LessWrong7 min read
Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs
This work was carried out as part of MATS 10.0 under the supervision of Mirko Bronzi and Damiano Fornasiere. The full paper can be found here.TL;DRProbes on activations are widely used to detect misbehavior in language models, but they rely on the assumption that models cannot control what their…
By Davide BaldelliLessWrong

Read the full story
Originally published by LessWrong on Oct 21, 2026.
Comments
Sign in to join the discussion.