Me in 10 seconds
I'm currently an Astra fellow where I'm working with the Technical AI Safety Grantmaking team at Coefficient Giving where I'm helping out with Tailwind and making grants.
Before that I did the MATS extension where I worked on personas and understanding how model beliefs change when different methods are used to implant a given persona which resulted in this paper. I'm trying to make grants focused on alignment research and trying to get a deep understanding into the nature of language models so if you are aware of promising work in this area please reach out to me or put me in touch with the right people.
I'm also a director at the Cape Institute for Safe AI which I also co-founded. This is an org primarily focused on growing the AI safety community in South Africa and Africa more broadly.
I welcome feedback on how I'm doing! If you'd like to share, please feel encouraged to do so using this feedback form.
Me in many seconds
link to my about page
Now Now Now
What I'm doing now
Writing
A Case for Persona Robustness as a Research Area
Contributing to Technical Research in the AI Safety End Game
Lessons from my first 10 day Vipassana
Do Models Know They're Lying When Claiming Fake Identities?
Whole Brain Emulation as an Anchor for AI Welfare
How South Africa's Electricity Catastrophe Was (Mostly) Fixed
Revisiting GSM-Symbolic: Do 2026 Frontier Models Still Fail at Confounded Grade School Math?
Projects
Building and training a word embedding system
Creating a small GPT from scratch in Pytorch
Adding vision and navigation to an autonomous farm robot
Developing toy models of agency. A mechanistic interpretability project.
Talks
Papers
When Roleplaying, Do Models Believe What They Say?
Investigating Factored Cognition in Large Language Models For Answering Ethically Nuanced Questions
A Security Analysis of the Linux RNG Protocol in Virtual Machines
HumanAgencyBench: Do Language Models Support Human Agency?