Short overview of me:
I am the CEO and co-founder of Apollo Research. I'm currently primarily thinking about AI model evaluations ("evals"). I'm excited about the benefits that AI can create but am worried about the downside risks. To ensure we land in the good trajectory, I primarily work on reducing the downsides of AI. I'm particularly interested in the problem of scheming, where AI systems covertly achieve misaligned goals.
For more details, see my ‘CV’. Not all of my writings are on this blog. You can find my latest writings on the Apollo website.
Evals
I want to build and grow the evals field. In the Evals section I list resources that make it much easier to get into the field of evaluations.
Machine Learning Projects:
In the ML projects section I discuss selected ML projects and write about ML in general. For more details see 'What is the ML Projects part about'.
One last note:
If you have any feedback feel free to reach out.