Hey :)

I'm Julian. I want to do the most good I can, so I work in AI safety. Right now I'm a generalist at Kairos.

In past lives, I ran the UToronto AI safety group and researched how agents cheat on ML tasks.

Outside of AI Safety, I have three great loves: brazilian jiu jitsu, partner dance, and talking with people / listening deeply.

You can give me anonymous feedback here. If you want to get in touch, my email is moncarz.julian@gmail.com.

I hope you have a lovely day!