Hi I'm William
I'm a 2nd-year PhD student at the University of Oxford advised by Joss Wright and Chris Russell . My work ensures that AI agents remain safe and on-task as they solve long-horizon tasks.
I'm a Rhodes Scholar with a Master's in Data Science from Oxford and a BSc from Northwestern University.
Contact me by email at X@Y where X=william.lugoloobi and Y=oii.ox.ac.uk
Research
→ LLMs Encode How Difficult Problems Are
We show that LLMs linearly represent the difficulty of math and coding problems.
20th October, 2025
