Why counting refusals can miss how a model steers an answer
A research preprint separates detecting a sensitive concept from choosing a response. It suggests a broader way to read claims about uncensored AI.
Model Behavior
Refusals, alignment and what evaluations can actually tell us.
2 stories
Refusal removal can change more than refusals, a preprint reports
A July research preprint examines changes in decision behavior after abliteration. Its narrow experiment raises a wider question about model modifications.