Experience

Alignment Research Center

• Research
• 1 - 100 Employee

• Machine Learning Researcher

  • Jan 2023 - Present

  I work on the ARC evals team evaluating the capabilities and safety of machine learning systems, trying to reduce worst-case risks from future models. I work on the ARC evals team evaluating the capabilities and safety of machine learning systems, trying to reduce worst-case risks from future models.



Center on Long-Term Risk

• United Kingdom
• Research Services
• 1 - 100 Employee

• Summer Research Fellow

  • Jun 2022 - Aug 2022

  Built a quantitative model of AI risk and different forms of safety work, which can be used to assess relative neglectedness, tractability and overall impact of different AI interventions. Supervised by Daniel Kokotajlo. Built a quantitative model of AI risk and different forms of safety work, which can be used to assess relative neglectedness, tractability and overall impact of different AI interventions. Supervised by Daniel Kokotajlo.



Future of Humanity Institute (Oxford University)

• United Kingdom
• Research
• 1 - 100 Employee

• Summer Research Fellow

  • Jul 2019 - Sep 2019

  Mentored by researchers at Oxford’s Future of Humanity Institute (Eliana Lorch and Owen Cotton-Barratt), I performed independent research into the role of ‘agency’ in conceptions of risks in AI systems. I gave a well-received final presentation disambiguating different notions of agency and how they relate to common arguments for risk. Mentored by researchers at Oxford’s Future of Humanity Institute (Eliana Lorch and Owen Cotton-Barratt), I performed independent research into the role of ‘agency’ in conceptions of risks in AI systems. I gave a well-received final presentation disambiguating different notions of agency and how they relate to common arguments for risk.



Machine Intelligence Research Institute

• United States
• Research Services
• 1 - 100 Employee

• Summer Fellow

  • Aug 2019 - Aug 2019

  I participated in the Machine Intelligence Research Institute’s competitive summer fellows program in August 2019 on beneficial AI development, and wrote a blog post reframing the alignment problem. I participated in the Machine Intelligence Research Institute’s competitive summer fellows program in August 2019 on beneficial AI development, and wrote a blog post reframing the alignment problem.