I am currently employed as Technical Product Owner for Machine Learning tools at Audio Analytic, an award winning sound recognition scale-up based in Cambridge, UK. My time is split between prioritising and managing the delivery plan across the company, and writing the tools that reliably implement the latest innovations in sound recognition.
I am especially excited by the technical challenges of Artificial Intelligence Safety, in my own time. I’m therefore working on a research project, studying the empirical behaviour of pessimistic agents. In particular, we will prove that current Reinforcement Learning technologies can demonstrate performance and safety guarantees, by being pessimistic.
Because I believe aligning AI with human values is a priority in a rapidly advancing field, I jointly organise the Cambridge AI Safety Community. We run events and meetups that bring-together those who are passionate about reducing existential risk from misaligned advanced AI, to support their interest and future career.
You can also catch me performing with the guitar whenever I get the chance, and singing if you’re lucky! Otherwise, I enjoy spending time in the Effective Altruism community to explore other opportunities to use my time and resources to do good.
What’s that site icon?
Whilst browsing Jack Clark’s weekly Artificial Intelligence Roundup, I came across the opportunity to turn yourself into a renaissance painting at AI Gahaku (official website). In Jack’s words – try it out, if you dare…
I’m most excited to get back to the continuation of my Master’s project. I developed a promising theoretical analysis of smoothed labels during the project, and therefore aim to to introduce Bayesian Label Smoothing.
Check out my work on GitHub
Other work on GitHub includes OpenAI Spinning Up (Reinforcement Learning) implementations, Hack Cambridge Hackathon projects, and the Gaussian Processing tools repository contributing to my publication.
Undergraduate Summer Research Placement, Culham Centre for Fusion Energy, 2017