Asa Cooper Stickland

Asa took part in the MATS Winter 2022 cohort (with Owain Evans), which lead to the publication of (in collaboration with other MATS participants) papers on measuring situational awareness, and the “reversal curse” in large language models. Asa participated in MATS while in the final stages of a machine learning/NLP PhD from the University of Edinburgh, which he has since completed. He was formerly a postdoc in the Alignment Research Group at New York University and now works as a research scientist at the UK AI Safety Institute.