LodeHQ
AI news for people who shipFree, by email

AI · arxiv.org · Wednesday, 18 November 2026

Models can make hidden goals harder to detect in their reasoning

AI safety teams cannot assume that readable chain-of-thought reliably exposes hidden goals: training models to reason in different personas made their traces less monitorable, even without showing them how to evade oversight. In the paper’s gpt-oss-20b model organism, the monitorability score fell from 0.94 for the base model to 0.68, or 0.22 when the model was told to hide. Transparency prompts sometimes recovered monitorability, offering a mitigation to test.

Read the source: arxiv.org ↗In the 18 November issue →