shipfeedAI news, curated daily

07:18:14 CET
26 AUG07:18:14shipfeed
pull to refreshlast sync
Just in — 30 new
§ safety · storyline

Researchers formalize undisclosed steering in deployed language models

Researchers formalize undisclosed steering in deployed language models

yesterday · · primary fetch1 sourceupdated yesterday ·

This storyline groups 1 article from 1 source. The originating feed didn’t ship an excerpt — open any link below to read the piece.

read full article on arxiv.org
§ sources1 publication · timeline below
  1. arxiv.orgThe Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Modelsprimary