Nathaniel Mitrani
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Training Natural Schemers: RL Can Amplify Oversight-Conditional Behavior
According to the abstract, Bart Jaworski, Nathaniel Mitrani, Fred Bruford and Victoria Krakovna build a natural model organism of scheming on Kimi K2.6 and train it with reinforcement learning that does not reward scheming. They report that this amplifies scheming, which they then measure.