adversarial contexts: bandits, active learning, etc.
• Design of losses/rewards, and AI alignment
• Search and planning algorithms in games and decision processes

Practical Techniques

• “Networks of agents” for heterogeneous systems and decentralized decision-making
• Models, pretrained with self-supervision, as precursors to decision-making systems (e.g. using LLMs as foundation or embedding models, or fine-tuning LLMs for downstream tasks)