Hello! I’m Ed. I currently work as a Software Engineer at Apollo Research where I build software for evaluations of LLM agents. I previously worked on the problem of faithfull chain-of-thought reasoning as an external contractor for Anthropic and as part of the SERI MATS programme.

Before getting into AI Safety I was a Senior Machine Learning Engineer at Speechmatics where I led a team working on representation learning in the audio domain. We think we have the best speech recognition in the world (you can try it out free here).

If you want to get in touch you can reach me at edward.r.rees[at]gmail.com.

Posts & Papers

Gaussian Processes - Interactive Demo