Rashad Aziz
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Depth-Conditioned Backdoors in Looped Language Models
According to the excerpt, Rashad Aziz shares initial results on training a backdoor in the Ouro-1.4B looped language model that depends on both a trigger and the number of loops completed. The post reports the backdoor persisting through at least 200 million tokens of safety training.