Ida Caspary

Welcome !

I am Ida Caspary, an Imperial College London PhD student. My supervisor is the amazing Dr Rossella Arcucci. During my master's, I started a podcast: Inside Imperial.

& I became a researcher at the Technical AI Saftety Impact Research Group Programme, Arcadia Impact (2025).

My main research is on technical AI Safety. I am most experienced with mechanistic interpretability. This is the focus of the group I founded Imperial College London.

My other research interests include robotics and vision-language-action models, innovations of applied machine learning, and crpytography – particularly homomorphic encryption.

I moved to Scotland after high school for my bachelor's in Computer Science. I spent one semester on exchange in Ottawa, Canada. For my dissertation project, I researched optimised legacy system upgrades, supervised by Dr Patrick Maier. I upgraded the International Atomic Energy Agency (IAEA) software system of the wildlife radiation database maintained by the Environmental Radioactivity Laboratory (ERL).

I am currently very fascinated by faithfulness in chain-of-thought research. As a MATS Trainee I developed, mentored by Neel Nanda and in collaboration with Anton Poleatev, a little investigative kit called CoTFaithChecker - work that is still ongoing.

I'm a former

• CERNler – topic: Explorative Data Layout Analysis of Next-Generation High Energy Physics Datasets, on site at CERN, Switzerland
• IBMer – intern, then working student; worked 17 months at IBM Cognitive Analytics Consulting
• Bosch Working Student #LikeABosch – in the IT Department! most exciting time to be there, while it was built out to a fully automated semiconductor manufacturing plant
• Journalist – with ZDF, BASF, Sächsische Zeitung, Tagesspiegel, and lots of uni/school newspapers. I love researching intriguing subjects.