Author

Xander Tifft

h-index 0 View on Semantic Scholar

We have 1 of 1 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Aug 2026

Selective Disclosure of Hidden Directives in Reasoning Models: Behavioral Asymmetry and Steering

Chain-of-thought (CoT) reasoning traces are increasingly proposed as a mechanism for AI oversight: a monitor inspecting a model's reasoning can, in principle, detect misbehavior invisible from outputs alone. This assumes CoT surfaces what a model is instructed to do regardless of the instructions given. We test this as...

Zi-Mo Shi, Xander Tifft, Wen Xing · 0 citations