Vladimir Ivanov

Re­ward Hack­ing Without Egre­gious Misal­ign­ment in an RL-Only Setting

We Should Study the Anal­ogy Between Inoc­u­la­tion Prompt­ing Non-Ro­bust­ness, Ne­ga­tion Ne­glect, and Back­door Non-Robustness

De­bunk­ing claims about sub­quadratic attention

iva’s Shortform

A Dilemma in AI Suffer­ing/​Happiness